search

alirezazareian / ovr-cnn

A new framework for open-vocabulary object detection, based on maskrcnn-benchmark
MIT License
226 stars 28 forks source link

How to reproduce the pretrained model? #7

Closed lxtGH closed 3 years ago

lxtGH commented 3 years ago

Hi! @alirezazareian Could you help me on how to reproduce the pretrained ckpt in caption pretraining stage.

alirezazareian commented 3 years ago

This config should reproduce the pretrained checkpoint. What is the image-caption matching accuracy you get after the last epoch? Could you share the logs or tensorboard plot?

lxtGH commented 3 years ago

Here is the log file: https://github.com/lxtGH/ovr-cnn/blob/master/log.txt The Masked Language Modeling Accuracy is nearly zero.

lxtGH commented 3 years ago

Hi! Alireza @alirezazareian I think I found the reason. Again, I pretrained the model again. https://github.com/lxtGH/ovr-cnn/blob/master/log_nex.txt This time the Masked Language Modeling Accuracy is normal. It seems that the pre-train stage is not very stable. I will report the fine-tuning results using this model here.

lxtGH commented 3 years ago

@alirezazareian Hi! still can not reproduce the results for the finetuning stage. AP50_split_seen is much lower than using your pretrained model

lxtGH commented 3 years ago

image

lxtGH commented 3 years ago

@alirezazareian Hi! Could you share your pretraining log for reference? I could find the difference.

lxtGH commented 3 years ago

Or you can desribe the pytorch version your have used?

alirezazareian commented 3 years ago

This should be my training log, although I am not entirely sure as it's been a while since I trained it. Could you find any difference with your log?

2020-08-04 11:05:18,287 maskrcnn_benchmark INFO: Using 8 GPUs
2020-08-04 11:05:18,287 maskrcnn_benchmark INFO: Namespace(config_file='configs/mmss_v07.yaml', distributed=True, local_rank=0, opts=['OUTPUT_DIR', '/home/alireza/runs/vltrain/121'], skip_test=True)
2020-08-04 11:05:18,287 maskrcnn_benchmark INFO: Collecting env info (might take some time)
2020-08-04 11:05:26,791 maskrcnn_benchmark INFO: 
PyTorch version: 1.0.0.dev20190328
Is debug build: No
CUDA used to build PyTorch: 10.0.130

OS: Debian GNU/Linux 9.12 (stretch)
GCC version: (Debian 6.3.0-18+deb9u1) 6.3.0 20170516
CMake version: Could not collect

Python version: 3.6
Is CUDA available: Yes
CUDA runtime version: 10.0.130
GPU models and configuration: 
GPU 0: Tesla V100-SXM2-16GB
GPU 1: Tesla V100-SXM2-16GB
GPU 2: Tesla V100-SXM2-16GB
GPU 3: Tesla V100-SXM2-16GB
GPU 4: Tesla V100-SXM2-16GB
GPU 5: Tesla V100-SXM2-16GB
GPU 6: Tesla V100-SXM2-16GB
GPU 7: Tesla V100-SXM2-16GB

Nvidia driver version: 418.87.01
cuDNN version: Could not collect

Versions of relevant libraries:
[pip3] numpy==1.18.5
[pip3] torch==1.4.0
[pip3] torchvision==0.2.2
[conda] mkl                       2020.1                      217  
[conda] pytorch                   1.4.0           py3.6_cuda10.0.130_cudnn7.6.3_0    pytorch
[conda] pytorch-nightly           1.0.0.dev20190328 py3.6_cuda10.0.130_cudnn7.4.2_0    pytorch
[conda] torchvision               0.2.2                      py_3    pytorch
        Pillow (7.1.2)
2020-08-04 11:05:26,794 maskrcnn_benchmark INFO: Loaded configuration file configs/mmss_v07.yaml
2020-08-04 11:05:26,794 maskrcnn_benchmark INFO: 
MODEL:
  META_ARCHITECTURE: "MMSS-GCNN"
  WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50"
  RESNETS:
    BACKBONE_OUT_CHANNELS: 2048
  BACKBONE:
    CONV_BODY: "R-50-C5"
    FREEZE_CONV_BODY_AT: 0
  LANGUAGE_BACKBONE:
    TYPE: "BERT-Base"
    FREEZE: True
  MMSS_HEAD:
    TYPES: ("GroundingHead", "TransformerHead")
    DEFAULT_HEAD: "GroundingHead"
    TIE_VL_PROJECTION_WEIGHTS: True
    SPATIAL_DROPOUT: 100
    GROUNDING:
      LOCAL_METRIC: "dot"
      GLOBAL_METRIC: "aligned_local"
      ALIGNMENT: "softmax"
      # 100.0 for euclidean, 10.0 for dot, 0.01 for cosine
      ALIGNMENT_TEMPERATURE: 10.0
      LOSS: "cross_entropy"
      # NEGATIVE_MINING: 'random'
      # TRIPLET_MARGIN: 1.0
      ALIGN_WORDS_TO_REGIONS: True
      ALIGN_REGIONS_TO_WORDS: True
    TRANSFORMER:
      MASKED_LANGUAGE_MODELING: True
      MASKED_LANGUAGE_MODELING_VALIDATION: False
      MASKED_VISUAL_MODELING: False
      MVM_LOSS: ''
      MMM_LOSS: 'cross_entropy'
      BERT_CONFIG:
        num_hidden_layers: 6
        num_attention_heads: 8
        intermediate_size: 768
DATASETS:
  TRAIN: ("coco_captions_train",)
  TEST: ("coco_captions_val",)
  DATASET_CLASS: "COCOCaptionsDataset"
SOLVER:
  BASE_LR: 0.01
  WEIGHT_DECAY: 0.0001
  STEPS: (20000, 35000)
  MAX_ITER: 40000
  IMS_PER_BATCH: 64
  TEST_PERIOD: 1000
  CHECKPOINT_PERIOD: 1000
  LOG_PERIOD: 100
  CLIP_GRAD_NORM_AT: 5.0
  GRADIENT_ACCUMULATION_STEPS: 1
  USE_TRAIN_MODE_FOR_VALIDATION_LOSS: False
TEST:
  DO_EVAL: False
  IMS_PER_BATCH: 64

2020-08-04 11:05:26,795 maskrcnn_benchmark INFO: Running with config:
AMP_VERBOSE: False
DATALOADER:
  ASPECT_RATIO_GROUPING: True
  NUM_WORKERS: 4
  SIZE_DIVISIBILITY: 0
DATASETS:
  DATASET_ARGS:
    LOAD_EMBEDDINGS: False
  DATASET_CLASS: COCOCaptionsDataset
  TEST: ('coco_captions_val',)
  TRAIN: ('coco_captions_train',)
DTYPE: float32
INPUT:
  BRIGHTNESS: 0.0
  CONTRAST: 0.0
  HORIZONTAL_FLIP_PROB_TRAIN: 0.5
  HUE: 0.0
  MAX_SIZE_TEST: 1333
  MAX_SIZE_TRAIN: 1333
  MIN_SIZE_TEST: 800
  MIN_SIZE_TRAIN: (800,)
  PIXEL_MEAN: [102.9801, 115.9465, 122.7717]
  PIXEL_STD: [1.0, 1.0, 1.0]
  SATURATION: 0.0
  TO_BGR255: True
  VERTICAL_FLIP_PROB_TRAIN: 0.0
MODEL:
  BACKBONE:
    CONV_BODY: R-50-C5
    FREEZE_CONV_BODY_AT: 0
  CLS_AGNOSTIC_BBOX_REG: False
  DEVICE: cuda
  FBNET:
    ARCH: default
    ARCH_DEF: 
    BN_TYPE: bn
    DET_HEAD_BLOCKS: []
    DET_HEAD_LAST_SCALE: 1.0
    DET_HEAD_STRIDE: 0
    DW_CONV_SKIP_BN: True
    DW_CONV_SKIP_RELU: True
    KPTS_HEAD_BLOCKS: []
    KPTS_HEAD_LAST_SCALE: 0.0
    KPTS_HEAD_STRIDE: 0
    MASK_HEAD_BLOCKS: []
    MASK_HEAD_LAST_SCALE: 0.0
    MASK_HEAD_STRIDE: 0
    RPN_BN_TYPE: 
    RPN_HEAD_BLOCKS: 0
    SCALE_FACTOR: 1.0
    WIDTH_DIVISOR: 1
  FPN:
    USE_GN: False
    USE_RELU: False
  GROUP_NORM:
    DIM_PER_GP: -1
    EPSILON: 1e-05
    NUM_GROUPS: 32
  KEYPOINT_ON: False
  LANGUAGE_BACKBONE:
    ADD_POSITION_EMBEDDING: False
    EMBEDDING_PATH: 
    FREEZE: True
    TYPE: BERT-Base
  LOAD_EMB_PRED_FROM_MMSS_HEAD: False
  LOAD_LAYER4_FROM_BACKBONE: False
  LOAD_TRAINER_STATE: True
  MASK_ON: False
  META_ARCHITECTURE: MMSS-GCNN
  MMSS_HEAD:
    DEFAULT_HEAD: GroundingHead
    GROUNDING:
      ALIGNMENT: softmax
      ALIGNMENT_TEMPERATURE: 10.0
      ALIGN_REGIONS_TO_WORDS: True
      ALIGN_WORDS_TO_REGIONS: True
      GLOBAL_METRIC: aligned_local
      LOCAL_METRIC: dot
      LOSS: cross_entropy
      NEGATIVE_MINING: random
      TRIPLET_MARGIN: 1.0
    SPATIAL_DROPOUT: 100
    TIE_VL_PROJECTION_WEIGHTS: True
    TRANSFORMER:
      BERT_CONFIG:
        attention_probs_dropout_prob: 0.1
        gradient_checkpointing: False
        hidden_act: gelu
        hidden_dropout_prob: 0.1
        hidden_size: 768
        initializer_range: 0.02
        intermediate_size: 768
        layer_norm_eps: 1e-12
        max_position_embeddings: 512
        num_attention_heads: 8
        num_hidden_layers: 6
        pad_token_id: 0
        type_vocab_size: 2
        vocab_size: 30522
      MASKED_LANGUAGE_MODELING: True
      MASKED_LANGUAGE_MODELING_PROB: 0.15
      MASKED_LANGUAGE_MODELING_PROB_MASK: 0.9
      MASKED_LANGUAGE_MODELING_PROB_NOISE: 0.0
      MASKED_LANGUAGE_MODELING_VALIDATION: False
      MASKED_VISUAL_MODELING: False
      MMM_LOSS: cross_entropy
      MVM_LOSS: 
      MVM_LOSS_NUM_NEGATIVE: 128
    TYPES: ('GroundingHead', 'TransformerHead')
  RESNETS:
    BACKBONE_OUT_CHANNELS: 2048
    DEFORMABLE_GROUPS: 1
    NUM_GROUPS: 1
    RES2_OUT_CHANNELS: 256
    RES5_DILATION: 1
    STAGE_WITH_DCN: (False, False, False, False)
    STEM_FUNC: StemWithFixedBatchNorm
    STEM_OUT_CHANNELS: 64
    STRIDE_IN_1X1: True
    TRANS_FUNC: BottleneckWithFixedBatchNorm
    WIDTH_PER_GROUP: 64
    WITH_MODULATED_DCN: False
  RETINANET:
    ANCHOR_SIZES: (32, 64, 128, 256, 512)
    ANCHOR_STRIDES: (8, 16, 32, 64, 128)
    ASPECT_RATIOS: (0.5, 1.0, 2.0)
    BBOX_REG_BETA: 0.11
    BBOX_REG_WEIGHT: 4.0
    BG_IOU_THRESHOLD: 0.4
    FG_IOU_THRESHOLD: 0.5
    INFERENCE_TH: 0.05
    LOSS_ALPHA: 0.25
    LOSS_GAMMA: 2.0
    NMS_TH: 0.4
    NUM_CLASSES: 81
    NUM_CONVS: 4
    OCTAVE: 2.0
    PRE_NMS_TOP_N: 1000
    PRIOR_PROB: 0.01
    SCALES_PER_OCTAVE: 3
    STRADDLE_THRESH: 0
    USE_C5: True
  RETINANET_ON: False
  ROI_BOX_HEAD:
    CONV_HEAD_DIM: 256
    DILATION: 1
    EMBEDDING_BASED: False
    EMB_DIM: 300
    FEATURE_EXTRACTOR: ResNet50Conv5ROIFeatureExtractor
    FREEZE_EMB_PRED: False
    FREEZE_FEATURE_EXTRACTOR: False
    LOSS_WEIGHT_BACKGROUND: 1.0
    MLP_HEAD_DIM: 1024
    NUM_CLASSES: 81
    NUM_STACKED_CONVS: 4
    POOLER_RESOLUTION: 14
    POOLER_SAMPLING_RATIO: 0
    POOLER_SCALES: (0.0625,)
    PREDICTOR: FastRCNNPredictor
    USE_GN: False
  ROI_HEADS:
    BATCH_SIZE_PER_IMAGE: 512
    BBOX_REG_WEIGHTS: (10.0, 10.0, 5.0, 5.0)
    BG_IOU_THRESHOLD: 0.5
    DETECTIONS_PER_IMG: 100
    FG_IOU_THRESHOLD: 0.5
    NMS: 0.5
    POSITIVE_FRACTION: 0.25
    SCORE_THRESH: 0.05
    USE_FPN: False
  ROI_KEYPOINT_HEAD:
    CONV_LAYERS: (512, 512, 512, 512, 512, 512, 512, 512)
    FEATURE_EXTRACTOR: KeypointRCNNFeatureExtractor
    MLP_HEAD_DIM: 1024
    NUM_CLASSES: 17
    POOLER_RESOLUTION: 14
    POOLER_SAMPLING_RATIO: 0
    POOLER_SCALES: (0.0625,)
    PREDICTOR: KeypointRCNNPredictor
    RESOLUTION: 14
    SHARE_BOX_FEATURE_EXTRACTOR: True
  ROI_MASK_HEAD:
    CONV_LAYERS: (256, 256, 256, 256)
    DILATION: 1
    FEATURE_EXTRACTOR: ResNet50Conv5ROIFeatureExtractor
    MLP_HEAD_DIM: 1024
    POOLER_RESOLUTION: 14
    POOLER_SAMPLING_RATIO: 0
    POOLER_SCALES: (0.0625,)
    POSTPROCESS_MASKS: False
    POSTPROCESS_MASKS_THRESHOLD: 0.5
    PREDICTOR: MaskRCNNC4Predictor
    RESOLUTION: 14
    SHARE_BOX_FEATURE_EXTRACTOR: True
    USE_GN: False
  RPN:
    ANCHOR_SIZES: (32, 64, 128, 256, 512)
    ANCHOR_STRIDE: (16,)
    ASPECT_RATIOS: (0.5, 1.0, 2.0)
    BATCH_SIZE_PER_IMAGE: 256
    BG_IOU_THRESHOLD: 0.3
    FG_IOU_THRESHOLD: 0.7
    FPN_POST_NMS_PER_BATCH: True
    FPN_POST_NMS_TOP_N_TEST: 2000
    FPN_POST_NMS_TOP_N_TRAIN: 2000
    MIN_SIZE: 0
    NMS_THRESH: 0.7
    POSITIVE_FRACTION: 0.5
    POST_NMS_TOP_N_TEST: 1000
    POST_NMS_TOP_N_TRAIN: 2000
    PRE_NMS_TOP_N_TEST: 6000
    PRE_NMS_TOP_N_TRAIN: 12000
    RPN_HEAD: SingleConvRPNHead
    STRADDLE_THRESH: 0
    USE_FPN: False
  RPN_ONLY: False
  WEIGHT: catalog://ImageNetPretrained/MSRA/R-50
OUTPUT_DIR: /home/alireza/runs/vltrain/121
PATHS_CATALOG: /home/alireza/maskrcnn/maskrcnn_benchmark/config/paths_catalog.py
SOLVER:
  BASE_LR: 0.01
  BIAS_LR_FACTOR: 2
  CHECKPOINT_PERIOD: 1000
  CLIP_GRAD_NORM_AT: 5.0
  GAMMA: 0.1
  GRADIENT_ACCUMULATION_STEPS: 1
  IMS_PER_BATCH: 64
  LOG_PERIOD: 100
  MAX_ITER: 40000
  MOMENTUM: 0.9
  STEPS: (20000, 35000)
  TEST_PERIOD: 1000
  USE_TRAIN_MODE_FOR_VALIDATION_LOSS: False
  WARMUP_FACTOR: 0.3333333333333333
  WARMUP_ITERS: 500
  WARMUP_METHOD: linear
  WEIGHT_DECAY: 0.0001
  WEIGHT_DECAY_BIAS: 0
TEST:
  BBOX_AUG:
    ENABLED: False
    H_FLIP: False
    MAX_SIZE: 4000
    SCALES: ()
    SCALE_H_FLIP: False
  DETECTIONS_PER_IMG: 100
  DO_EVAL: False
  EXPECTED_RESULTS: []
  EXPECTED_RESULTS_SIGMA_TOL: 4
  IMS_PER_BATCH: 64
2020-08-04 11:05:26,795 maskrcnn_benchmark INFO: Saving config into: /home/alireza/runs/vltrain/121/config.yml
2020-08-04 11:05:32,401 maskrcnn_benchmark.make_optimizer INFO: The following parameters will be trained: 
2020-08-04 11:05:32,401 maskrcnn_benchmark.make_optimizer INFO: backbone.body.stem.conv1.weight
2020-08-04 11:05:32,401 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer1.0.downsample.0.weight
2020-08-04 11:05:32,402 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer1.0.conv1.weight
2020-08-04 11:05:32,402 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer1.0.conv2.weight
2020-08-04 11:05:32,402 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer1.0.conv3.weight
2020-08-04 11:05:32,402 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer1.1.conv1.weight
2020-08-04 11:05:32,402 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer1.1.conv2.weight
2020-08-04 11:05:32,402 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer1.1.conv3.weight
2020-08-04 11:05:32,402 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer1.2.conv1.weight
2020-08-04 11:05:32,402 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer1.2.conv2.weight
2020-08-04 11:05:32,402 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer1.2.conv3.weight
2020-08-04 11:05:32,402 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer2.0.downsample.0.weight
2020-08-04 11:05:32,402 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer2.0.conv1.weight
2020-08-04 11:05:32,402 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer2.0.conv2.weight
2020-08-04 11:05:32,402 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer2.0.conv3.weight
2020-08-04 11:05:32,402 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer2.1.conv1.weight
2020-08-04 11:05:32,402 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer2.1.conv2.weight
2020-08-04 11:05:32,403 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer2.1.conv3.weight
2020-08-04 11:05:32,403 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer2.2.conv1.weight
2020-08-04 11:05:32,403 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer2.2.conv2.weight
2020-08-04 11:05:32,403 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer2.2.conv3.weight
2020-08-04 11:05:32,403 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer2.3.conv1.weight
2020-08-04 11:05:32,403 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer2.3.conv2.weight
2020-08-04 11:05:32,403 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer2.3.conv3.weight
2020-08-04 11:05:32,403 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer3.0.downsample.0.weight
2020-08-04 11:05:32,403 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer3.0.conv1.weight
2020-08-04 11:05:32,403 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer3.0.conv2.weight
2020-08-04 11:05:32,403 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer3.0.conv3.weight
2020-08-04 11:05:32,403 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer3.1.conv1.weight
2020-08-04 11:05:32,403 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer3.1.conv2.weight
2020-08-04 11:05:32,403 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer3.1.conv3.weight
2020-08-04 11:05:32,403 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer3.2.conv1.weight
2020-08-04 11:05:32,403 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer3.2.conv2.weight
2020-08-04 11:05:32,403 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer3.2.conv3.weight
2020-08-04 11:05:32,404 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer3.3.conv1.weight
2020-08-04 11:05:32,404 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer3.3.conv2.weight
2020-08-04 11:05:32,404 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer3.3.conv3.weight
2020-08-04 11:05:32,404 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer3.4.conv1.weight
2020-08-04 11:05:32,404 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer3.4.conv2.weight
2020-08-04 11:05:32,404 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer3.4.conv3.weight
2020-08-04 11:05:32,404 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer3.5.conv1.weight
2020-08-04 11:05:32,404 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer3.5.conv2.weight
2020-08-04 11:05:32,404 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer3.5.conv3.weight
2020-08-04 11:05:32,404 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer4.0.downsample.0.weight
2020-08-04 11:05:32,404 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer4.0.conv1.weight
2020-08-04 11:05:32,404 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer4.0.conv2.weight
2020-08-04 11:05:32,404 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer4.0.conv3.weight
2020-08-04 11:05:32,404 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer4.1.conv1.weight
2020-08-04 11:05:32,404 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer4.1.conv2.weight
2020-08-04 11:05:32,404 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer4.1.conv3.weight
2020-08-04 11:05:32,405 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer4.2.conv1.weight
2020-08-04 11:05:32,405 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer4.2.conv2.weight
2020-08-04 11:05:32,405 maskrcnn_benchmark.make_optimizer INFO: backbone.body.layer4.2.conv3.weight
2020-08-04 11:05:32,406 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.GroundingHead.v2l_projection.weight
2020-08-04 11:05:32,406 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.GroundingHead.v2l_projection.bias
2020-08-04 11:05:32,406 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.visual_emb.image_embeddings.weight
2020-08-04 11:05:32,406 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.visual_emb.image_embeddings.bias
2020-08-04 11:05:32,406 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.visual_emb.image_location_embeddings.weight
2020-08-04 11:05:32,406 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.visual_emb.image_location_embeddings.bias
2020-08-04 11:05:32,406 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.visual_emb.LayerNorm.weight
2020-08-04 11:05:32,406 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.visual_emb.LayerNorm.bias
2020-08-04 11:05:32,406 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.0.attention.self.query.weight
2020-08-04 11:05:32,407 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.0.attention.self.query.bias
2020-08-04 11:05:32,407 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.0.attention.self.key.weight
2020-08-04 11:05:32,407 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.0.attention.self.key.bias
2020-08-04 11:05:32,407 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.0.attention.self.value.weight
2020-08-04 11:05:32,407 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.0.attention.self.value.bias
2020-08-04 11:05:32,407 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.0.attention.output.dense.weight
2020-08-04 11:05:32,407 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.0.attention.output.dense.bias
2020-08-04 11:05:32,407 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.0.attention.output.LayerNorm.weight
2020-08-04 11:05:32,407 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.0.attention.output.LayerNorm.bias
2020-08-04 11:05:32,407 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.0.intermediate.dense.weight
2020-08-04 11:05:32,407 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.0.intermediate.dense.bias
2020-08-04 11:05:32,407 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.0.output.dense.weight
2020-08-04 11:05:32,407 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.0.output.dense.bias
2020-08-04 11:05:32,407 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.0.output.LayerNorm.weight
2020-08-04 11:05:32,407 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.0.output.LayerNorm.bias
2020-08-04 11:05:32,408 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.1.attention.self.query.weight
2020-08-04 11:05:32,408 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.1.attention.self.query.bias
2020-08-04 11:05:32,408 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.1.attention.self.key.weight
2020-08-04 11:05:32,408 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.1.attention.self.key.bias
2020-08-04 11:05:32,408 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.1.attention.self.value.weight
2020-08-04 11:05:32,408 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.1.attention.self.value.bias
2020-08-04 11:05:32,408 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.1.attention.output.dense.weight
2020-08-04 11:05:32,408 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.1.attention.output.dense.bias
2020-08-04 11:05:32,408 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.1.attention.output.LayerNorm.weight
2020-08-04 11:05:32,408 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.1.attention.output.LayerNorm.bias
2020-08-04 11:05:32,408 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.1.intermediate.dense.weight
2020-08-04 11:05:32,408 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.1.intermediate.dense.bias
2020-08-04 11:05:32,408 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.1.output.dense.weight
2020-08-04 11:05:32,408 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.1.output.dense.bias
2020-08-04 11:05:32,408 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.1.output.LayerNorm.weight
2020-08-04 11:05:32,408 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.1.output.LayerNorm.bias
2020-08-04 11:05:32,408 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.2.attention.self.query.weight
2020-08-04 11:05:32,409 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.2.attention.self.query.bias
2020-08-04 11:05:32,409 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.2.attention.self.key.weight
2020-08-04 11:05:32,409 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.2.attention.self.key.bias
2020-08-04 11:05:32,409 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.2.attention.self.value.weight
2020-08-04 11:05:32,409 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.2.attention.self.value.bias
2020-08-04 11:05:32,409 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.2.attention.output.dense.weight
2020-08-04 11:05:32,409 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.2.attention.output.dense.bias
2020-08-04 11:05:32,409 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.2.attention.output.LayerNorm.weight
2020-08-04 11:05:32,409 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.2.attention.output.LayerNorm.bias
2020-08-04 11:05:32,409 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.2.intermediate.dense.weight
2020-08-04 11:05:32,409 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.2.intermediate.dense.bias
2020-08-04 11:05:32,409 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.2.output.dense.weight
2020-08-04 11:05:32,409 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.2.output.dense.bias
2020-08-04 11:05:32,409 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.2.output.LayerNorm.weight
2020-08-04 11:05:32,409 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.2.output.LayerNorm.bias
2020-08-04 11:05:32,410 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.3.attention.self.query.weight
2020-08-04 11:05:32,410 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.3.attention.self.query.bias
2020-08-04 11:05:32,410 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.3.attention.self.key.weight
2020-08-04 11:05:32,410 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.3.attention.self.key.bias
2020-08-04 11:05:32,410 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.3.attention.self.value.weight
2020-08-04 11:05:32,410 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.3.attention.self.value.bias
2020-08-04 11:05:32,410 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.3.attention.output.dense.weight
2020-08-04 11:05:32,410 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.3.attention.output.dense.bias
2020-08-04 11:05:32,410 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.3.attention.output.LayerNorm.weight
2020-08-04 11:05:32,410 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.3.attention.output.LayerNorm.bias
2020-08-04 11:05:32,410 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.3.intermediate.dense.weight
2020-08-04 11:05:32,410 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.3.intermediate.dense.bias
2020-08-04 11:05:32,410 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.3.output.dense.weight
2020-08-04 11:05:32,410 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.3.output.dense.bias
2020-08-04 11:05:32,410 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.3.output.LayerNorm.weight
2020-08-04 11:05:32,411 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.3.output.LayerNorm.bias
2020-08-04 11:05:32,411 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.4.attention.self.query.weight
2020-08-04 11:05:32,411 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.4.attention.self.query.bias
2020-08-04 11:05:32,411 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.4.attention.self.key.weight
2020-08-04 11:05:32,411 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.4.attention.self.key.bias
2020-08-04 11:05:32,411 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.4.attention.self.value.weight
2020-08-04 11:05:32,411 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.4.attention.self.value.bias
2020-08-04 11:05:32,411 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.4.attention.output.dense.weight
2020-08-04 11:05:32,411 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.4.attention.output.dense.bias
2020-08-04 11:05:32,411 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.4.attention.output.LayerNorm.weight
2020-08-04 11:05:32,411 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.4.attention.output.LayerNorm.bias
2020-08-04 11:05:32,411 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.4.intermediate.dense.weight
2020-08-04 11:05:32,411 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.4.intermediate.dense.bias
2020-08-04 11:05:32,411 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.4.output.dense.weight
2020-08-04 11:05:32,411 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.4.output.dense.bias
2020-08-04 11:05:32,411 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.4.output.LayerNorm.weight
2020-08-04 11:05:32,411 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.4.output.LayerNorm.bias
2020-08-04 11:05:32,412 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.5.attention.self.query.weight
2020-08-04 11:05:32,412 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.5.attention.self.query.bias
2020-08-04 11:05:32,412 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.5.attention.self.key.weight
2020-08-04 11:05:32,412 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.5.attention.self.key.bias
2020-08-04 11:05:32,412 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.5.attention.self.value.weight
2020-08-04 11:05:32,412 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.5.attention.self.value.bias
2020-08-04 11:05:32,412 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.5.attention.output.dense.weight
2020-08-04 11:05:32,412 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.5.attention.output.dense.bias
2020-08-04 11:05:32,412 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.5.attention.output.LayerNorm.weight
2020-08-04 11:05:32,412 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.5.attention.output.LayerNorm.bias
2020-08-04 11:05:32,412 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.5.intermediate.dense.weight
2020-08-04 11:05:32,412 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.5.intermediate.dense.bias
2020-08-04 11:05:32,412 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.5.output.dense.weight
2020-08-04 11:05:32,412 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.5.output.dense.bias
2020-08-04 11:05:32,413 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.5.output.LayerNorm.weight
2020-08-04 11:05:32,413 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.encoder.layer.5.output.LayerNorm.bias
2020-08-04 11:05:32,413 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.pooler.dense.weight
2020-08-04 11:05:32,413 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.pooler.dense.bias
2020-08-04 11:05:32,413 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.heads.predictions.bias
2020-08-04 11:05:32,413 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.heads.predictions.transform.dense.weight
2020-08-04 11:05:32,413 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.heads.predictions.transform.dense.bias
2020-08-04 11:05:32,413 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.heads.predictions.transform.LayerNorm.weight
2020-08-04 11:05:32,413 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.heads.predictions.transform.LayerNorm.bias
2020-08-04 11:05:32,413 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.heads.bi_seq_relationship.weight
2020-08-04 11:05:32,413 maskrcnn_benchmark.make_optimizer INFO: mmss_heads.TransformerHead.heads.bi_seq_relationship.bias
2020-08-04 11:05:32,780 maskrcnn_benchmark.utils.checkpoint INFO: Loading checkpoint from catalog://ImageNetPretrained/MSRA/R-50
2020-08-04 11:05:32,780 maskrcnn_benchmark.utils.checkpoint INFO: catalog://ImageNetPretrained/MSRA/R-50 points to https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/MSRA/R-50.pkl
2020-08-04 11:05:33,118 maskrcnn_benchmark.utils.checkpoint INFO: url https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/MSRA/R-50.pkl cached in /home/alireza/.torch/models/R-50.pkl
2020-08-04 11:05:33,398 maskrcnn_benchmark.utils.c2_model_loading INFO: Remapping C2 weights
2020-08-04 11:05:33,398 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: conv1_b              mapped name: conv1.bias
2020-08-04 11:05:33,398 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: conv1_w              mapped name: conv1.weight
2020-08-04 11:05:33,398 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: fc1000_b             mapped name: fc1000.bias
2020-08-04 11:05:33,399 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: fc1000_w             mapped name: fc1000.weight
2020-08-04 11:05:33,399 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch1_b     mapped name: layer1.0.downsample.0.bias
2020-08-04 11:05:33,399 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch1_bn_b  mapped name: layer1.0.downsample.1.bias
2020-08-04 11:05:33,399 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch1_bn_s  mapped name: layer1.0.downsample.1.weight
2020-08-04 11:05:33,399 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch1_w     mapped name: layer1.0.downsample.0.weight
2020-08-04 11:05:33,399 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2a_b    mapped name: layer1.0.conv1.bias
2020-08-04 11:05:33,399 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2a_bn_b mapped name: layer1.0.bn1.bias
2020-08-04 11:05:33,399 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2a_bn_s mapped name: layer1.0.bn1.weight
2020-08-04 11:05:33,399 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2a_w    mapped name: layer1.0.conv1.weight
2020-08-04 11:05:33,399 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2b_b    mapped name: layer1.0.conv2.bias
2020-08-04 11:05:33,399 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2b_bn_b mapped name: layer1.0.bn2.bias
2020-08-04 11:05:33,399 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2b_bn_s mapped name: layer1.0.bn2.weight
2020-08-04 11:05:33,399 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2b_w    mapped name: layer1.0.conv2.weight
2020-08-04 11:05:33,399 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2c_b    mapped name: layer1.0.conv3.bias
2020-08-04 11:05:33,399 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2c_bn_b mapped name: layer1.0.bn3.bias
2020-08-04 11:05:33,399 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2c_bn_s mapped name: layer1.0.bn3.weight
2020-08-04 11:05:33,399 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2c_w    mapped name: layer1.0.conv3.weight
2020-08-04 11:05:33,400 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2a_b    mapped name: layer1.1.conv1.bias
2020-08-04 11:05:33,400 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2a_bn_b mapped name: layer1.1.bn1.bias
2020-08-04 11:05:33,400 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2a_bn_s mapped name: layer1.1.bn1.weight
2020-08-04 11:05:33,400 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2a_w    mapped name: layer1.1.conv1.weight
2020-08-04 11:05:33,400 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2b_b    mapped name: layer1.1.conv2.bias
2020-08-04 11:05:33,400 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2b_bn_b mapped name: layer1.1.bn2.bias
2020-08-04 11:05:33,400 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2b_bn_s mapped name: layer1.1.bn2.weight
2020-08-04 11:05:33,400 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2b_w    mapped name: layer1.1.conv2.weight
2020-08-04 11:05:33,400 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2c_b    mapped name: layer1.1.conv3.bias
2020-08-04 11:05:33,400 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2c_bn_b mapped name: layer1.1.bn3.bias
2020-08-04 11:05:33,400 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2c_bn_s mapped name: layer1.1.bn3.weight
2020-08-04 11:05:33,400 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2c_w    mapped name: layer1.1.conv3.weight
2020-08-04 11:05:33,400 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2a_b    mapped name: layer1.2.conv1.bias
2020-08-04 11:05:33,400 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2a_bn_b mapped name: layer1.2.bn1.bias
2020-08-04 11:05:33,400 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2a_bn_s mapped name: layer1.2.bn1.weight
2020-08-04 11:05:33,400 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2a_w    mapped name: layer1.2.conv1.weight
2020-08-04 11:05:33,400 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2b_b    mapped name: layer1.2.conv2.bias
2020-08-04 11:05:33,400 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2b_bn_b mapped name: layer1.2.bn2.bias
2020-08-04 11:05:33,401 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2b_bn_s mapped name: layer1.2.bn2.weight
2020-08-04 11:05:33,401 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2b_w    mapped name: layer1.2.conv2.weight
2020-08-04 11:05:33,401 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2c_b    mapped name: layer1.2.conv3.bias
2020-08-04 11:05:33,401 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2c_bn_b mapped name: layer1.2.bn3.bias
2020-08-04 11:05:33,401 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2c_bn_s mapped name: layer1.2.bn3.weight
2020-08-04 11:05:33,401 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2c_w    mapped name: layer1.2.conv3.weight
2020-08-04 11:05:33,401 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch1_b     mapped name: layer2.0.downsample.0.bias
2020-08-04 11:05:33,401 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch1_bn_b  mapped name: layer2.0.downsample.1.bias
2020-08-04 11:05:33,401 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch1_bn_s  mapped name: layer2.0.downsample.1.weight
2020-08-04 11:05:33,401 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch1_w     mapped name: layer2.0.downsample.0.weight
2020-08-04 11:05:33,401 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2a_b    mapped name: layer2.0.conv1.bias
2020-08-04 11:05:33,401 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2a_bn_b mapped name: layer2.0.bn1.bias
2020-08-04 11:05:33,401 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2a_bn_s mapped name: layer2.0.bn1.weight
2020-08-04 11:05:33,401 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2a_w    mapped name: layer2.0.conv1.weight
2020-08-04 11:05:33,401 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2b_b    mapped name: layer2.0.conv2.bias
2020-08-04 11:05:33,401 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2b_bn_b mapped name: layer2.0.bn2.bias
2020-08-04 11:05:33,401 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2b_bn_s mapped name: layer2.0.bn2.weight
2020-08-04 11:05:33,401 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2b_w    mapped name: layer2.0.conv2.weight
2020-08-04 11:05:33,402 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2c_b    mapped name: layer2.0.conv3.bias
2020-08-04 11:05:33,402 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2c_bn_b mapped name: layer2.0.bn3.bias
2020-08-04 11:05:33,402 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2c_bn_s mapped name: layer2.0.bn3.weight
2020-08-04 11:05:33,402 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2c_w    mapped name: layer2.0.conv3.weight
2020-08-04 11:05:33,402 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2a_b    mapped name: layer2.1.conv1.bias
2020-08-04 11:05:33,402 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2a_bn_b mapped name: layer2.1.bn1.bias
2020-08-04 11:05:33,402 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2a_bn_s mapped name: layer2.1.bn1.weight
2020-08-04 11:05:33,402 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2a_w    mapped name: layer2.1.conv1.weight
2020-08-04 11:05:33,402 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2b_b    mapped name: layer2.1.conv2.bias
2020-08-04 11:05:33,402 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2b_bn_b mapped name: layer2.1.bn2.bias
2020-08-04 11:05:33,402 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2b_bn_s mapped name: layer2.1.bn2.weight
2020-08-04 11:05:33,402 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2b_w    mapped name: layer2.1.conv2.weight
2020-08-04 11:05:33,402 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2c_b    mapped name: layer2.1.conv3.bias
2020-08-04 11:05:33,402 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2c_bn_b mapped name: layer2.1.bn3.bias
2020-08-04 11:05:33,402 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2c_bn_s mapped name: layer2.1.bn3.weight
2020-08-04 11:05:33,402 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2c_w    mapped name: layer2.1.conv3.weight
2020-08-04 11:05:33,402 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2a_b    mapped name: layer2.2.conv1.bias
2020-08-04 11:05:33,402 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2a_bn_b mapped name: layer2.2.bn1.bias
2020-08-04 11:05:33,402 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2a_bn_s mapped name: layer2.2.bn1.weight
2020-08-04 11:05:33,403 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2a_w    mapped name: layer2.2.conv1.weight
2020-08-04 11:05:33,403 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2b_b    mapped name: layer2.2.conv2.bias
2020-08-04 11:05:33,403 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2b_bn_b mapped name: layer2.2.bn2.bias
2020-08-04 11:05:33,403 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2b_bn_s mapped name: layer2.2.bn2.weight
2020-08-04 11:05:33,403 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2b_w    mapped name: layer2.2.conv2.weight
2020-08-04 11:05:33,403 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2c_b    mapped name: layer2.2.conv3.bias
2020-08-04 11:05:33,403 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2c_bn_b mapped name: layer2.2.bn3.bias
2020-08-04 11:05:33,403 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2c_bn_s mapped name: layer2.2.bn3.weight
2020-08-04 11:05:33,403 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2c_w    mapped name: layer2.2.conv3.weight
2020-08-04 11:05:33,403 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2a_b    mapped name: layer2.3.conv1.bias
2020-08-04 11:05:33,403 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2a_bn_b mapped name: layer2.3.bn1.bias
2020-08-04 11:05:33,403 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2a_bn_s mapped name: layer2.3.bn1.weight
2020-08-04 11:05:33,403 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2a_w    mapped name: layer2.3.conv1.weight
2020-08-04 11:05:33,403 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2b_b    mapped name: layer2.3.conv2.bias
2020-08-04 11:05:33,403 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2b_bn_b mapped name: layer2.3.bn2.bias
2020-08-04 11:05:33,403 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2b_bn_s mapped name: layer2.3.bn2.weight
2020-08-04 11:05:33,403 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2b_w    mapped name: layer2.3.conv2.weight
2020-08-04 11:05:33,403 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2c_b    mapped name: layer2.3.conv3.bias
2020-08-04 11:05:33,404 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2c_bn_b mapped name: layer2.3.bn3.bias
2020-08-04 11:05:33,404 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2c_bn_s mapped name: layer2.3.bn3.weight
2020-08-04 11:05:33,404 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2c_w    mapped name: layer2.3.conv3.weight
2020-08-04 11:05:33,404 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch1_b     mapped name: layer3.0.downsample.0.bias
2020-08-04 11:05:33,404 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch1_bn_b  mapped name: layer3.0.downsample.1.bias
2020-08-04 11:05:33,404 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch1_bn_s  mapped name: layer3.0.downsample.1.weight
2020-08-04 11:05:33,404 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch1_w     mapped name: layer3.0.downsample.0.weight
2020-08-04 11:05:33,404 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2a_b    mapped name: layer3.0.conv1.bias
2020-08-04 11:05:33,404 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2a_bn_b mapped name: layer3.0.bn1.bias
2020-08-04 11:05:33,404 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2a_bn_s mapped name: layer3.0.bn1.weight
2020-08-04 11:05:33,404 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2a_w    mapped name: layer3.0.conv1.weight
2020-08-04 11:05:33,404 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2b_b    mapped name: layer3.0.conv2.bias
2020-08-04 11:05:33,404 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2b_bn_b mapped name: layer3.0.bn2.bias
2020-08-04 11:05:33,404 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2b_bn_s mapped name: layer3.0.bn2.weight
2020-08-04 11:05:33,404 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2b_w    mapped name: layer3.0.conv2.weight
2020-08-04 11:05:33,404 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2c_b    mapped name: layer3.0.conv3.bias
2020-08-04 11:05:33,404 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2c_bn_b mapped name: layer3.0.bn3.bias
2020-08-04 11:05:33,404 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2c_bn_s mapped name: layer3.0.bn3.weight
2020-08-04 11:05:33,405 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2c_w    mapped name: layer3.0.conv3.weight
2020-08-04 11:05:33,405 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2a_b    mapped name: layer3.1.conv1.bias
2020-08-04 11:05:33,405 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2a_bn_b mapped name: layer3.1.bn1.bias
2020-08-04 11:05:33,405 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2a_bn_s mapped name: layer3.1.bn1.weight
2020-08-04 11:05:33,405 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2a_w    mapped name: layer3.1.conv1.weight
2020-08-04 11:05:33,405 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2b_b    mapped name: layer3.1.conv2.bias
2020-08-04 11:05:33,405 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2b_bn_b mapped name: layer3.1.bn2.bias
2020-08-04 11:05:33,405 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2b_bn_s mapped name: layer3.1.bn2.weight
2020-08-04 11:05:33,405 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2b_w    mapped name: layer3.1.conv2.weight
2020-08-04 11:05:33,405 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2c_b    mapped name: layer3.1.conv3.bias
2020-08-04 11:05:33,405 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2c_bn_b mapped name: layer3.1.bn3.bias
2020-08-04 11:05:33,405 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2c_bn_s mapped name: layer3.1.bn3.weight
2020-08-04 11:05:33,405 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2c_w    mapped name: layer3.1.conv3.weight
2020-08-04 11:05:33,405 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2a_b    mapped name: layer3.2.conv1.bias
2020-08-04 11:05:33,405 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2a_bn_b mapped name: layer3.2.bn1.bias
2020-08-04 11:05:33,405 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2a_bn_s mapped name: layer3.2.bn1.weight
2020-08-04 11:05:33,405 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2a_w    mapped name: layer3.2.conv1.weight
2020-08-04 11:05:33,405 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2b_b    mapped name: layer3.2.conv2.bias
2020-08-04 11:05:33,405 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2b_bn_b mapped name: layer3.2.bn2.bias
2020-08-04 11:05:33,406 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2b_bn_s mapped name: layer3.2.bn2.weight
2020-08-04 11:05:33,406 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2b_w    mapped name: layer3.2.conv2.weight
2020-08-04 11:05:33,406 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2c_b    mapped name: layer3.2.conv3.bias
2020-08-04 11:05:33,406 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2c_bn_b mapped name: layer3.2.bn3.bias
2020-08-04 11:05:33,406 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2c_bn_s mapped name: layer3.2.bn3.weight
2020-08-04 11:05:33,406 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2c_w    mapped name: layer3.2.conv3.weight
2020-08-04 11:05:33,406 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2a_b    mapped name: layer3.3.conv1.bias
2020-08-04 11:05:33,406 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2a_bn_b mapped name: layer3.3.bn1.bias
2020-08-04 11:05:33,406 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2a_bn_s mapped name: layer3.3.bn1.weight
2020-08-04 11:05:33,406 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2a_w    mapped name: layer3.3.conv1.weight
2020-08-04 11:05:33,406 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2b_b    mapped name: layer3.3.conv2.bias
2020-08-04 11:05:33,406 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2b_bn_b mapped name: layer3.3.bn2.bias
2020-08-04 11:05:33,406 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2b_bn_s mapped name: layer3.3.bn2.weight
2020-08-04 11:05:33,406 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2b_w    mapped name: layer3.3.conv2.weight
2020-08-04 11:05:33,406 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2c_b    mapped name: layer3.3.conv3.bias
2020-08-04 11:05:33,406 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2c_bn_b mapped name: layer3.3.bn3.bias
2020-08-04 11:05:33,406 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2c_bn_s mapped name: layer3.3.bn3.weight
2020-08-04 11:05:33,406 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2c_w    mapped name: layer3.3.conv3.weight
2020-08-04 11:05:33,406 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2a_b    mapped name: layer3.4.conv1.bias
2020-08-04 11:05:33,407 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2a_bn_b mapped name: layer3.4.bn1.bias
2020-08-04 11:05:33,407 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2a_bn_s mapped name: layer3.4.bn1.weight
2020-08-04 11:05:33,407 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2a_w    mapped name: layer3.4.conv1.weight
2020-08-04 11:05:33,407 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2b_b    mapped name: layer3.4.conv2.bias
2020-08-04 11:05:33,407 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2b_bn_b mapped name: layer3.4.bn2.bias
2020-08-04 11:05:33,407 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2b_bn_s mapped name: layer3.4.bn2.weight
2020-08-04 11:05:33,407 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2b_w    mapped name: layer3.4.conv2.weight
2020-08-04 11:05:33,407 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2c_b    mapped name: layer3.4.conv3.bias
2020-08-04 11:05:33,407 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2c_bn_b mapped name: layer3.4.bn3.bias
2020-08-04 11:05:33,407 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2c_bn_s mapped name: layer3.4.bn3.weight
2020-08-04 11:05:33,407 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2c_w    mapped name: layer3.4.conv3.weight
2020-08-04 11:05:33,407 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2a_b    mapped name: layer3.5.conv1.bias
2020-08-04 11:05:33,407 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2a_bn_b mapped name: layer3.5.bn1.bias
2020-08-04 11:05:33,407 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2a_bn_s mapped name: layer3.5.bn1.weight
2020-08-04 11:05:33,407 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2a_w    mapped name: layer3.5.conv1.weight
2020-08-04 11:05:33,407 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2b_b    mapped name: layer3.5.conv2.bias
2020-08-04 11:05:33,407 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2b_bn_b mapped name: layer3.5.bn2.bias
2020-08-04 11:05:33,407 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2b_bn_s mapped name: layer3.5.bn2.weight
2020-08-04 11:05:33,407 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2b_w    mapped name: layer3.5.conv2.weight
2020-08-04 11:05:33,408 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2c_b    mapped name: layer3.5.conv3.bias
2020-08-04 11:05:33,408 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2c_bn_b mapped name: layer3.5.bn3.bias
2020-08-04 11:05:33,408 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2c_bn_s mapped name: layer3.5.bn3.weight
2020-08-04 11:05:33,408 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2c_w    mapped name: layer3.5.conv3.weight
2020-08-04 11:05:33,408 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch1_b     mapped name: layer4.0.downsample.0.bias
2020-08-04 11:05:33,408 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch1_bn_b  mapped name: layer4.0.downsample.1.bias
2020-08-04 11:05:33,408 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch1_bn_s  mapped name: layer4.0.downsample.1.weight
2020-08-04 11:05:33,408 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch1_w     mapped name: layer4.0.downsample.0.weight
2020-08-04 11:05:33,408 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2a_b    mapped name: layer4.0.conv1.bias
2020-08-04 11:05:33,408 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2a_bn_b mapped name: layer4.0.bn1.bias
2020-08-04 11:05:33,408 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2a_bn_s mapped name: layer4.0.bn1.weight
2020-08-04 11:05:33,408 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2a_w    mapped name: layer4.0.conv1.weight
2020-08-04 11:05:33,408 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2b_b    mapped name: layer4.0.conv2.bias
2020-08-04 11:05:33,408 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2b_bn_b mapped name: layer4.0.bn2.bias
2020-08-04 11:05:33,408 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2b_bn_s mapped name: layer4.0.bn2.weight
2020-08-04 11:05:33,408 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2b_w    mapped name: layer4.0.conv2.weight
2020-08-04 11:05:33,408 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2c_b    mapped name: layer4.0.conv3.bias
2020-08-04 11:05:33,408 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2c_bn_b mapped name: layer4.0.bn3.bias
2020-08-04 11:05:33,408 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2c_bn_s mapped name: layer4.0.bn3.weight
2020-08-04 11:05:33,409 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2c_w    mapped name: layer4.0.conv3.weight
2020-08-04 11:05:33,409 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2a_b    mapped name: layer4.1.conv1.bias
2020-08-04 11:05:33,409 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2a_bn_b mapped name: layer4.1.bn1.bias
2020-08-04 11:05:33,409 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2a_bn_s mapped name: layer4.1.bn1.weight
2020-08-04 11:05:33,409 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2a_w    mapped name: layer4.1.conv1.weight
2020-08-04 11:05:33,409 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2b_b    mapped name: layer4.1.conv2.bias
2020-08-04 11:05:33,409 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2b_bn_b mapped name: layer4.1.bn2.bias
2020-08-04 11:05:33,409 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2b_bn_s mapped name: layer4.1.bn2.weight
2020-08-04 11:05:33,409 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2b_w    mapped name: layer4.1.conv2.weight
2020-08-04 11:05:33,409 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2c_b    mapped name: layer4.1.conv3.bias
2020-08-04 11:05:33,409 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2c_bn_b mapped name: layer4.1.bn3.bias
2020-08-04 11:05:33,409 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2c_bn_s mapped name: layer4.1.bn3.weight
2020-08-04 11:05:33,409 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2c_w    mapped name: layer4.1.conv3.weight
2020-08-04 11:05:33,409 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2a_b    mapped name: layer4.2.conv1.bias
2020-08-04 11:05:33,409 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2a_bn_b mapped name: layer4.2.bn1.bias
2020-08-04 11:05:33,409 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2a_bn_s mapped name: layer4.2.bn1.weight
2020-08-04 11:05:33,409 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2a_w    mapped name: layer4.2.conv1.weight
2020-08-04 11:05:33,409 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2b_b    mapped name: layer4.2.conv2.bias
2020-08-04 11:05:33,410 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2b_bn_b mapped name: layer4.2.bn2.bias
2020-08-04 11:05:33,410 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2b_bn_s mapped name: layer4.2.bn2.weight
2020-08-04 11:05:33,410 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2b_w    mapped name: layer4.2.conv2.weight
2020-08-04 11:05:33,410 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2c_b    mapped name: layer4.2.conv3.bias
2020-08-04 11:05:33,410 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2c_bn_b mapped name: layer4.2.bn3.bias
2020-08-04 11:05:33,410 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2c_bn_s mapped name: layer4.2.bn3.weight
2020-08-04 11:05:33,410 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2c_w    mapped name: layer4.2.conv3.weight
2020-08-04 11:05:33,410 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res_conv1_bn_b       mapped name: bn1.bias
2020-08-04 11:05:33,410 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res_conv1_bn_s       mapped name: bn1.weight
2020-08-04 11:05:33,410 maskrcnn_benchmark.utils.c2_model_loading INFO: Remapping conv weights for deformable conv weights
2020-08-04 11:05:33,877 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.bn1.bias                                                                   loaded from layer1.0.bn1.bias            of shape (64,)
2020-08-04 11:05:33,892 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.bn1.weight                                                                 loaded from layer1.0.bn1.weight          of shape (64,)
2020-08-04 11:05:33,892 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.bn2.bias                                                                   loaded from layer1.0.bn2.bias            of shape (64,)
2020-08-04 11:05:33,892 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.bn2.weight                                                                 loaded from layer1.0.bn2.weight          of shape (64,)
2020-08-04 11:05:33,893 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.bn3.bias                                                                   loaded from layer1.0.bn3.bias            of shape (256,)
2020-08-04 11:05:33,893 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.bn3.weight                                                                 loaded from layer1.0.bn3.weight          of shape (256,)
2020-08-04 11:05:33,893 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.conv1.weight                                                               loaded from layer1.0.conv1.weight        of shape (64, 64, 1, 1)
2020-08-04 11:05:33,893 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.conv2.weight                                                               loaded from layer1.0.conv2.weight        of shape (64, 64, 3, 3)
2020-08-04 11:05:33,893 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.conv3.weight                                                               loaded from layer1.0.conv3.weight        of shape (256, 64, 1, 1)
2020-08-04 11:05:33,893 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.downsample.0.weight                                                        loaded from layer1.0.downsample.0.weight of shape (256, 64, 1, 1)
2020-08-04 11:05:33,893 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.downsample.1.bias                                                          loaded from layer1.0.downsample.1.bias   of shape (256,)
2020-08-04 11:05:33,893 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.downsample.1.weight                                                        loaded from layer1.0.downsample.1.weight of shape (256,)
2020-08-04 11:05:33,893 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.bn1.bias                                                                   loaded from layer1.1.bn1.bias            of shape (64,)
2020-08-04 11:05:33,893 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.bn1.weight                                                                 loaded from layer1.1.bn1.weight          of shape (64,)
2020-08-04 11:05:33,894 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.bn2.bias                                                                   loaded from layer1.1.bn2.bias            of shape (64,)
2020-08-04 11:05:33,894 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.bn2.weight                                                                 loaded from layer1.1.bn2.weight          of shape (64,)
2020-08-04 11:05:33,894 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.bn3.bias                                                                   loaded from layer1.1.bn3.bias            of shape (256,)
2020-08-04 11:05:33,894 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.bn3.weight                                                                 loaded from layer1.1.bn3.weight          of shape (256,)
2020-08-04 11:05:33,894 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.conv1.weight                                                               loaded from layer1.1.conv1.weight        of shape (64, 256, 1, 1)
2020-08-04 11:05:33,894 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.conv2.weight                                                               loaded from layer1.1.conv2.weight        of shape (64, 64, 3, 3)
2020-08-04 11:05:33,894 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.conv3.weight                                                               loaded from layer1.1.conv3.weight        of shape (256, 64, 1, 1)
2020-08-04 11:05:33,894 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.bn1.bias                                                                   loaded from layer1.2.bn1.bias            of shape (64,)
2020-08-04 11:05:33,894 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.bn1.weight                                                                 loaded from layer1.2.bn1.weight          of shape (64,)
2020-08-04 11:05:33,894 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.bn2.bias                                                                   loaded from layer1.2.bn2.bias            of shape (64,)
2020-08-04 11:05:33,894 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.bn2.weight                                                                 loaded from layer1.2.bn2.weight          of shape (64,)
2020-08-04 11:05:33,894 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.bn3.bias                                                                   loaded from layer1.2.bn3.bias            of shape (256,)
2020-08-04 11:05:33,894 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.bn3.weight                                                                 loaded from layer1.2.bn3.weight          of shape (256,)
2020-08-04 11:05:33,894 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.conv1.weight                                                               loaded from layer1.2.conv1.weight        of shape (64, 256, 1, 1)
2020-08-04 11:05:33,895 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.conv2.weight                                                               loaded from layer1.2.conv2.weight        of shape (64, 64, 3, 3)
2020-08-04 11:05:33,895 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.conv3.weight                                                               loaded from layer1.2.conv3.weight        of shape (256, 64, 1, 1)
2020-08-04 11:05:33,895 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.bn1.bias                                                                   loaded from layer2.0.bn1.bias            of shape (128,)
2020-08-04 11:05:33,895 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.bn1.weight                                                                 loaded from layer2.0.bn1.weight          of shape (128,)
2020-08-04 11:05:33,895 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.bn2.bias                                                                   loaded from layer2.0.bn2.bias            of shape (128,)
2020-08-04 11:05:33,895 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.bn2.weight                                                                 loaded from layer2.0.bn2.weight          of shape (128,)
2020-08-04 11:05:33,895 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.bn3.bias                                                                   loaded from layer2.0.bn3.bias            of shape (512,)
2020-08-04 11:05:33,895 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.bn3.weight                                                                 loaded from layer2.0.bn3.weight          of shape (512,)
2020-08-04 11:05:33,895 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.conv1.weight                                                               loaded from layer2.0.conv1.weight        of shape (128, 256, 1, 1)
2020-08-04 11:05:33,895 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.conv2.weight                                                               loaded from layer2.0.conv2.weight        of shape (128, 128, 3, 3)
2020-08-04 11:05:33,895 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.conv3.weight                                                               loaded from layer2.0.conv3.weight        of shape (512, 128, 1, 1)
2020-08-04 11:05:33,895 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.downsample.0.weight                                                        loaded from layer2.0.downsample.0.weight of shape (512, 256, 1, 1)
2020-08-04 11:05:33,895 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.downsample.1.bias                                                          loaded from layer2.0.downsample.1.bias   of shape (512,)
2020-08-04 11:05:33,896 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.downsample.1.weight                                                        loaded from layer2.0.downsample.1.weight of shape (512,)
2020-08-04 11:05:33,896 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.bn1.bias                                                                   loaded from layer2.1.bn1.bias            of shape (128,)
2020-08-04 11:05:33,896 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.bn1.weight                                                                 loaded from layer2.1.bn1.weight          of shape (128,)
2020-08-04 11:05:33,896 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.bn2.bias                                                                   loaded from layer2.1.bn2.bias            of shape (128,)
2020-08-04 11:05:33,896 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.bn2.weight                                                                 loaded from layer2.1.bn2.weight          of shape (128,)
2020-08-04 11:05:33,896 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.bn3.bias                                                                   loaded from layer2.1.bn3.bias            of shape (512,)
2020-08-04 11:05:33,896 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.bn3.weight                                                                 loaded from layer2.1.bn3.weight          of shape (512,)
2020-08-04 11:05:33,917 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.conv1.weight                                                               loaded from layer2.1.conv1.weight        of shape (128, 512, 1, 1)
2020-08-04 11:05:33,917 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.conv2.weight                                                               loaded from layer2.1.conv2.weight        of shape (128, 128, 3, 3)
2020-08-04 11:05:33,917 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.conv3.weight                                                               loaded from layer2.1.conv3.weight        of shape (512, 128, 1, 1)
2020-08-04 11:05:33,917 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.bn1.bias                                                                   loaded from layer2.2.bn1.bias            of shape (128,)
2020-08-04 11:05:33,917 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.bn1.weight                                                                 loaded from layer2.2.bn1.weight          of shape (128,)
2020-08-04 11:05:33,917 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.bn2.bias                                                                   loaded from layer2.2.bn2.bias            of shape (128,)
2020-08-04 11:05:33,917 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.bn2.weight                                                                 loaded from layer2.2.bn2.weight          of shape (128,)
2020-08-04 11:05:33,917 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.bn3.bias                                                                   loaded from layer2.2.bn3.bias            of shape (512,)
2020-08-04 11:05:33,917 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.bn3.weight                                                                 loaded from layer2.2.bn3.weight          of shape (512,)
2020-08-04 11:05:33,917 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.conv1.weight                                                               loaded from layer2.2.conv1.weight        of shape (128, 512, 1, 1)
2020-08-04 11:05:33,917 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.conv2.weight                                                               loaded from layer2.2.conv2.weight        of shape (128, 128, 3, 3)
2020-08-04 11:05:33,925 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.conv3.weight                                                               loaded from layer2.2.conv3.weight        of shape (512, 128, 1, 1)
2020-08-04 11:05:33,925 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.bn1.bias                                                                   loaded from layer2.3.bn1.bias            of shape (128,)
2020-08-04 11:05:33,925 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.bn1.weight                                                                 loaded from layer2.3.bn1.weight          of shape (128,)
2020-08-04 11:05:33,925 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.bn2.bias                                                                   loaded from layer2.3.bn2.bias            of shape (128,)
2020-08-04 11:05:33,925 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.bn2.weight                                                                 loaded from layer2.3.bn2.weight          of shape (128,)
2020-08-04 11:05:33,925 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.bn3.bias                                                                   loaded from layer2.3.bn3.bias            of shape (512,)
2020-08-04 11:05:33,925 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.bn3.weight                                                                 loaded from layer2.3.bn3.weight          of shape (512,)
2020-08-04 11:05:33,925 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.conv1.weight                                                               loaded from layer2.3.conv1.weight        of shape (128, 512, 1, 1)
2020-08-04 11:05:33,925 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.conv2.weight                                                               loaded from layer2.3.conv2.weight        of shape (128, 128, 3, 3)
2020-08-04 11:05:33,925 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.conv3.weight                                                               loaded from layer2.3.conv3.weight        of shape (512, 128, 1, 1)
2020-08-04 11:05:33,925 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.bn1.bias                                                                   loaded from layer3.0.bn1.bias            of shape (256,)
2020-08-04 11:05:33,925 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.bn1.weight                                                                 loaded from layer3.0.bn1.weight          of shape (256,)
2020-08-04 11:05:33,925 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.bn2.bias                                                                   loaded from layer3.0.bn2.bias            of shape (256,)
2020-08-04 11:05:33,926 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.bn2.weight                                                                 loaded from layer3.0.bn2.weight          of shape (256,)
2020-08-04 11:05:33,926 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.bn3.bias                                                                   loaded from layer3.0.bn3.bias            of shape (1024,)
2020-08-04 11:05:33,926 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.bn3.weight                                                                 loaded from layer3.0.bn3.weight          of shape (1024,)
2020-08-04 11:05:33,926 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.conv1.weight                                                               loaded from layer3.0.conv1.weight        of shape (256, 512, 1, 1)
2020-08-04 11:05:33,926 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.conv2.weight                                                               loaded from layer3.0.conv2.weight        of shape (256, 256, 3, 3)
2020-08-04 11:05:33,926 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.conv3.weight                                                               loaded from layer3.0.conv3.weight        of shape (1024, 256, 1, 1)
2020-08-04 11:05:33,926 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.downsample.0.weight                                                        loaded from layer3.0.downsample.0.weight of shape (1024, 512, 1, 1)
2020-08-04 11:05:33,926 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.downsample.1.bias                                                          loaded from layer3.0.downsample.1.bias   of shape (1024,)
2020-08-04 11:05:33,926 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.downsample.1.weight                                                        loaded from layer3.0.downsample.1.weight of shape (1024,)
2020-08-04 11:05:33,926 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.bn1.bias                                                                   loaded from layer3.1.bn1.bias            of shape (256,)
2020-08-04 11:05:33,926 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.bn1.weight                                                                 loaded from layer3.1.bn1.weight          of shape (256,)
2020-08-04 11:05:33,926 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.bn2.bias                                                                   loaded from layer3.1.bn2.bias            of shape (256,)
2020-08-04 11:05:33,926 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.bn2.weight                                                                 loaded from layer3.1.bn2.weight          of shape (256,)
2020-08-04 11:05:33,926 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.bn3.bias                                                                   loaded from layer3.1.bn3.bias            of shape (1024,)
2020-08-04 11:05:33,926 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.bn3.weight                                                                 loaded from layer3.1.bn3.weight          of shape (1024,)
2020-08-04 11:05:33,926 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.conv1.weight                                                               loaded from layer3.1.conv1.weight        of shape (256, 1024, 1, 1)
2020-08-04 11:05:33,927 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.conv2.weight                                                               loaded from layer3.1.conv2.weight        of shape (256, 256, 3, 3)
2020-08-04 11:05:33,927 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.conv3.weight                                                               loaded from layer3.1.conv3.weight        of shape (1024, 256, 1, 1)
2020-08-04 11:05:33,927 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.bn1.bias                                                                   loaded from layer3.2.bn1.bias            of shape (256,)
2020-08-04 11:05:33,927 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.bn1.weight                                                                 loaded from layer3.2.bn1.weight          of shape (256,)
2020-08-04 11:05:33,927 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.bn2.bias                                                                   loaded from layer3.2.bn2.bias            of shape (256,)
2020-08-04 11:05:33,927 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.bn2.weight                                                                 loaded from layer3.2.bn2.weight          of shape (256,)
2020-08-04 11:05:33,927 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.bn3.bias                                                                   loaded from layer3.2.bn3.bias            of shape (1024,)
2020-08-04 11:05:33,927 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.bn3.weight                                                                 loaded from layer3.2.bn3.weight          of shape (1024,)
2020-08-04 11:05:33,927 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.conv1.weight                                                               loaded from layer3.2.conv1.weight        of shape (256, 1024, 1, 1)
2020-08-04 11:05:33,927 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.conv2.weight                                                               loaded from layer3.2.conv2.weight        of shape (256, 256, 3, 3)
2020-08-04 11:05:33,927 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.conv3.weight                                                               loaded from layer3.2.conv3.weight        of shape (1024, 256, 1, 1)
2020-08-04 11:05:33,927 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.bn1.bias                                                                   loaded from layer3.3.bn1.bias            of shape (256,)
2020-08-04 11:05:33,927 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.bn1.weight                                                                 loaded from layer3.3.bn1.weight          of shape (256,)
2020-08-04 11:05:33,927 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.bn2.bias                                                                   loaded from layer3.3.bn2.bias            of shape (256,)
2020-08-04 11:05:33,927 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.bn2.weight                                                                 loaded from layer3.3.bn2.weight          of shape (256,)
2020-08-04 11:05:33,927 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.bn3.bias                                                                   loaded from layer3.3.bn3.bias            of shape (1024,)
2020-08-04 11:05:33,928 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.bn3.weight                                                                 loaded from layer3.3.bn3.weight          of shape (1024,)
2020-08-04 11:05:33,928 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.conv1.weight                                                               loaded from layer3.3.conv1.weight        of shape (256, 1024, 1, 1)
2020-08-04 11:05:33,928 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.conv2.weight                                                               loaded from layer3.3.conv2.weight        of shape (256, 256, 3, 3)
2020-08-04 11:05:33,928 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.conv3.weight                                                               loaded from layer3.3.conv3.weight        of shape (1024, 256, 1, 1)
2020-08-04 11:05:33,928 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.bn1.bias                                                                   loaded from layer3.4.bn1.bias            of shape (256,)
2020-08-04 11:05:33,928 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.bn1.weight                                                                 loaded from layer3.4.bn1.weight          of shape (256,)
2020-08-04 11:05:33,928 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.bn2.bias                                                                   loaded from layer3.4.bn2.bias            of shape (256,)
2020-08-04 11:05:33,928 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.bn2.weight                                                                 loaded from layer3.4.bn2.weight          of shape (256,)
2020-08-04 11:05:33,928 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.bn3.bias                                                                   loaded from layer3.4.bn3.bias            of shape (1024,)
2020-08-04 11:05:33,928 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.bn3.weight                                                                 loaded from layer3.4.bn3.weight          of shape (1024,)
2020-08-04 11:05:33,928 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.conv1.weight                                                               loaded from layer3.4.conv1.weight        of shape (256, 1024, 1, 1)
2020-08-04 11:05:33,928 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.conv2.weight                                                               loaded from layer3.4.conv2.weight        of shape (256, 256, 3, 3)
2020-08-04 11:05:33,928 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.conv3.weight                                                               loaded from layer3.4.conv3.weight        of shape (1024, 256, 1, 1)
2020-08-04 11:05:33,928 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.bn1.bias                                                                   loaded from layer3.5.bn1.bias            of shape (256,)
2020-08-04 11:05:33,928 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.bn1.weight                                                                 loaded from layer3.5.bn1.weight          of shape (256,)
2020-08-04 11:05:33,929 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.bn2.bias                                                                   loaded from layer3.5.bn2.bias            of shape (256,)
2020-08-04 11:05:33,929 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.bn2.weight                                                                 loaded from layer3.5.bn2.weight          of shape (256,)
2020-08-04 11:05:33,929 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.bn3.bias                                                                   loaded from layer3.5.bn3.bias            of shape (1024,)
2020-08-04 11:05:33,929 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.bn3.weight                                                                 loaded from layer3.5.bn3.weight          of shape (1024,)
2020-08-04 11:05:33,929 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.conv1.weight                                                               loaded from layer3.5.conv1.weight        of shape (256, 1024, 1, 1)
2020-08-04 11:05:33,929 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.conv2.weight                                                               loaded from layer3.5.conv2.weight        of shape (256, 256, 3, 3)
2020-08-04 11:05:33,929 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.conv3.weight                                                               loaded from layer3.5.conv3.weight        of shape (1024, 256, 1, 1)
2020-08-04 11:05:33,929 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.bn1.bias                                                                   loaded from layer4.0.bn1.bias            of shape (512,)
2020-08-04 11:05:33,929 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.bn1.weight                                                                 loaded from layer4.0.bn1.weight          of shape (512,)
2020-08-04 11:05:33,929 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.bn2.bias                                                                   loaded from layer4.0.bn2.bias            of shape (512,)
2020-08-04 11:05:33,929 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.bn2.weight                                                                 loaded from layer4.0.bn2.weight          of shape (512,)
2020-08-04 11:05:33,929 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.bn3.bias                                                                   loaded from layer4.0.bn3.bias            of shape (2048,)
2020-08-04 11:05:33,929 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.bn3.weight                                                                 loaded from layer4.0.bn3.weight          of shape (2048,)
2020-08-04 11:05:33,929 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.conv1.weight                                                               loaded from layer4.0.conv1.weight        of shape (512, 1024, 1, 1)
2020-08-04 11:05:33,929 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.conv2.weight                                                               loaded from layer4.0.conv2.weight        of shape (512, 512, 3, 3)
2020-08-04 11:05:33,929 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.conv3.weight                                                               loaded from layer4.0.conv3.weight        of shape (2048, 512, 1, 1)
2020-08-04 11:05:33,930 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.downsample.0.weight                                                        loaded from layer4.0.downsample.0.weight of shape (2048, 1024, 1, 1)
2020-08-04 11:05:33,930 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.downsample.1.bias                                                          loaded from layer4.0.downsample.1.bias   of shape (2048,)
2020-08-04 11:05:33,930 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.downsample.1.weight                                                        loaded from layer4.0.downsample.1.weight of shape (2048,)
2020-08-04 11:05:33,930 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.bn1.bias                                                                   loaded from layer4.1.bn1.bias            of shape (512,)
2020-08-04 11:05:33,930 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.bn1.weight                                                                 loaded from layer4.1.bn1.weight          of shape (512,)
2020-08-04 11:05:33,930 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.bn2.bias                                                                   loaded from layer4.1.bn2.bias            of shape (512,)
2020-08-04 11:05:33,930 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.bn2.weight                                                                 loaded from layer4.1.bn2.weight          of shape (512,)
2020-08-04 11:05:33,930 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.bn3.bias                                                                   loaded from layer4.1.bn3.bias            of shape (2048,)
2020-08-04 11:05:33,930 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.bn3.weight                                                                 loaded from layer4.1.bn3.weight          of shape (2048,)
2020-08-04 11:05:33,930 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.conv1.weight                                                               loaded from layer4.1.conv1.weight        of shape (512, 2048, 1, 1)
2020-08-04 11:05:33,930 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.conv2.weight                                                               loaded from layer4.1.conv2.weight        of shape (512, 512, 3, 3)
2020-08-04 11:05:33,930 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.conv3.weight                                                               loaded from layer4.1.conv3.weight        of shape (2048, 512, 1, 1)
2020-08-04 11:05:33,930 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.bn1.bias                                                                   loaded from layer4.2.bn1.bias            of shape (512,)
2020-08-04 11:05:33,930 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.bn1.weight                                                                 loaded from layer4.2.bn1.weight          of shape (512,)
2020-08-04 11:05:33,930 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.bn2.bias                                                                   loaded from layer4.2.bn2.bias            of shape (512,)
2020-08-04 11:05:33,930 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.bn2.weight                                                                 loaded from layer4.2.bn2.weight          of shape (512,)
2020-08-04 11:05:33,931 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.bn3.bias                                                                   loaded from layer4.2.bn3.bias            of shape (2048,)
2020-08-04 11:05:33,931 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.bn3.weight                                                                 loaded from layer4.2.bn3.weight          of shape (2048,)
2020-08-04 11:05:33,931 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.conv1.weight                                                               loaded from layer4.2.conv1.weight        of shape (512, 2048, 1, 1)
2020-08-04 11:05:33,931 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.conv2.weight                                                               loaded from layer4.2.conv2.weight        of shape (512, 512, 3, 3)
2020-08-04 11:05:33,931 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.conv3.weight                                                               loaded from layer4.2.conv3.weight        of shape (2048, 512, 1, 1)
2020-08-04 11:05:33,931 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.stem.bn1.bias                                                                       loaded from bn1.bias                     of shape (64,)
2020-08-04 11:05:33,931 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.stem.bn1.weight                                                                     loaded from bn1.weight                   of shape (64,)
2020-08-04 11:05:33,931 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.stem.conv1.weight                                                                   loaded from conv1.weight                 of shape (64, 3, 7, 7)
2020-08-04 11:05:34,060 maskrcnn_benchmark.data.build WARNING: When using more than one image per GPU you may encounter an out-of-memory (OOM) error if your GPU does not have sufficient memory. If this happens, you can reduce SOLVER.IMS_PER_BATCH (for training) or TEST.IMS_PER_BATCH (for inference). For training, you must also adjust the learning rate and schedule length according to the linear scaling rule. See for example: https://github.com/facebookresearch/Detectron/blob/master/configs/getting_started/tutorial_1gpu_e2e_faster_rcnn_R-50-FPN.yaml#L14
2020-08-04 11:05:37,189 maskrcnn_benchmark.utils.miscellaneous WARNING: Dataset [COCOCaptionsDataset] has no categories attribute, labels.json file won't be created
2020-08-04 11:05:37,419 maskrcnn_benchmark.data.build WARNING: When using more than one image per GPU you may encounter an out-of-memory (OOM) error if your GPU does not have sufficient memory. If this happens, you can reduce SOLVER.IMS_PER_BATCH (for training) or TEST.IMS_PER_BATCH (for inference). For training, you must also adjust the learning rate and schedule length according to the linear scaling rule. See for example: https://github.com/facebookresearch/Detectron/blob/master/configs/getting_started/tutorial_1gpu_e2e_faster_rcnn_R-50-FPN.yaml#L14
2020-08-04 11:05:37,489 maskrcnn_benchmark.trainer INFO: Start training
2020-08-04 11:06:49,898 maskrcnn_benchmark.trainer INFO: eta: 8:01:27  iter: 100  Cross-Entropy Loss (Align Regions, Choose Caption): 1.6825 (1.9629)  Cross-Entropy Loss (Align Regions, Choose Image): 1.6405 (1.9497)  Cross-Entropy Loss (Align Words, Choose Caption): 1.8226 (2.0018)  Cross-Entropy Loss (Align Words, Choose Image): 1.7348 (1.9750)  Image Caption Matching Loss: 4.1483 (4.1557)  Masked Language Modeling Loss: 4.6826 (5.5908)  Masked Visual Modeling Loss: 0.0000 (0.0000)  loss: 15.8034 (17.6360)  Batch Accuracy (Align Regions, Choose Caption): 0.3750 (0.2195)  Batch Accuracy (Align Regions, Choose Image): 0.3906 (0.2242)  Batch Accuracy (Align Words, Choose Caption): 0.3438 (0.2080)  Batch Accuracy (Align Words, Choose Image): 0.3750 (0.2255)  Batch Accuracy (Choose Caption): 0.1562 (0.1300)  Batch Accuracy (Choose Image): 0.1250 (0.1322)  Masked Language Modeling Accuracy: 0.3336 (0.2439)  time: 0.6759 (0.7240)  data: 0.0395 (0.0535)  lr: 0.004653  max mem: 10750
2020-08-04 11:07:58,221 maskrcnn_benchmark.trainer INFO: eta: 7:46:43  iter: 200  Cross-Entropy Loss (Align Regions, Choose Caption): 1.0699 (1.5826)  Cross-Entropy Loss (Align Regions, Choose Image): 0.9873 (1.5649)  Cross-Entropy Loss (Align Words, Choose Caption): 1.2449 (1.7080)  Cross-Entropy Loss (Align Words, Choose Image): 1.0132 (1.5988)  Image Caption Matching Loss: 4.0515 (4.1294)  Masked Language Modeling Loss: 4.1125 (4.9744)  Masked Visual Modeling Loss: 0.0000 (0.0000)  loss: 12.5578 (15.5581)  Batch Accuracy (Align Regions, Choose Caption): 0.6406 (0.3958)  Batch Accuracy (Align Regions, Choose Image): 0.6250 (0.3980)  Batch Accuracy (Align Words, Choose Caption): 0.5781 (0.3534)  Batch Accuracy (Align Words, Choose Image): 0.6562 (0.3999)  Batch Accuracy (Choose Caption): 0.2500 (0.1593)  Batch Accuracy (Choose Image): 0.2188 (0.1584)  Masked Language Modeling Accuracy: 0.3844 (0.3000)  time: 0.6827 (0.7036)  data: 0.0383 (0.0463)  lr: 0.005987  max mem: 10750
2020-08-04 11:09:06,653 maskrcnn_benchmark.trainer INFO: eta: 7:41:18  iter: 300  Cross-Entropy Loss (Align Regions, Choose Caption): 0.9103 (1.3632)  Cross-Entropy Loss (Align Regions, Choose Image): 0.8133 (1.3498)  Cross-Entropy Loss (Align Words, Choose Caption): 1.0594 (1.5118)  Cross-Entropy Loss (Align Words, Choose Image): 0.8226 (1.3664)  Image Caption Matching Loss: 3.7361 (4.0607)  Masked Language Modeling Loss: 3.8365 (4.6433)  Masked Visual Modeling Loss: 0.0000 (0.0000)  loss: 11.2430 (14.2952)  Batch Accuracy (Align Regions, Choose Caption): 0.7188 (0.4904)  Batch Accuracy (Align Regions, Choose Image): 0.7031 (0.4920)  Batch Accuracy (Align Words, Choose Caption): 0.6406 (0.4429)  Batch Accuracy (Align Words, Choose Image): 0.7188 (0.4990)  Batch Accuracy (Choose Caption): 0.2344 (0.1877)  Batch Accuracy (Choose Image): 0.2500 (0.1837)  Masked Language Modeling Accuracy: 0.4162 (0.3327)  time: 0.6842 (0.6972)  data: 0.0409 (0.0440)  lr: 0.007320  max mem: 10990
2020-08-04 11:10:14,459 maskrcnn_benchmark.trainer INFO: eta: 7:36:59  iter: 400  Cross-Entropy Loss (Align Regions, Choose Caption): 0.7567 (1.2321)  Cross-Entropy Loss (Align Regions, Choose Image): 0.7568 (1.2181)  Cross-Entropy Loss (Align Words, Choose Caption): 0.9849 (1.3883)  Cross-Entropy Loss (Align Words, Choose Image): 0.7574 (1.2242)  Image Caption Matching Loss: 3.2667 (3.8996)  Masked Language Modeling Loss: 3.5416 (4.3997)  Masked Visual Modeling Loss: 0.0000 (0.0000)  loss: 10.1175 (13.3620)  Batch Accuracy (Align Regions, Choose Caption): 0.7344 (0.5463)  Batch Accuracy (Align Regions, Choose Image): 0.7500 (0.5477)  Batch Accuracy (Align Words, Choose Caption): 0.6875 (0.4993)  Batch Accuracy (Align Words, Choose Image): 0.7500 (0.5582)  Batch Accuracy (Choose Caption): 0.3281 (0.2214)  Batch Accuracy (Choose Image): 0.3125 (0.2157)  Masked Language Modeling Accuracy: 0.4270 (0.3564)  time: 0.6761 (0.6924)  data: 0.0391 (0.0427)  lr: 0.008653  max mem: 10990
2020-08-04 11:11:21,972 maskrcnn_benchmark.trainer INFO: eta: 7:33:33  iter: 500  Cross-Entropy Loss (Align Regions, Choose Caption): 0.7263 (1.1427)  Cross-Entropy Loss (Align Regions, Choose Image): 0.7552 (1.1284)  Cross-Entropy Loss (Align Words, Choose Caption): 0.8545 (1.3019)  Cross-Entropy Loss (Align Words, Choose Image): 0.6839 (1.1265)  Image Caption Matching Loss: 2.5992 (3.6966)  Masked Language Modeling Loss: 3.4270 (4.2172)  Masked Visual Modeling Loss: 0.0000 (0.0000)  loss: 9.0821 (12.6134)  Batch Accuracy (Align Regions, Choose Caption): 0.7344 (0.5829)  Batch Accuracy (Align Regions, Choose Image): 0.7500 (0.5862)  Batch Accuracy (Align Words, Choose Caption): 0.6875 (0.5356)  Batch Accuracy (Align Words, Choose Image): 0.7500 (0.5972)  Batch Accuracy (Choose Caption): 0.4844 (0.2655)  Batch Accuracy (Choose Image): 0.4688 (0.2580)  Masked Language Modeling Accuracy: 0.4569 (0.3741)  time: 0.6718 (0.6890)  data: 0.0376 (0.0419)  lr: 0.009987  max mem: 10990
2020-08-04 11:12:29,637 maskrcnn_benchmark.trainer INFO: eta: 7:31:03  iter: 600  Cross-Entropy Loss (Align Regions, Choose Caption): 0.8109 (1.0814)  Cross-Entropy Loss (Align Regions, Choose Image): 0.7675 (1.0656)  Cross-Entropy Loss (Align Words, Choose Caption): 0.8851 (1.2345)  Cross-Entropy Loss (Align Words, Choose Image): 0.7401 (1.0554)  Image Caption Matching Loss: 2.2591 (3.4643)  Masked Language Modeling Loss: 3.2249 (4.0671)  Masked Visual Modeling Loss: 0.0000 (0.0000)  loss: 8.6563 (11.9681)  Batch Accuracy (Align Regions, Choose Caption): 0.7500 (0.6089)  Batch Accuracy (Align Regions, Choose Image): 0.7188 (0.6133)  Batch Accuracy (Align Words, Choose Caption): 0.7031 (0.5637)  Batch Accuracy (Align Words, Choose Image): 0.7344 (0.6255)  Batch Accuracy (Choose Caption): 0.5469 (0.3110)  Batch Accuracy (Choose Image): 0.5469 (0.3041)  Masked Language Modeling Accuracy: 0.4715 (0.3894)  time: 0.6740 (0.6869)  data: 0.0381 (0.0413)  lr: 0.010000  max mem: 11029
2020-08-04 11:13:37,207 maskrcnn_benchmark.trainer INFO: eta: 7:28:52  iter: 700  Cross-Entropy Loss (Align Regions, Choose Caption): 0.7495 (1.0351)  Cross-Entropy Loss (Align Regions, Choose Image): 0.7199 (1.0188)  Cross-Entropy Loss (Align Words, Choose Caption): 0.8646 (1.1872)  Cross-Entropy Loss (Align Words, Choose Image): 0.6466 (1.0038)  Image Caption Matching Loss: 1.9027 (3.2569)  Masked Language Modeling Loss: 3.1395 (3.9443)  Masked Visual Modeling Loss: 0.0000 (0.0000)  loss: 7.9662 (11.4461)  Batch Accuracy (Align Regions, Choose Caption): 0.7344 (0.6275)  Batch Accuracy (Align Regions, Choose Image): 0.7500 (0.6336)  Batch Accuracy (Align Words, Choose Caption): 0.7031 (0.5822)  Batch Accuracy (Align Words, Choose Image): 0.7500 (0.6457)  Batch Accuracy (Choose Caption): 0.6094 (0.3527)  Batch Accuracy (Choose Image): 0.6094 (0.3459)  Masked Language Modeling Accuracy: 0.4806 (0.4022)  time: 0.6730 (0.6853)  data: 0.0370 (0.0409)  lr: 0.010000  max mem: 11668
2020-08-04 11:14:44,629 maskrcnn_benchmark.trainer INFO: eta: 7:26:49  iter: 800  Cross-Entropy Loss (Align Regions, Choose Caption): 0.7765 (0.9941)  Cross-Entropy Loss (Align Regions, Choose Image): 0.7362 (0.9768)  Cross-Entropy Loss (Align Words, Choose Caption): 0.8146 (1.1391)  Cross-Entropy Loss (Align Words, Choose Image): 0.6845 (0.9586)  Image Caption Matching Loss: 1.7244 (3.0742)  Masked Language Modeling Loss: 2.9407 (3.8268)  Masked Visual Modeling Loss: 0.0000 (0.0000)  loss: 7.7543 (10.9696)  Batch Accuracy (Align Regions, Choose Caption): 0.7500 (0.6444)  Batch Accuracy (Align Regions, Choose Image): 0.7500 (0.6499)  Batch Accuracy (Align Words, Choose Caption): 0.7031 (0.6006)  Batch Accuracy (Align Words, Choose Image): 0.7969 (0.6637)  Batch Accuracy (Choose Caption): 0.6719 (0.3895)  Batch Accuracy (Choose Image): 0.6562 (0.3834)  Masked Language Modeling Accuracy: 0.5045 (0.4146)  time: 0.6723 (0.6839)  data: 0.0390 (0.0405)  lr: 0.010000  max mem: 11668
2020-08-04 11:15:52,211 maskrcnn_benchmark.trainer INFO: eta: 7:25:05  iter: 900  Cross-Entropy Loss (Align Regions, Choose Caption): 0.6775 (0.9608)  Cross-Entropy Loss (Align Regions, Choose Image): 0.6389 (0.9432)  Cross-Entropy Loss (Align Words, Choose Caption): 0.7341 (1.1026)  Cross-Entropy Loss (Align Words, Choose Image): 0.6375 (0.9226)  Image Caption Matching Loss: 1.6405 (2.9178)  Masked Language Modeling Loss: 2.8683 (3.7332)  Masked Visual Modeling Loss: 0.0000 (0.0000)  loss: 7.1467 (10.5804)  Batch Accuracy (Align Regions, Choose Caption): 0.7656 (0.6574)  Batch Accuracy (Align Regions, Choose Image): 0.7656 (0.6635)  Batch Accuracy (Align Words, Choose Caption): 0.7344 (0.6151)  Batch Accuracy (Align Words, Choose Image): 0.7812 (0.6778)  Batch Accuracy (Choose Caption): 0.6719 (0.4216)  Batch Accuracy (Choose Image): 0.6875 (0.4158)  Masked Language Modeling Accuracy: 0.5068 (0.4242)  time: 0.6750 (0.6830)  data: 0.0380 (0.0403)  lr: 0.010000  max mem: 11668
2020-08-04 11:16:59,878 maskrcnn_benchmark.trainer INFO: eta: 7:23:32  iter: 1000  Cross-Entropy Loss (Align Regions, Choose Caption): 0.6644 (0.9350)  Cross-Entropy Loss (Align Regions, Choose Image): 0.6102 (0.9167)  Cross-Entropy Loss (Align Words, Choose Caption): 0.7471 (1.0709)  Cross-Entropy Loss (Align Words, Choose Image): 0.6171 (0.8921)  Image Caption Matching Loss: 1.5533 (2.7840)  Masked Language Modeling Loss: 2.7717 (3.6484)  Masked Visual Modeling Loss: 0.0000 (0.0000)  loss: 7.0535 (10.2470)  Batch Accuracy (Align Regions, Choose Caption): 0.7656 (0.6678)  Batch Accuracy (Align Regions, Choose Image): 0.7656 (0.6745)  Batch Accuracy (Align Words, Choose Caption): 0.7344 (0.6273)  Batch Accuracy (Align Words, Choose Image): 0.7812 (0.6889)  Batch Accuracy (Choose Caption): 0.6875 (0.4488)  Batch Accuracy (Choose Image): 0.6875 (0.4439)  Masked Language Modeling Accuracy: 0.5148 (0.4330)  time: 0.6745 (0.6824)  data: 0.0379 (0.0401)  lr: 0.010000  max mem: 11668
2020-08-04 11:17:00,196 maskrcnn_benchmark.utils.checkpoint INFO: Saving checkpoint to /home/alireza/runs/vltrain/121/model_0001000.pth

This goes on for a while and finally we have:

2020-08-04 19:17:53,792 maskrcnn_benchmark.trainer INFO: eta: 0:01:14  iter: 39900  Cross-Entropy Loss (Align Regions, Choose Caption): 0.2195 (0.3917)  Cross-Entropy Loss (Align Regions, Choose Image): 0.2311 (0.3784)  Cross-Entropy Loss (Align Words, Choose Caption): 0.2003 (0.3690)  Cross-Entropy Loss (Align Words, Choose Image): 0.1716 (0.3110)  Image Caption Matching Loss: 0.2174 (0.4902)  Masked Language Modeling Loss: 1.7325 (1.8332)  Masked Visual Modeling Loss: 0.0000 (0.0000)  loss: 2.7870 (3.7736)  Batch Accuracy (Align Regions, Choose Caption): 0.9062 (0.8691)  Batch Accuracy (Align Regions, Choose Image): 0.9219 (0.8714)  Batch Accuracy (Align Words, Choose Caption): 0.9375 (0.8730)  Batch Accuracy (Align Words, Choose Image): 0.9219 (0.8922)  Batch Accuracy (Choose Caption): 0.9531 (0.9049)  Batch Accuracy (Choose Image): 0.9531 (0.9052)  Masked Language Modeling Accuracy: 0.6429 (0.6386)  time: 0.6685 (0.7403)  data: 0.0360 (0.1031)  lr: 0.000100  max mem: 12152
2020-08-04 19:19:00,867 maskrcnn_benchmark.trainer INFO: eta: 0:00:00  iter: 40000  Cross-Entropy Loss (Align Regions, Choose Caption): 0.2684 (0.3914)  Cross-Entropy Loss (Align Regions, Choose Image): 0.2396 (0.3780)  Cross-Entropy Loss (Align Words, Choose Caption): 0.2185 (0.3686)  Cross-Entropy Loss (Align Words, Choose Image): 0.1979 (0.3107)  Image Caption Matching Loss: 0.2538 (0.4896)  Masked Language Modeling Loss: 1.4964 (1.8325)  Masked Visual Modeling Loss: 0.0000 (0.0000)  loss: 2.6669 (3.7707)  Batch Accuracy (Align Regions, Choose Caption): 0.8906 (0.8692)  Batch Accuracy (Align Regions, Choose Image): 0.9219 (0.8715)  Batch Accuracy (Align Words, Choose Caption): 0.9219 (0.8731)  Batch Accuracy (Align Words, Choose Image): 0.9219 (0.8923)  Batch Accuracy (Choose Caption): 0.9531 (0.9050)  Batch Accuracy (Choose Image): 0.9531 (0.9053)  Masked Language Modeling Accuracy: 0.6903 (0.6387)  time: 0.6707 (0.7401)  data: 0.0342 (0.1029)  lr: 0.000100  max mem: 12152
2020-08-04 19:19:01,169 maskrcnn_benchmark.utils.checkpoint INFO: Saving checkpoint to /home/alireza/runs/vltrain/121/model_0040000.pth
2020-08-04 19:20:08,973 maskrcnn_benchmark.trainer INFO: [Validation]:   eta: 0:00:00  iter: 40000  loss: 0.8663 (0.8559)  Cross-Entropy Loss (Align Regions, Choose Caption): 0.1506 (0.1652)  Cross-Entropy Loss (Align Regions, Choose Image): 0.1740 (0.1847)  Cross-Entropy Loss (Align Words, Choose Caption): 0.1662 (0.1719)  Cross-Entropy Loss (Align Words, Choose Image): 0.1187 (0.1481)  Image Caption Matching Loss: 0.1837 (0.1860)  Masked Language Modeling Loss: 0.0000 (0.0000)  Masked Visual Modeling Loss: 0.0000 (0.0000)  Batch Accuracy (Align Regions, Choose Caption): 0.9531 (0.9427)  Batch Accuracy (Align Regions, Choose Image): 0.9219 (0.9335)  Batch Accuracy (Align Words, Choose Caption): 0.9375 (0.9354)  Batch Accuracy (Align Words, Choose Image): 0.9375 (0.9490)  Batch Accuracy (Choose Caption): 0.9688 (0.9637)  Batch Accuracy (Choose Image): 0.9531 (0.9603)  Masked Language Modeling Accuracy: 0.0000 (0.0000)  lr: 0.000100  max mem: 12152
2020-08-04 19:20:09,537 maskrcnn_benchmark.utils.checkpoint INFO: Saving checkpoint to /home/alireza/runs/vltrain/121/model_final.pth
2020-08-04 19:20:13,599 maskrcnn_benchmark.trainer INFO: Total training time: 8:14:36.107446 (0.7419 s / it)
alirezazareian commented 3 years ago

It is strange that you said only seen class performance cannot be reproduced. If the problem is in the pretraining stage, it should affect seen and unseen equally. Note that AP50_split_seen and AP50_split_unseen show the generalized performance when you evaluate on coco_generalized_zeroshot_val. But they show base and target performance in non-generalized form when you evaluate on coco_not_zeroshot_val and coco_zeroshot_val respectively. Here is the final evaluation output I get after finetuning the pretrained model on object detection:

2020-08-06 17:06:18,368 maskrcnn_benchmark.inference INFO: Start evaluation on coco_not_zeroshot_val dataset(4533 images).
2020-08-06 17:07:17,418 maskrcnn_benchmark.inference INFO: Total run time: 0:00:59.049673 (0.10421296815432488 s / img per device, on 8 devices)
2020-08-06 17:07:17,418 maskrcnn_benchmark.inference INFO: Model inference time: 0:00:53.669309 (0.09471750964188508 s / img per device, on 8 devices)
2020-08-06 17:07:19,192 maskrcnn_benchmark.inference INFO: Evaluating bbox proposals
2020-08-06 17:07:56,323 maskrcnn_benchmark.inference INFO: Preparing results for COCO format
2020-08-06 17:07:56,325 maskrcnn_benchmark.inference INFO: Preparing bbox results
2020-08-06 17:07:57,865 maskrcnn_benchmark.inference INFO: Evaluating predictions
2020-08-06 17:08:47,831 maskrcnn_benchmark.inference INFO: 
Task: box_proposal
AR@100, ARs@100, ARm@100, ARl@100, AR@1000, ARs@1000, ARm@1000, ARl@1000
0.4791, 0.2997, 0.5641, 0.6889, 0.4791, 0.2997, 0.5641, 0.6889
Task: bbox
AP, AP50, AP75, APs, APm, APl, AP50_class_person, AP50_class_bicycle, AP50_class_car, AP50_class_motorcycle, AP50_class_train, AP50_class_truck, AP50_class_boat, AP50_class_bench, AP50_class_bird, AP50_class_horse, AP50_class_sheep, AP50_class_bear, AP50_class_zebra, AP50_class_giraffe, AP50_class_backpack, AP50_class_handbag, AP50_class_suitcase, AP50_class_frisbee, AP50_class_skis, AP50_class_kite, AP50_class_surfboard, AP50_class_bottle, AP50_class_fork, AP50_class_spoon, AP50_class_bowl, AP50_class_banana, AP50_class_apple, AP50_class_sandwich, AP50_class_orange, AP50_class_broccoli, AP50_class_carrot, AP50_class_pizza, AP50_class_donut, AP50_class_chair, AP50_class_bed, AP50_class_toilet, AP50_class_tv, AP50_class_laptop, AP50_class_mouse, AP50_class_remote, AP50_class_microwave, AP50_class_oven, AP50_class_toaster, AP50_class_refrigerator, AP50_class_book, AP50_class_clock, AP50_class_vase, AP50_class_toothbrush, AP50_split_seen
0.2688, 0.4676, 0.2711, 0.1165, 0.2998, 0.3715, 0.7589, 0.4438, 0.5255, 0.6232, 0.7177, 0.3771, 0.3753, 0.2853, 0.4248, 0.6627, 0.5901, 0.7871, 0.8643, 0.8554, 0.1508, 0.1205, 0.3555, 0.6725, 0.2594, 0.4994, 0.4462, 0.4545, 0.2894, 0.1086, 0.4908, 0.3398, 0.2314, 0.3959, 0.3206, 0.3828, 0.2756, 0.6398, 0.4292, 0.3236, 0.5397, 0.6920, 0.6807, 0.6620, 0.6553, 0.2390, 0.6345, 0.4350, 0.3859, 0.6281, 0.2104, 0.6410, 0.4021, 0.1616, 0.4676

2020-08-06 17:08:48,499 maskrcnn_benchmark.inference INFO: Start evaluation on coco_zeroshot_val dataset(2064 images).
2020-08-06 17:09:11,053 maskrcnn_benchmark.inference INFO: Total run time: 0:00:22.554012 (0.08741865139598995 s / img per device, on 8 devices)
2020-08-06 17:09:11,054 maskrcnn_benchmark.inference INFO: Model inference time: 0:00:20.010486 (0.07756002466807994 s / img per device, on 8 devices)
2020-08-06 17:09:11,911 maskrcnn_benchmark.inference INFO: Evaluating bbox proposals
2020-08-06 17:09:22,189 maskrcnn_benchmark.inference INFO: Preparing results for COCO format
2020-08-06 17:09:22,189 maskrcnn_benchmark.inference INFO: Preparing bbox results
2020-08-06 17:09:22,505 maskrcnn_benchmark.inference INFO: Evaluating predictions
2020-08-06 17:09:27,167 maskrcnn_benchmark.inference INFO: 
Task: box_proposal
AR@100, ARs@100, ARm@100, ARl@100, AR@1000, ARs@1000, ARm@1000, ARl@1000
0.3567, 0.1648, 0.3916, 0.5186, 0.3567, 0.1648, 0.3916, 0.5186
Task: bbox
AP, AP50, AP75, APs, APm, APl, AP50_class_airplane, AP50_class_bus, AP50_class_cat, AP50_class_dog, AP50_class_cow, AP50_class_elephant, AP50_class_umbrella, AP50_class_tie, AP50_class_snowboard, AP50_class_skateboard, AP50_class_cup, AP50_class_knife, AP50_class_cake, AP50_class_couch, AP50_class_keyboard, AP50_class_sink, AP50_class_scissors, AP50_split_unseen
0.1466, 0.2746, 0.1383, 0.0828, 0.1659, 0.2026, 0.3133, 0.6267, 0.3941, 0.5513, 0.5875, 0.5904, 0.1021, 0.0014, 0.3099, 0.0903, 0.2240, 0.0546, 0.1816, 0.3637, 0.0503, 0.1190, 0.1079, 0.2746

2020-08-06 17:09:27,281 maskrcnn_benchmark.inference INFO: Start evaluation on coco_generalized_zeroshot_val dataset(4836 images).
2020-08-06 17:10:32,876 maskrcnn_benchmark.inference INFO: Total run time: 0:01:05.595098 (0.10851132800699365 s / img per device, on 8 devices)
2020-08-06 17:10:32,879 maskrcnn_benchmark.inference INFO: Model inference time: 0:00:57.917472 (0.09581054154262748 s / img per device, on 8 devices)
2020-08-06 17:10:34,701 maskrcnn_benchmark.inference INFO: Evaluating bbox proposals
2020-08-06 17:11:12,835 maskrcnn_benchmark.inference INFO: Preparing results for COCO format
2020-08-06 17:11:12,837 maskrcnn_benchmark.inference INFO: Preparing bbox results
2020-08-06 17:11:14,481 maskrcnn_benchmark.inference INFO: Evaluating predictions
2020-08-06 17:12:09,313 maskrcnn_benchmark.inference INFO: 
Task: box_proposal
AR@100, ARs@100, ARm@100, ARl@100, AR@1000, ARs@1000, ARm@1000, ARl@1000
0.4700, 0.2891, 0.5485, 0.6707, 0.4700, 0.2891, 0.5485, 0.6707
Task: bbox
AP, AP50, AP75, APs, APm, APl, AP50_class_person, AP50_class_bicycle, AP50_class_car, AP50_class_motorcycle, AP50_class_airplane, AP50_class_bus, AP50_class_train, AP50_class_truck, AP50_class_boat, AP50_class_bench, AP50_class_bird, AP50_class_cat, AP50_class_dog, AP50_class_horse, AP50_class_sheep, AP50_class_cow, AP50_class_elephant, AP50_class_bear, AP50_class_zebra, AP50_class_giraffe, AP50_class_backpack, AP50_class_umbrella, AP50_class_handbag, AP50_class_tie, AP50_class_suitcase, AP50_class_frisbee, AP50_class_skis, AP50_class_snowboard, AP50_class_kite, AP50_class_skateboard, AP50_class_surfboard, AP50_class_bottle, AP50_class_cup, AP50_class_fork, AP50_class_knife, AP50_class_spoon, AP50_class_bowl, AP50_class_banana, AP50_class_apple, AP50_class_sandwich, AP50_class_orange, AP50_class_broccoli, AP50_class_carrot, AP50_class_pizza, AP50_class_donut, AP50_class_cake, AP50_class_chair, AP50_class_couch, AP50_class_bed, AP50_class_toilet, AP50_class_tv, AP50_class_laptop, AP50_class_mouse, AP50_class_remote, AP50_class_keyboard, AP50_class_microwave, AP50_class_oven, AP50_class_toaster, AP50_class_sink, AP50_class_refrigerator, AP50_class_book, AP50_class_clock, AP50_class_vase, AP50_class_scissors, AP50_class_toothbrush, AP50_split_seen, AP50_split_unseen
0.2258, 0.3993, 0.2263, 0.0955, 0.2511, 0.3154, 0.7582, 0.4409, 0.5255, 0.6233, 0.2989, 0.4933, 0.7110, 0.3726, 0.3738, 0.2838, 0.4177, 0.3214, 0.5163, 0.6437, 0.5649, 0.4667, 0.5544, 0.7802, 0.8638, 0.8565, 0.1503, 0.0799, 0.1194, 0.0024, 0.3527, 0.6709, 0.2279, 0.1133, 0.4983, 0.1333, 0.4358, 0.4520, 0.2054, 0.2715, 0.0302, 0.0969, 0.4729, 0.3383, 0.2318, 0.3924, 0.3188, 0.3817, 0.2764, 0.6373, 0.4250, 0.1394, 0.3194, 0.2536, 0.5354, 0.6923, 0.6776, 0.6532, 0.6484, 0.2376, 0.0646, 0.6274, 0.4387, 0.2619, 0.1083, 0.6259, 0.2125, 0.6381, 0.3886, 0.0946, 0.1533, 0.4599, 0.2280
lxtGH commented 3 years ago

@alirezazareian Thanks for your reply!! I found the reason. I use detectron2 ImageNet pretrained model rather than maskrcnn_benchmark ImageNet pretrained model. Now the results are normal.

yestinl commented 2 years ago

Here is the log file: https://github.com/lxtGH/ovr-cnn/blob/master/log.txt The Masked Language Modeling Accuracy is nearly zero.

How you resolve the problem about this? Could you provide me the details?