mukesh-2538
commented
4 years ago I am trying it on custom dataset.
Open mukesh-2538 opened 4 years ago
mukesh-2538
commented
4 years ago I am trying it on custom dataset.
KaihuaTang
commented
4 years ago Try moving the following codes:
Sorry that I'm working on other projects, so I don't have GPUs to test this commit. It should solve the problem. Please tell me if it doesn't.
mukesh-2538
commented
4 years ago are the changes to be made in visual_genome .py?
KaihuaTang
commented
4 years ago yes
mukesh-2538
commented
4 years ago It is working. Thankyou so much
mukesh-2538
commented
4 years ago i think you will get this file("VG_stanford_filtered_with_attribute_train_statistics.cache") along with the pretrained weights.
Kritz23
commented
4 years ago i think you will get this file("VG_stanford_filtered_with_attribute_train_statistics.cache") along with the pretrained weights.
I have downloaded the pretrained model folder. In that folder, this file is already present.
mukesh-2538
commented
4 years ago Are you trying it on custom images?
Kritz23
commented
4 years ago Are you trying it on custom images?
Yes
mukesh-2538
commented
4 years ago Are you trying it on custom images?
Yes is the last_checkpoint file pointing to the correct path on your machine?
Kritz23
commented
4 years ago Are you trying it on custom images?
Yes is the last_checkpoint file pointing to the correct path on your machine?
Yes. ("MODEL.PRETRAINED_DETECTOR_CKPT causal_motifs_sgdet/model_0028000.pth")
Ankit-Vohra
commented
4 years ago Hi @mukesh-2538 , after solving your error, this error pops up. AttributeError: 'VGDataset' object has no attribute 'gt_classes' Did you solve this? Also, my question is why does it require ground truth for SGDET on custom images?
mukesh-2538
commented
4 years ago @Ankit-Vohra I am facing this issue in the latest commit
❓ Questions and Help
2020-08-14 07:57:08,698 maskrcnn_benchmark INFO: Using 1 GPUs 2020-08-14 07:57:08,698 maskrcnn_benchmark INFO: AMP_VERBOSE: False DATALOADER: ASPECT_RATIO_GROUPING: True NUM_WORKERS: 4 SIZE_DIVISIBILITY: 32 DATASETS: TEST: ('VG_stanford_filtered_with_attribute_test',) TRAIN: ('VG_stanford_filtered_with_attribute_train',) VAL: ('VG_stanford_filtered_with_attribute_val',) DETECTED_SGG_DIR: /content/image DTYPE: float16 GLOVE_DIR: /content/glove INPUT: BRIGHTNESS: 0.0 CONTRAST: 0.0 HUE: 0.0 MAX_SIZE_TEST: 1000 MAX_SIZE_TRAIN: 1000 MIN_SIZE_TEST: 600 MIN_SIZE_TRAIN: (600,) 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: ATTRIBUTE_ON: False BACKBONE: CONV_BODY: R-101-FPN FREEZE_CONV_BODY_AT: 2 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 FLIP_AUG: False FPN: USE_GN: False USE_RELU: False GROUP_NORM: DIM_PER_GP: -1 EPSILON: 1e-05 NUM_GROUPS: 32 KEYPOINT_ON: False MASK_ON: False META_ARCHITECTURE: GeneralizedRCNN PRETRAINED_DETECTOR_CKPT: /content/sgdetmodel/ RELATION_ON: True RESNETS: BACKBONE_OUT_CHANNELS: 256 DEFORMABLE_GROUPS: 1 NUM_GROUPS: 32 RES2_OUT_CHANNELS: 256 RES5_DILATION: 1 STAGE_WITH_DCN: (False, False, False, False) STEM_FUNC: StemWithFixedBatchNorm STEM_OUT_CHANNELS: 64 STRIDE_IN_1X1: False TRANS_FUNC: BottleneckWithFixedBatchNorm WIDTH_PER_GROUP: 8 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_ATTRIBUTE_HEAD: ATTRIBUTE_BGFG_RATIO: 3 ATTRIBUTE_BGFG_SAMPLE: True ATTRIBUTE_LOSS_WEIGHT: 1.0 FEATURE_EXTRACTOR: FPN2MLPFeatureExtractor MAX_ATTRIBUTES: 10 NUM_ATTRIBUTES: 201 POS_WEIGHT: 50.0 PREDICTOR: FPNPredictor SHARE_BOX_FEATURE_EXTRACTOR: True USE_BINARY_LOSS: True ROI_BOX_HEAD: CONV_HEAD_DIM: 256 DILATION: 1 FEATURE_EXTRACTOR: FPN2MLPFeatureExtractor MLP_HEAD_DIM: 4096 NUM_CLASSES: 151 NUM_STACKED_CONVS: 4 POOLER_RESOLUTION: 7 POOLER_SAMPLING_RATIO: 2 POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) PREDICTOR: FPNPredictor USE_GN: False ROI_HEADS: BATCH_SIZE_PER_IMAGE: 256 BBOX_REG_WEIGHTS: (10.0, 10.0, 5.0, 5.0) BG_IOU_THRESHOLD: 0.3 DETECTIONS_PER_IMG: 80 FG_IOU_THRESHOLD: 0.5 NMS: 0.3 NMS_FILTER_DUPLICATES: True POSITIVE_FRACTION: 0.5 POST_NMS_PER_CLS_TOPN: 300 SCORE_THRESH: 0.01 USE_FPN: True 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 ROI_RELATION_HEAD: ADD_GTBOX_TO_PROPOSAL_IN_TRAIN: True BATCH_SIZE_PER_IMAGE: 1024 CAUSAL: CONTEXT_LAYER: motifs EFFECT_ANALYSIS: True EFFECT_TYPE: TDE FUSION_TYPE: sum SEPARATE_SPATIAL: False SPATIAL_FOR_VISION: True CONTEXT_DROPOUT_RATE: 0.2 CONTEXT_HIDDEN_DIM: 512 CONTEXT_OBJ_LAYER: 1 CONTEXT_POOLING_DIM: 4096 CONTEXT_REL_LAYER: 1 EMBED_DIM: 200 FEATURE_EXTRACTOR: RelationFeatureExtractor LABEL_SMOOTHING_LOSS: False NUM_CLASSES: 51 NUM_SAMPLE_PER_GT_REL: 4 POOLING_ALL_LEVELS: True POSITIVE_FRACTION: 0.25 PREDICTOR: CausalAnalysisPredictor PREDICT_USE_BIAS: True PREDICT_USE_VISION: True REL_PROP: [0.01858, 0.00057, 0.00051, 0.00109, 0.0015, 0.00489, 0.00432, 0.02913, 0.00245, 0.00121, 0.00404, 0.0011, 0.00132, 0.00172, 5e-05, 0.00242, 0.0005, 0.00048, 0.00208, 0.15608, 0.0265, 0.06091, 0.009, 0.00183, 0.00225, 0.0009, 0.00028, 0.00077, 0.04844, 0.08645, 0.31621, 0.00088, 0.00301, 0.00042, 0.00186, 0.001, 0.00027, 0.01012, 0.0001, 0.01286, 0.00647, 0.00084, 0.01077, 0.00132, 0.00069, 0.00376, 0.00214, 0.11424, 0.01205, 0.02958] REQUIRE_BOX_OVERLAP: False TRANSFORMER: DROPOUT_RATE: 0.1 INNER_DIM: 2048 KEY_DIM: 64 NUM_HEAD: 8 OBJ_LAYER: 4 REL_LAYER: 2 VAL_DIM: 64 USE_GT_BOX: False USE_GT_OBJECT_LABEL: False RPN: ANCHOR_SIZES: (32, 64, 128, 256, 512) ANCHOR_STRIDE: (4, 8, 16, 32, 64) ASPECT_RATIOS: (0.23232838, 0.63365731, 1.28478321, 3.15089189) BATCH_SIZE_PER_IMAGE: 256 BG_IOU_THRESHOLD: 0.3 FG_IOU_THRESHOLD: 0.7 FPN_POST_NMS_PER_BATCH: False FPN_POST_NMS_TOP_N_TEST: 1000 FPN_POST_NMS_TOP_N_TRAIN: 1000 MIN_SIZE: 0 NMS_THRESH: 0.7 POSITIVE_FRACTION: 0.5 POST_NMS_TOP_N_TEST: 1000 POST_NMS_TOP_N_TRAIN: 1000 PRE_NMS_TOP_N_TEST: 6000 PRE_NMS_TOP_N_TRAIN: 6000 RPN_HEAD: SingleConvRPNHead RPN_MID_CHANNEL: 256 STRADDLE_THRESH: 0 USE_FPN: True RPN_ONLY: False VGG: VGG16_OUT_CHANNELS: 512 WEIGHT: catalog://ImageNetPretrained/FAIR/20171220/X-101-32x8d OUTPUT_DIR: /content/sgdetmodel/ PATHS_CATALOG: /content/Scene/maskrcnn_benchmark/config/paths_catalog.py PATHS_DATA: /content/Scene/maskrcnn_benchmark/config/../data/datasets SOLVER: BASE_LR: 0.01 BIAS_LR_FACTOR: 1 CHECKPOINT_PERIOD: 2000 CLIP_NORM: 5.0 GAMMA: 0.1 GRAD_NORM_CLIP: 5.0 IMS_PER_BATCH: 16 MAX_ITER: 40000 MOMENTUM: 0.9 PRE_VAL: True PRINT_GRAD_FREQ: 4000 SCHEDULE: COOLDOWN: 0 FACTOR: 0.1 MAX_DECAY_STEP: 3 PATIENCE: 2 THRESHOLD: 0.001 TYPE: WarmupReduceLROnPlateau STEPS: (10000, 16000) TO_VAL: True UPDATE_SCHEDULE_DURING_LOAD: False VAL_PERIOD: 2000 WARMUP_FACTOR: 0.1 WARMUP_ITERS: 500 WARMUP_METHOD: linear WEIGHT_DECAY: 0.0001 WEIGHT_DECAY_BIAS: 0.0 TEST: ALLOW_LOAD_FROM_CACHE: False BBOX_AUG: ENABLED: False H_FLIP: False MAX_SIZE: 4000 SCALES: () SCALE_H_FLIP: False CUSTUM_EVAL: True CUSTUM_PATH: /content/image DETECTIONS_PER_IMG: 100 EXPECTED_RESULTS: [] EXPECTED_RESULTS_SIGMA_TOL: 4 IMS_PER_BATCH: 1 RELATION: IOU_THRESHOLD: 0.5 LATER_NMS_PREDICTION_THRES: 0.5 MULTIPLE_PREDS: False REQUIRE_OVERLAP: False SYNC_GATHER: True SAVE_PROPOSALS: False 2020-08-14 07:57:08,699 maskrcnn_benchmark INFO: Collecting env info (might take some time) 2020-08-14 07:57:09,863 maskrcnn_benchmark INFO: PyTorch version: 1.5.0+cu101 Is debug build: No CUDA used to build PyTorch: 10.1
OS: Ubuntu 18.04.3 LTS GCC version: (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 CMake version: version 3.12.0
Python version: 3.6 Is CUDA available: Yes CUDA runtime version: 10.1.243 GPU models and configuration: GPU 0: Tesla T4 Nvidia driver version: 418.67 cuDNN version: /usr/lib/x86_64-linux-gnu/libcudnn.so.7.6.5
Versions of relevant libraries: [pip3] numpy==1.18.5 [pip3] torch==1.5.0+cu101 [pip3] torchsummary==1.5.1 [pip3] torchtext==0.3.1 [pip3] torchvision==0.6.0+cu101 [conda] Could not collect Pillow (7.0.0) 2020-08-14 07:57:13,530 maskrcnn_benchmark.data.build INFO: ---------------------------------------------------------------------------------------------------- 2020-08-14 07:57:13,530 maskrcnn_benchmark.data.build INFO: get dataset statistics... 2020-08-14 07:57:13,530 maskrcnn_benchmark.data.build INFO: Loading data statistics from: /content/sgdetmodel/VG_stanford_filtered_with_attribute_train_statistics.cache 2020-08-14 07:57:13,530 maskrcnn_benchmark.data.build INFO: ---------------------------------------------------------------------------------------------------- loading word vectors from /content/glove/glove.6B.200d.pt background -> background fail on background loading word vectors from /content/glove/glove.6B.200d.pt background -> background fail on background 2020-08-14 07:57:18,746 maskrcnn_benchmark.utils.checkpoint INFO: Loading checkpoint from /content/sgdetmodel/model_0028000.pth Traceback (most recent call last): File "tools/relation_test_net.py", line 112, in
main()
File "tools/relation_test_net.py", line 94, in main
data_loaders_val = make_data_loader(cfg, mode="test", is_distributed=distributed)
File "/content/Scene/maskrcnn_benchmark/data/build.py", line 240, in make_data_loader
custom_data_info['ind_to_classes'] = dataset.ind_to_classes
AttributeError: 'VGDataset' object has no attribute 'ind_to_classes'
Traceback (most recent call last):
File "/usr/lib/python3.6/runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "/usr/lib/python3.6/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/usr/local/lib/python3.6/dist-packages/torch/distributed/launch.py", line 263, in
main()
File "/usr/local/lib/python3.6/dist-packages/torch/distributed/launch.py", line 259, in main
cmd=cmd)
subprocess.CalledProcessError: Command '['/usr/bin/python3', '-u', 'tools/relation_test_net.py', '--local_rank=0', '--config-file', 'configs/e2e_relation_X_101_32_8_FPN_1x.yaml', 'MODEL.ROI_RELATION_HEAD.USE_GT_BOX', 'False', 'MODEL.ROI_RELATION_HEAD.USE_GT_OBJECT_LABEL', 'False', 'MODEL.ROI_RELATION_HEAD.PREDICTOR', 'CausalAnalysisPredictor', 'MODEL.ROI_RELATION_HEAD.CAUSAL.EFFECT_TYPE', 'TDE', 'MODEL.ROI_RELATION_HEAD.CAUSAL.FUSION_TYPE', 'sum', 'MODEL.ROI_RELATION_HEAD.CAUSAL.CONTEXT_LAYER', 'motifs', 'TEST.IMS_PER_BATCH', '1', 'DTYPE', 'float16', 'GLOVE_DIR', '/content/glove', 'MODEL.PRETRAINED_DETECTOR_CKPT', '/content/sgdetmodel/', 'OUTPUT_DIR', '/content/sgdetmodel/', 'TEST.CUSTUM_EVAL', 'True', 'TEST.CUSTUM_PATH', '/content/image', 'DETECTED_SGG_DIR', '/content/image']' returned non-zero exit status 1.