search

chensnathan / YOLOF

You Only Look One-level Feature (YOLOF), CVPR2021, Detectron2
MIT License
271 stars 28 forks source link

mAP is very low #38

Closed shenhaibb closed 2 years ago

shenhaibb commented 2 years ago

my dataset only has one class, my training log is below, why is my ap only 22?

[04/24 08:11:21] detectron2 INFO: Rank of current process: 0. World size: 1 [04/24 08:11:21] detectron2 INFO: Environment info:

sys.platform linux Python 3.7.13 (default, Mar 29 2022, 02:18:16) [GCC 7.5.0] numpy 1.21.6 detectron2 0.6 @/media/henu/新加卷1/rxh/YOLOF-master/detectron2/detectron2 Compiler GCC 9.4 CUDA compiler CUDA 11.4 detectron2 arch flags 7.0 DETECTRON2_ENV_MODULE PyTorch 1.9.0+cu111 @/home/henu/anaconda3/envs/YOLOF/lib/python3.7/site-packages/torch PyTorch debug build False GPU available Yes GPU 0 NVIDIA GeForce RTX 3070 (arch=8.6) Driver version 470.103.01 CUDA_HOME /usr/local/cuda Pillow 9.1.0 torchvision 0.10.0+cu111 @/home/henu/anaconda3/envs/YOLOF/lib/python3.7/site-packages/torchvision torchvision arch flags 3.5, 5.0, 6.0, 7.0, 7.5, 8.0, 8.6 fvcore 0.1.5.post20220414 iopath 0.1.9 cv2 4.5.5

PyTorch built with:

[04/24 08:11:21] detectron2 INFO: Command line arguments: Namespace(config_file='../configs/yolof_CSP_D_53_DC5_9x_stage2_3x.yaml', dist_url='tcp://127.0.0.1:50152', eval_only=False, machine_rank=0, num_gpus=0, num_machines=1, opts=[], resume=False) [04/24 08:11:21] detectron2 INFO: Contents of args.config_file=../configs/yolof_CSP_D_53_DC5_9x_stage2_3x.yaml: BASE: "Base-YOLOF.yaml" MODEL: WEIGHTS: ""

or

WEIGHTS: "./output/yolof/CSP_D_53_DC5_9x/model_final.pth"

META_ARCHITECTURE: "YOLOF" BACKBONE: NAME: "build_darknet_backbone" DARKNET: NORM: "BN" RES5_DILATION: 2 ANCHOR_GENERATOR: SIZES: [[16, 32, 64, 128, 256, 512]] YOLOF: ENCODER: IN_CHANNELS: 1024 NUM_RESIDUAL_BLOCKS: 8 BLOCK_DILATIONS: [1, 2, 3, 4, 5, 6, 7, 8] NORM: "BN" ACTIVATION: "LeakyReLU" DECODER: NUM_ANCHORS: 6 NORM: "BN" ACTIVATION: "LeakyReLU" POS_IGNORE_THRESHOLD: 0.1 NEG_IGNORE_THRESHOLD: 0.8 INPUT: JITTER_CROP: ENABLED: True RESIZE: ENABLED: True DISTORTION: ENABLED: True MOSAIC: ENABLED: True OUTPUT_DIR: "output/yolof/CSP_D_53_DC5_3x"

[04/24 08:11:21] detectron2 INFO: Running with full config: CUDNN_BENCHMARK: false DATALOADER: ASPECT_RATIO_GROUPING: true FILTER_EMPTY_ANNOTATIONS: true NUM_WORKERS: 8 REPEAT_THRESHOLD: 0.0 SAMPLER_TRAIN: TrainingSampler DATASETS: PRECOMPUTED_PROPOSAL_TOPK_TEST: 1000 PRECOMPUTED_PROPOSAL_TOPK_TRAIN: 2000 PROPOSAL_FILES_TEST: [] PROPOSAL_FILES_TRAIN: [] TEST:

[04/24 08:11:21] detectron2 INFO: Full config saved to output/yolof/CSP_D_53_DC5_3x/config.yaml [04/24 08:11:21] d2.utils.env INFO: Using a generated random seed 21895643 [04/24 08:11:24] d2.engine.defaults INFO: Model: YOLOF( (backbone): DarkNet( (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn1): BatchNorm2d(32, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (act1): MishCuda() (layer1): CrossStagePartialBlock( (base_layer): Sequential( (0): Conv2d(32, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): BatchNorm2d(64, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (2): MishCuda() ) (partial_transition1): Sequential( (0): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(64, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (2): MishCuda() ) (stage_layers): Sequential( (0): DarkBlock( (downsample): Sequential( (0): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(64, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (2): MishCuda() ) (bn1): BatchNorm2d(32, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (bn2): BatchNorm2d(64, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (conv1): Conv2d(64, 32, kernel_size=(1, 1), stride=(1, 1), bias=False) (conv2): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (activation): MishCuda() ) ) (partial_transition2): Sequential( (0): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(64, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (2): MishCuda() ) (fuse_transition): Sequential( (0): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(64, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (2): MishCuda() ) ) (layer2): CrossStagePartialBlock( (base_layer): Sequential( (0): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): BatchNorm2d(128, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (2): MishCuda() ) (partial_transition1): Sequential( (0): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(64, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (2): MishCuda() ) (stage_layers): Sequential( (0): DarkBlock( (downsample): Sequential( (0): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(64, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (2): MishCuda() ) (bn1): BatchNorm2d(64, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (bn2): BatchNorm2d(64, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (activation): MishCuda() ) (1): DarkBlock( (bn1): BatchNorm2d(64, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (bn2): BatchNorm2d(64, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (activation): MishCuda() ) ) (partial_transition2): Sequential( (0): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(64, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (2): MishCuda() ) (fuse_transition): Sequential( (0): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(128, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (2): MishCuda() ) ) (layer3): CrossStagePartialBlock( (base_layer): Sequential( (0): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): BatchNorm2d(256, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (2): MishCuda() ) (partial_transition1): Sequential( (0): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(128, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (2): MishCuda() ) (stage_layers): Sequential( (0): DarkBlock( (downsample): Sequential( (0): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(128, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (2): MishCuda() ) (bn1): BatchNorm2d(128, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (bn2): BatchNorm2d(128, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (conv1): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (activation): MishCuda() ) (1): DarkBlock( (bn1): BatchNorm2d(128, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (bn2): BatchNorm2d(128, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (conv1): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (activation): MishCuda() ) (2): DarkBlock( (bn1): BatchNorm2d(128, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (bn2): BatchNorm2d(128, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (conv1): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (activation): MishCuda() ) (3): DarkBlock( (bn1): BatchNorm2d(128, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (bn2): BatchNorm2d(128, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (conv1): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (activation): MishCuda() ) (4): DarkBlock( (bn1): BatchNorm2d(128, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (bn2): BatchNorm2d(128, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (conv1): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (activation): MishCuda() ) (5): DarkBlock( (bn1): BatchNorm2d(128, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (bn2): BatchNorm2d(128, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (conv1): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (activation): MishCuda() ) (6): DarkBlock( (bn1): BatchNorm2d(128, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (bn2): BatchNorm2d(128, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (conv1): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (activation): MishCuda() ) (7): DarkBlock( (bn1): BatchNorm2d(128, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (bn2): BatchNorm2d(128, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (conv1): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (activation): MishCuda() ) ) (partial_transition2): Sequential( (0): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(128, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (2): MishCuda() ) (fuse_transition): Sequential( (0): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(256, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (2): MishCuda() ) ) (layer4): CrossStagePartialBlock( (base_layer): Sequential( (0): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (2): MishCuda() ) (partial_transition1): Sequential( (0): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(256, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (2): MishCuda() ) (stage_layers): Sequential( (0): DarkBlock( (downsample): Sequential( (0): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(256, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (2): MishCuda() ) (bn1): BatchNorm2d(256, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (bn2): BatchNorm2d(256, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (conv1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (activation): MishCuda() ) (1): DarkBlock( (bn1): BatchNorm2d(256, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (bn2): BatchNorm2d(256, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (conv1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (activation): MishCuda() ) (2): DarkBlock( (bn1): BatchNorm2d(256, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (bn2): BatchNorm2d(256, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (conv1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (activation): MishCuda() ) (3): DarkBlock( (bn1): BatchNorm2d(256, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (bn2): BatchNorm2d(256, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (conv1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (activation): MishCuda() ) (4): DarkBlock( (bn1): BatchNorm2d(256, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (bn2): BatchNorm2d(256, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (conv1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (activation): MishCuda() ) (5): DarkBlock( (bn1): BatchNorm2d(256, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (bn2): BatchNorm2d(256, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (conv1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (activation): MishCuda() ) (6): DarkBlock( (bn1): BatchNorm2d(256, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (bn2): BatchNorm2d(256, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (conv1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (activation): MishCuda() ) (7): DarkBlock( (bn1): BatchNorm2d(256, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (bn2): BatchNorm2d(256, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (conv1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (activation): MishCuda() ) ) (partial_transition2): Sequential( (0): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(256, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (2): MishCuda() ) (fuse_transition): Sequential( (0): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(512, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (2): MishCuda() ) ) (layer5): CrossStagePartialBlock( (base_layer): Sequential( (0): Conv2d(512, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(2, 2), dilation=(2, 2), bias=False) (1): BatchNorm2d(1024, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (2): MishCuda() ) (partial_transition1): Sequential( (0): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(512, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (2): MishCuda() ) (stage_layers): Sequential( (0): DarkBlock( (downsample): Sequential( (0): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(512, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (2): MishCuda() ) (bn1): BatchNorm2d(512, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (bn2): BatchNorm2d(512, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (conv1): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(2, 2), dilation=(2, 2), bias=False) (activation): MishCuda() ) (1): DarkBlock( (bn1): BatchNorm2d(512, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (bn2): BatchNorm2d(512, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (conv1): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(2, 2), dilation=(2, 2), bias=False) (activation): MishCuda() ) (2): DarkBlock( (bn1): BatchNorm2d(512, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (bn2): BatchNorm2d(512, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (conv1): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(2, 2), dilation=(2, 2), bias=False) (activation): MishCuda() ) (3): DarkBlock( (bn1): BatchNorm2d(512, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (bn2): BatchNorm2d(512, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (conv1): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(2, 2), dilation=(2, 2), bias=False) (activation): MishCuda() ) ) (partial_transition2): Sequential( (0): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(512, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (2): MishCuda() ) (fuse_transition): Sequential( (0): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(1024, eps=0.0001, momentum=0.03, affine=True, track_running_stats=True) (2): MishCuda() ) ) ) (encoder): DilatedEncoder( (lateral_conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1)) (lateral_norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (fpn_conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (fpn_norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (dilated_encoder_blocks): Sequential( (0): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) ) ) (1): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(2, 2), dilation=(2, 2)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) ) ) (2): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(3, 3), dilation=(3, 3)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) ) ) (3): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(4, 4), dilation=(4, 4)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) ) ) (4): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(5, 5), dilation=(5, 5)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) ) ) (5): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(6, 6), dilation=(6, 6)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) ) ) (6): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(7, 7), dilation=(7, 7)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) ) ) (7): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(8, 8), dilation=(8, 8)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) ) ) ) ) (decoder): Decoder( (cls_subnet): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): LeakyReLU(negative_slope=0.1, inplace=True) ) (bbox_subnet): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): LeakyReLU(negative_slope=0.1, inplace=True) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): LeakyReLU(negative_slope=0.1, inplace=True) (6): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (7): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (8): LeakyReLU(negative_slope=0.1, inplace=True) (9): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (10): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (11): LeakyReLU(negative_slope=0.1, inplace=True) ) (cls_score): Conv2d(512, 480, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (bbox_pred): Conv2d(512, 24, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (object_pred): Conv2d(512, 6, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (anchor_generator): DefaultAnchorGenerator( (cell_anchors): BufferList() ) (anchor_matcher): UniformMatcher() ) [04/24 08:11:24] d2.data.datasets.coco INFO: Loaded 1597 images in COCO format from ../datasets/waste/annotations/instances_train2017.json [04/24 08:11:24] d2.data.build INFO: Removed 0 images with no usable annotations. 1597 images left. [04/24 08:11:24] d2.data.build INFO: Distribution of instances among all 1 categories:  category #instances
waste 4481

[04/24 08:11:24] d2.data.build INFO: Using training sampler TrainingSampler [04/24 08:11:24] d2.data.common INFO: Serializing 1597 elements to byte tensors and concatenating them all ... [04/24 08:11:24] d2.data.common INFO: Serialized dataset takes 0.56 MiB [04/24 08:11:24] fvcore.common.checkpoint INFO: No checkpoint found. Initializing model from scratch [04/24 08:11:24] d2.engine.train_loop INFO: Starting training from iteration 0 [04/24 08:11:26] d2.utils.events INFO: eta: 0:36:32 iter: 19 total_loss: 2.364 loss_cls: 1.376 loss_box_reg: 0.9352 time: 0.0964 data_time: 0.0208 lr: 1.1126e-05 max_mem: 1553M ...... [04/24 10:04:25] d2.utils.events INFO: eta: 0:00:05 iter: 22479 total_loss: 0.9622 loss_cls: 0.4854 loss_box_reg: 0.4483 time: 0.2895 data_time: 0.0056 lr: 5.01e-06 max_mem: 4488M [04/24 10:04:30] fvcore.common.checkpoint INFO: Saving checkpoint to output/yolof/CSP_D_53_DC5_3x/model_0022499.pth [04/24 10:04:32] fvcore.common.checkpoint INFO: Saving checkpoint to output/yolof/CSP_D_53_DC5_3x/model_final.pth [04/24 10:04:33] d2.utils.events INFO: eta: 0:00:00 iter: 22499 total_loss: 0.9663 loss_cls: 0.5062 loss_box_reg: 0.4621 time: 0.2895 data_time: 0.0056 lr: 5.01e-06 max_mem: 4488M [04/24 10:04:36] d2.engine.hooks INFO: Overall training speed: 22498 iterations in 1:48:33 (0.2895 s / it) [04/24 10:04:36] d2.engine.hooks INFO: Total training time: 1:50:17 (0:01:44 on hooks) [04/24 10:04:37] d2.data.datasets.coco INFO: Loaded 399 images in COCO format from ../datasets/waste/annotations/instances_val2017.json [04/24 10:04:37] d2.data.build INFO: Distribution of instances among all 1 categories:  category #instances
waste 1081

[04/24 10:04:37] d2.data.common INFO: Serializing 399 elements to byte tensors and concatenating them all ... [04/24 10:04:37] d2.data.common INFO: Serialized dataset takes 0.14 MiB [04/24 10:04:37] d2.evaluation.evaluator INFO: Start inference on 399 batches [04/24 10:04:37] d2.evaluation.evaluator INFO: Inference done 11/399. Dataloading: 0.0006 s/iter. Inference: 0.0287 s/iter. Eval: 0.0002 s/iter. Total: 0.0294 s/iter. ETA=0:00:11 [04/24 10:04:42] d2.evaluation.evaluator INFO: Inference done 186/399. Dataloading: 0.0006 s/iter. Inference: 0.0276 s/iter. Eval: 0.0004 s/iter. Total: 0.0287 s/iter. ETA=0:00:06 [04/24 10:04:47] d2.evaluation.evaluator INFO: Inference done 364/399. Dataloading: 0.0006 s/iter. Inference: 0.0275 s/iter. Eval: 0.0003 s/iter. Total: 0.0285 s/iter. ETA=0:00:00 [04/24 10:04:48] d2.evaluation.evaluator INFO: Total inference time: 0:00:11.249452 (0.028552 s / iter per device, on 1 devices) [04/24 10:04:48] d2.evaluation.evaluator INFO: Total inference pure compute time: 0:00:10 (0.027472 s / iter per device, on 1 devices) [04/24 10:04:48] d2.evaluation.coco_evaluation INFO: Preparing results for COCO format ... [04/24 10:04:48] d2.evaluation.coco_evaluation INFO: Saving results to output/yolof/CSP_D_53_DC5_3x/inference/coco_instances_results.json [04/24 10:04:49] d2.evaluation.coco_evaluation INFO: Evaluating predictions with unofficial COCO API... [04/24 10:04:49] d2.evaluation.fast_eval_api INFO: Evaluate annotation type bbox [04/24 10:04:49] d2.evaluation.fast_eval_api INFO: COCOeval_opt.evaluate() finished in 0.11 seconds. [04/24 10:04:49] d2.evaluation.fast_eval_api INFO: Accumulating evaluation results... [04/24 10:04:49] d2.evaluation.fast_eval_api INFO: COCOeval_opt.accumulate() finished in 0.04 seconds. [04/24 10:04:49] d2.evaluation.coco_evaluation INFO: Evaluation results for bbox: AP AP50 AP75 APs APm APl
9.092 22.634 5.217 1.165 9.953 8.744

[04/24 10:04:49] d2.engine.defaults INFO: Evaluation results for coco_my_val in csv format: [04/24 10:04:49] d2.evaluation.testing INFO: copypaste: Task: bbox [04/24 10:04:49] d2.evaluation.testing INFO: copypaste: AP,AP50,AP75,APs,APm,APl [04/24 10:04:49] d2.evaluation.testing INFO: copypaste: 9.0921,22.6339,5.2169,1.1645,9.9529,8.7440

shenhaibb commented 2 years ago

sorry, i forget set steps corresponding yaml