Training AP is always 0 using coco128 dataset #1760

Jessica-hub · 2024-03-03T21:08:27Z

I used the coco128 and unzip into the datasets folder. The command is python tools/train.py -f exps/example/custom/yolox_s.py -d 1 -b 32 --fp16 -o -c C:\Users\olivi\YOLOX\pretrained\yolox_s.pth However, the APs have a lot of nan and 0. The log details are below.

2024-03-03 15:05:28 | INFO | yolox.core.trainer:130 - args: Namespace(experiment_name='yolox_s', name=None, dist_backend='nccl', dist_url=None, batch_size=32, devices=1, exp_file='exps/example/custom/yolox_s.py', resume=False, ckpt='C:\Users\olivi\YOLOX\pretrained\yolox_s.pth', start_epoch=None, num_machines=1, machine_rank=0, fp16=True, cache=None, occupy=True, logger='tensorboard', opts=[])
2024-03-03 15:05:28 | INFO | yolox.core.trainer:131 - exp value:
╒═══════════════════╤════════════════════════════╕
│ keys │ values │
╞═══════════════════╪════════════════════════════╡
│ seed │ None │
├───────────────────┼────────────────────────────┤
│ output_dir │ './YOLOX_outputs' │
├───────────────────┼────────────────────────────┤
│ print_interval │ 10 │
├───────────────────┼────────────────────────────┤
│ eval_interval │ 1 │
├───────────────────┼────────────────────────────┤
│ dataset │ None │
├───────────────────┼────────────────────────────┤
│ num_classes │ 71 │
├───────────────────┼────────────────────────────┤
│ depth │ 0.33 │
├───────────────────┼────────────────────────────┤
│ width │ 0.5 │
├───────────────────┼────────────────────────────┤
│ act │ 'silu' │
├───────────────────┼────────────────────────────┤
│ data_num_workers │ 4 │
├───────────────────┼────────────────────────────┤
│ input_size │ (640, 640) │
├───────────────────┼────────────────────────────┤
│ multiscale_range │ 5 │
├───────────────────┼────────────────────────────┤
│ data_dir │ 'datasets/coco128' │
├───────────────────┼────────────────────────────┤
│ train_ann │ 'instances_train2017.json' │
├───────────────────┼────────────────────────────┤
│ val_ann │ 'instances_val2017.json' │
├───────────────────┼────────────────────────────┤
│ test_ann │ 'instances_test2017.json' │
├───────────────────┼────────────────────────────┤
│ mosaic_prob │ 1.0 │
├───────────────────┼────────────────────────────┤
│ mixup_prob │ 1.0 │
├───────────────────┼────────────────────────────┤
│ hsv_prob │ 1.0 │
├───────────────────┼────────────────────────────┤
│ flip_prob │ 0.5 │
├───────────────────┼────────────────────────────┤
│ degrees │ 10.0 │
├───────────────────┼────────────────────────────┤
│ translate │ 0.1 │
├───────────────────┼────────────────────────────┤
│ mosaic_scale │ (0.1, 2) │
├───────────────────┼────────────────────────────┤
│ enable_mixup │ True │
├───────────────────┼────────────────────────────┤
│ mixup_scale │ (0.5, 1.5) │
├───────────────────┼────────────────────────────┤
│ shear │ 2.0 │
├───────────────────┼────────────────────────────┤
│ warmup_epochs │ 5 │
├───────────────────┼────────────────────────────┤
│ max_epoch │ 300 │
├───────────────────┼────────────────────────────┤
│ warmup_lr │ 0 │
├───────────────────┼────────────────────────────┤
│ min_lr_ratio │ 0.05 │
├───────────────────┼────────────────────────────┤
│ basic_lr_per_img │ 0.00015625 │
├───────────────────┼────────────────────────────┤
│ scheduler │ 'yoloxwarmcos' │
├───────────────────┼────────────────────────────┤
│ no_aug_epochs │ 15 │
├───────────────────┼────────────────────────────┤
│ ema │ True │
├───────────────────┼────────────────────────────┤
│ weight_decay │ 0.0005 │
├───────────────────┼────────────────────────────┤
│ momentum │ 0.9 │
├───────────────────┼────────────────────────────┤
│ save_history_ckpt │ True │
├───────────────────┼────────────────────────────┤
│ exp_name │ 'yolox_s' │
├───────────────────┼────────────────────────────┤
│ test_size │ (640, 640) │
├───────────────────┼────────────────────────────┤
│ test_conf │ 0.01 │
├───────────────────┼────────────────────────────┤
│ nmsthre │ 0.65 │
╘═══════════════════╧════════════════════════════╛
qt.qpa.fonts: Unable to open default EUDC font: "EUDC.TTE"
2024-03-03 15:05:34 | INFO | yolox.core.trainer:136 - Model Summary: Params: 8.96M, Gflops: 26.91
2024-03-03 15:05:34 | INFO | yolox.core.trainer:319 - loading checkpoint for fine tuning
2024-03-03 15:05:35 | WARNING | yolox.utils.checkpoint:24 - Shape of head.cls_preds.0.weight in checkpoint is torch.Size([80, 128, 1, 1]), while shape of head.cls_preds.0.weight in model is torch.Size([71, 128, 1, 1]).
2024-03-03 15:05:35 | WARNING | yolox.utils.checkpoint:24 - Shape of head.cls_preds.0.bias in checkpoint is torch.Size([80]), while shape of head.cls_preds.0.bias in model is torch.Size([71]).
2024-03-03 15:05:35 | WARNING | yolox.utils.checkpoint:24 - Shape of head.cls_preds.1.weight in checkpoint is torch.Size([80, 128, 1, 1]), while shape of head.cls_preds.1.weight in model is torch.Size([71, 128, 1, 1]).
2024-03-03 15:05:35 | WARNING | yolox.utils.checkpoint:24 - Shape of head.cls_preds.1.bias in checkpoint is torch.Size([80]), while shape of head.cls_preds.1.bias in model is torch.Size([71]).
2024-03-03 15:05:35 | WARNING | yolox.utils.checkpoint:24 - Shape of head.cls_preds.2.weight in checkpoint is torch.Size([80, 128, 1, 1]), while shape of head.cls_preds.2.weight in model is torch.Size([71, 128, 1, 1]).
2024-03-03 15:05:35 | WARNING | yolox.utils.checkpoint:24 - Shape of head.cls_preds.2.bias in checkpoint is torch.Size([80]), while shape of head.cls_preds.2.bias in model is torch.Size([71]).
2024-03-03 15:05:35 | INFO | yolox.data.datasets.coco:63 - loading annotations into memory...
2024-03-03 15:05:35 | INFO | yolox.data.datasets.coco:63 - Done (t=0.00s)
2024-03-03 15:05:35 | INFO | pycocotools.coco:86 - creating index...
2024-03-03 15:05:35 | INFO | pycocotools.coco:86 - index created!
2024-03-03 15:05:35 | INFO | yolox.core.trainer:155 - init prefetcher, this might take one minute or less...
C:\Users\olivi\yolox\yolox\utils\metric.py:43: UserWarning: The torch.cuda.DtypeTensor constructors are no longer recommended. It's best to use methods such as torch.tensor(data, dtype=, device='cuda') to create tensors. (Triggered internally at ..\torch\csrc\tensor\python_tensor.cpp:85.)
x = torch.cuda.FloatTensor(256, 1024, block_mem)
2024-03-03 15:05:52 | INFO | yolox.data.datasets.coco:63 - loading annotations into memory...
2024-03-03 15:05:52 | INFO | yolox.data.datasets.coco:63 - Done (t=0.01s)
2024-03-03 15:05:52 | INFO | pycocotools.coco:86 - creating index...
2024-03-03 15:05:52 | INFO | pycocotools.coco:86 - index created!
2024-03-03 15:05:52 | INFO | yolox.core.trainer:191 - Training start...
2024-03-03 15:05:52 | INFO | yolox.core.trainer:192 -
YOLOX(
(backbone): YOLOPAFPN(
(backbone): CSPDarknet(
(stem): Focus(
(conv): BaseConv(
(conv): Conv2d(12, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
(dark2): Sequential(
(0): BaseConv(
(conv): Conv2d(32, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(1): CSPLayer(
(conv1): BaseConv(
(conv): Conv2d(64, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv2): BaseConv(
(conv): Conv2d(64, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv3): BaseConv(
(conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(m): Sequential(
(0): Bottleneck(
(conv1): BaseConv(
(conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv2): BaseConv(
(conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
)
)
)
(dark3): Sequential(
(0): BaseConv(
(conv): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(1): CSPLayer(
(conv1): BaseConv(
(conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv2): BaseConv(
(conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv3): BaseConv(
(conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(m): Sequential(
(0): Bottleneck(
(conv1): BaseConv(
(conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv2): BaseConv(
(conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
(1): Bottleneck(
(conv1): BaseConv(
(conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv2): BaseConv(
(conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
(2): Bottleneck(
(conv1): BaseConv(
(conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv2): BaseConv(
(conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
)
)
)
(dark4): Sequential(
(0): BaseConv(
(conv): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(1): CSPLayer(
(conv1): BaseConv(
(conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv2): BaseConv(
(conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv3): BaseConv(
(conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(m): Sequential(
(0): Bottleneck(
(conv1): BaseConv(
(conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv2): BaseConv(
(conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
(1): Bottleneck(
(conv1): BaseConv(
(conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv2): BaseConv(
(conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
(2): Bottleneck(
(conv1): BaseConv(
(conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv2): BaseConv(
(conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
)
)
)
(dark5): Sequential(
(0): BaseConv(
(conv): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(1): SPPBottleneck(
(conv1): BaseConv(
(conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(m): ModuleList(
(0): MaxPool2d(kernel_size=5, stride=1, padding=2, dilation=1, ceil_mode=False)
(1): MaxPool2d(kernel_size=9, stride=1, padding=4, dilation=1, ceil_mode=False)
(2): MaxPool2d(kernel_size=13, stride=1, padding=6, dilation=1, ceil_mode=False)
)
(conv2): BaseConv(
(conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
(2): CSPLayer(
(conv1): BaseConv(
(conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv2): BaseConv(
(conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv3): BaseConv(
(conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(m): Sequential(
(0): Bottleneck(
(conv1): BaseConv(
(conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv2): BaseConv(
(conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
)
)
)
)
(upsample): Upsample(scale_factor=2.0, mode='nearest')
(lateral_conv0): BaseConv(
(conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(C3_p4): CSPLayer(
(conv1): BaseConv(
(conv): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv2): BaseConv(
(conv): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv3): BaseConv(
(conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(m): Sequential(
(0): Bottleneck(
(conv1): BaseConv(
(conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv2): BaseConv(
(conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
)
)
(reduce_conv1): BaseConv(
(conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(C3_p3): CSPLayer(
(conv1): BaseConv(
(conv): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv2): BaseConv(
(conv): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv3): BaseConv(
(conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(m): Sequential(
(0): Bottleneck(
(conv1): BaseConv(
(conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv2): BaseConv(
(conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
)
)
(bu_conv2): BaseConv(
(conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(C3_n3): CSPLayer(
(conv1): BaseConv(
(conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv2): BaseConv(
(conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv3): BaseConv(
(conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(m): Sequential(
(0): Bottleneck(
(conv1): BaseConv(
(conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv2): BaseConv(
(conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
)
)
(bu_conv1): BaseConv(
(conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(C3_n4): CSPLayer(
(conv1): BaseConv(
(conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv2): BaseConv(
(conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv3): BaseConv(
(conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(m): Sequential(
(0): Bottleneck(
(conv1): BaseConv(
(conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(conv2): BaseConv(
(conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
)
)
)
(head): YOLOXHead(
(cls_convs): ModuleList(
(0-2): 3 x Sequential(
(0): BaseConv(
(conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(1): BaseConv(
(conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
)
(reg_convs): ModuleList(
(0-2): 3 x Sequential(
(0): BaseConv(
(conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(1): BaseConv(
(conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
)
(cls_preds): ModuleList(
(0-2): 3 x Conv2d(128, 71, kernel_size=(1, 1), stride=(1, 1))
)
(reg_preds): ModuleList(
(0-2): 3 x Conv2d(128, 4, kernel_size=(1, 1), stride=(1, 1))
)
(obj_preds): ModuleList(
(0-2): 3 x Conv2d(128, 1, kernel_size=(1, 1), stride=(1, 1))
)
(stems): ModuleList(
(0): BaseConv(
(conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(1): BaseConv(
(conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
(2): BaseConv(
(conv): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
(act): SiLU(inplace=True)
)
)
(l1_loss): L1Loss()
(bcewithlog_loss): BCEWithLogitsLoss()
(iou_loss): IOUloss()
)
)
2024-03-03 15:05:52 | INFO | yolox.core.trainer:203 - ---> start train epoch1
2024-03-03 15:05:59 | INFO | yolox.core.trainer:364 - Save weights to ./YOLOX_outputs\yolox_s
100%|####################################################################################| 1/1 [00:05<00:00, 5.11s/it]
2024-03-03 15:06:04 | INFO | yolox.evaluators.coco_evaluator:259 - Evaluate in main process...
2024-03-03 15:06:04 | INFO | yolox.evaluators.coco_evaluator:292 - Loading and preparing results...
2024-03-03 15:06:04 | INFO | yolox.evaluators.coco_evaluator:292 - DONE (t=0.01s)
2024-03-03 15:06:04 | INFO | pycocotools.coco:366 - creating index...
2024-03-03 15:06:04 | INFO | pycocotools.coco:366 - index created!
2024-03-03 15:06:04 | INFO | yolox.evaluators.coco_evaluator:302 - Running per image evaluation...
2024-03-03 15:06:04 | INFO | yolox.evaluators.coco_evaluator:302 - Evaluate annotation type bbox
2024-03-03 15:06:04 | INFO | yolox.evaluators.coco_evaluator:302 - DONE (t=0.01s).
2024-03-03 15:06:04 | INFO | yolox.evaluators.coco_evaluator:303 - Accumulating evaluation results...
2024-03-03 15:06:04 | INFO | yolox.evaluators.coco_evaluator:303 - DONE (t=0.03s).
2024-03-03 15:06:04 | INFO | yolox.core.trainer:354 -
Average forward time: 0.00 ms, Average NMS time: 0.00 ms, Average inference time: 0.00 ms
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.092
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.103
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.103
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.060
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.100
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.069
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.138
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.138
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.180
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.100
per class AP:

class	AP	class	AP	class	AP
0	nan	1	nan	2	nan
3	nan	4	nan	5	nan
6	nan	7	0.000	8	nan
9	nan	10	nan	11	nan
12	nan	13	nan	14	nan
15	nan	16	nan	17	nan
18	0.000	19	nan	20	nan
21	nan	22	nan	23	nan
24	nan	25	nan	26	0.000
27	nan	28	nan	29	nan
30	nan	31	nan	32	30.000
33	nan	34	0.000	35	nan
36	nan	37	0.000	38	nan
39	nan	40	nan	41	nan
42	nan	43	nan	44	0.000
45	nan	46	nan	47	nan
48	nan	49	90.000	50	nan
51	nan	52	nan	53	nan
54	nan	55	nan	56	0.000
57	0.000	58	nan	59	nan
60	nan	61	0.000	62	nan
63	nan	64	nan	65	nan
66	nan	67	nan	68	nan
69	0.000	70	0.000
per class AR:
class	AR	class	AR	class	AR
:--------	:------	:--------	:-------	:--------	:-------
0	nan	1	nan	2	nan
3	nan	4	nan	5	nan
6	nan	7	0.000	8	nan
9	nan	10	nan	11	nan
12	nan	13	nan	14	nan
15	nan	16	nan	17	nan
18	0.000	19	nan	20	nan
21	nan	22	nan	23	nan
24	nan	25	nan	26	0.000
27	nan	28	nan	29	nan
30	nan	31	nan	32	90.000
33	nan	34	0.000	35	nan
36	nan	37	0.000	38	nan
39	nan	40	nan	41	nan
42	nan	43	nan	44	0.000
45	nan	46	nan	47	nan
48	nan	49	90.000	50	nan
51	nan	52	nan	53	nan
54	nan	55	nan	56	0.000
57	0.000	58	nan	59	nan
60	nan	61	0.000	62	nan
63	nan	64	nan	65	nan
66	nan	67	nan	68	nan
69	0.000	70	0.000

class	AP	class	AP	class	AP
0	nan	1	nan	2	nan
3	nan	4	nan	5	nan
6	nan	7	0.000	8	nan
9	nan	10	nan	11	nan
12	nan	13	nan	14	nan
15	nan	16	nan	17	nan
18	0.000	19	nan	20	nan
21	nan	22	nan	23	nan
24	nan	25	nan	26	0.000
27	nan	28	nan	29	nan
30	nan	31	nan	32	0.000
33	nan	34	0.000	35	nan
36	nan	37	0.000	38	nan
39	nan	40	nan	41	nan
42	nan	43	nan	44	0.000
45	nan	46	nan	47	nan
48	nan	49	90.000	50	nan
51	nan	52	nan	53	nan
54	nan	55	nan	56	0.000
57	0.000	58	nan	59	nan
60	nan	61	60.000	62	nan
63	nan	64	nan	65	nan
66	nan	67	nan	68	nan
69	0.000	70	0.000
per class AR:
class	AR	class	AR	class	AR
:--------	:------	:--------	:-------	:--------	:------
0	nan	1	nan	2	nan
3	nan	4	nan	5	nan
6	nan	7	0.000	8	nan
9	nan	10	nan	11	nan
12	nan	13	nan	14	nan
15	nan	16	nan	17	nan
18	0.000	19	nan	20	nan
21	nan	22	nan	23	nan
24	nan	25	nan	26	0.000
27	nan	28	nan	29	nan
30	nan	31	nan	32	0.000
33	nan	34	0.000	35	nan
36	nan	37	0.000	38	nan
39	nan	40	nan	41	nan
42	nan	43	nan	44	0.000
45	nan	46	nan	47	nan
48	nan	49	90.000	50	nan
51	nan	52	nan	53	nan
54	nan	55	nan	56	0.000
57	0.000	58	nan	59	nan
60	nan	61	60.000	62	nan
63	nan	64	nan	65	nan
66	nan	67	nan	68	nan
69	0.000	70	0.000

class	AP	class	AP	class	AP
0	nan	1	nan	2	nan
3	nan	4	nan	5	nan
6	nan	7	0.000	8	nan
9	nan	10	nan	11	nan
12	nan	13	nan	14	nan
15	nan	16	nan	17	nan
18	0.000	19	nan	20	nan
21	nan	22	nan	23	nan
24	nan	25	nan	26	0.000
27	nan	28	nan	29	nan
30	nan	31	nan	32	0.000
33	nan	34	0.000	35	nan
36	nan	37	0.000	38	nan
39	nan	40	nan	41	nan
42	nan	43	nan	44	0.000
45	nan	46	nan	47	nan
48	nan	49	40.000	50	nan
51	nan	52	nan	53	nan
54	nan	55	nan	56	0.000
57	0.000	58	nan	59	nan
60	nan	61	0.000	62	nan
63	nan	64	nan	65	nan
66	nan	67	nan	68	nan
69	0.000	70	0.000
per class AR:
class	AR	class	AR	class	AR
:--------	:------	:--------	:-------	:--------	:------
0	nan	1	nan	2	nan
3	nan	4	nan	5	nan
6	nan	7	0.000	8	nan
9	nan	10	nan	11	nan
12	nan	13	nan	14	nan
15	nan	16	nan	17	nan
18	0.000	19	nan	20	nan
21	nan	22	nan	23	nan
24	nan	25	nan	26	0.000
27	nan	28	nan	29	nan
30	nan	31	nan	32	0.000
33	nan	34	0.000	35	nan
36	nan	37	0.000	38	nan
39	nan	40	nan	41	nan
42	nan	43	nan	44	0.000
45	nan	46	nan	47	nan
48	nan	49	80.000	50	nan
51	nan	52	nan	53	nan
54	nan	55	nan	56	0.000
57	0.000	58	nan	59	nan
60	nan	61	0.000	62	nan
63	nan	64	nan	65	nan
66	nan	67	nan	68	nan
69	0.000	70	0.000

class	AP	class	AP	class	AP
0	nan	1	nan	2	nan
3	nan	4	nan	5	nan
6	nan	7	0.000	8	nan
9	nan	10	nan	11	nan
12	nan	13	nan	14	nan
15	nan	16	nan	17	nan
18	0.000	19	nan	20	nan
21	nan	22	nan	23	nan
24	nan	25	nan	26	0.000
27	nan	28	nan	29	nan
30	nan	31	nan	32	0.000
33	nan	34	0.000	35	nan
36	nan	37	0.000	38	nan
39	nan	40	nan	41	nan
42	nan	43	nan	44	0.000
45	nan	46	nan	47	nan
48	nan	49	0.000	50	nan
51	nan	52	nan	53	nan
54	nan	55	nan	56	0.000
57	0.000	58	nan	59	nan
60	nan	61	0.000	62	nan
63	nan	64	nan	65	nan
66	nan	67	nan	68	nan
69	0.000	70	0.000
per class AR:
class	AR	class	AR	class	AR
:--------	:------	:--------	:------	:--------	:------
0	nan	1	nan	2	nan
3	nan	4	nan	5	nan
6	nan	7	0.000	8	nan
9	nan	10	nan	11	nan
12	nan	13	nan	14	nan
15	nan	16	nan	17	nan
18	0.000	19	nan	20	nan
21	nan	22	nan	23	nan
24	nan	25	nan	26	0.000
27	nan	28	nan	29	nan
30	nan	31	nan	32	0.000
33	nan	34	0.000	35	nan
36	nan	37	0.000	38	nan
39	nan	40	nan	41	nan
42	nan	43	nan	44	0.000
45	nan	46	nan	47	nan
48	nan	49	0.000	50	nan
51	nan	52	nan	53	nan
54	nan	55	nan	56	0.000
57	0.000	58	nan	59	nan
60	nan	61	0.000	62	nan
63	nan	64	nan	65	nan
66	nan	67	nan	68	nan
69	0.000	70	0.000

class	AP	class	AP	class	AP
0	nan	1	nan	2	nan
3	nan	4	nan	5	nan
6	nan	7	0.000	8	nan
9	nan	10	nan	11	nan
12	nan	13	nan	14	nan
15	nan	16	nan	17	nan
18	0.000	19	nan	20	nan
21	nan	22	nan	23	nan
24	nan	25	nan	26	0.000
27	nan	28	nan	29	nan
30	nan	31	nan	32	0.000
33	nan	34	0.000	35	nan
36	nan	37	0.000	38	nan
39	nan	40	nan	41	nan
42	nan	43	nan	44	0.000
45	nan	46	nan	47	nan
48	nan	49	0.000	50	nan
51	nan	52	nan	53	nan
54	nan	55	nan	56	0.000
57	0.000	58	nan	59	nan
60	nan	61	0.000	62	nan
63	nan	64	nan	65	nan
66	nan	67	nan	68	nan
69	0.000	70	0.000
per class AR:
class	AR	class	AR	class	AR
:--------	:------	:--------	:------	:--------	:------
0	nan	1	nan	2	nan
3	nan	4	nan	5	nan
6	nan	7	0.000	8	nan
9	nan	10	nan	11	nan
12	nan	13	nan	14	nan
15	nan	16	nan	17	nan
18	0.000	19	nan	20	nan
21	nan	22	nan	23	nan
24	nan	25	nan	26	0.000
27	nan	28	nan	29	nan
30	nan	31	nan	32	0.000
33	nan	34	0.000	35	nan
36	nan	37	0.000	38	nan
39	nan	40	nan	41	nan
42	nan	43	nan	44	0.000
45	nan	46	nan	47	nan
48	nan	49	0.000	50	nan
51	nan	52	nan	53	nan
54	nan	55	nan	56	0.000
57	0.000	58	nan	59	nan
60	nan	61	0.000	62	nan
63	nan	64	nan	65	nan
66	nan	67	nan	68	nan
69	0.000	70	0.000

mahaling · 2024-03-11T01:24:31Z

@Jessica-hub did you resolve this. I am also getting the same.

YCAyca · 2024-03-26T22:09:20Z

me tooo. I mean I get this error with custom dataset but still it would help to know why its like this with coco

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Training AP is always 0 using coco128 dataset #1760

Training AP is always 0 using coco128 dataset #1760

Jessica-hub commented Mar 3, 2024

mahaling commented Mar 11, 2024

YCAyca commented Mar 26, 2024 •

edited

Training AP is always 0 using coco128 dataset #1760

Training AP is always 0 using coco128 dataset #1760

Comments

Jessica-hub commented Mar 3, 2024

mahaling commented Mar 11, 2024

YCAyca commented Mar 26, 2024 • edited

YCAyca commented Mar 26, 2024 •

edited