TuSimple Test: The model and loaded state dict do not match exactly.

[bsangee08]

I tried to use the pretrained model 'tusimple_large' to test and I'm running into this error.

Command used to test

python tools/condlanenet/tusimple/test_tusimple.py configs/condlanenet/tusimple/tusimple_large_test.py '/content/gdrive/MyDrive/LaneDetection/tusimple_large.pth' --show --show_dst '/content/showPath' --result_dst '/content/result'

Error:

The model and loaded state dict do not match exactly

size mismatch for bbox_head.mlp.layers.0.weight: copying a param with shape torch.Size([64, 200, 1]) from checkpoint, the shape in current model is torch.Size([64, 100, 1]). [ ] 0/2782, elapsed: 0s, ETA:Traceback (most recent call last): File "tools/condlanenet/tusimple/test_tusimple.py", line 236, in main() File "tools/condlanenet/tusimple/test_tusimple.py", line 232, in main crop_bbox=cfg.crop_bbox) File "tools/condlanenet/tusimple/test_tusimple.py", line 141, in single_gpu_test return_loss=False, rescale=False, thr=hm_thr, data) File "/usr/local/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, *kwargs) File "/usr/local/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py", line 159, in forward return self.module(inputs[0], kwargs[0]) File "/usr/local/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(input, kwargs) File "/content/gdrive/My Drive/LaneDetection/conditional-lane-detection/mmdet/models/detectors/condlanenet.py", line 329, in forward return self.forward_test(img, img_metas, kwargs) File "/content/gdrive/My Drive/LaneDetection/conditional-lane-detection/mmdet/models/detectors/condlanenet.py", line 369, in forward_test kwargs['thr']) File "/content/gdrive/My Drive/LaneDetection/conditional-lane-detection/mmdet/models/dense_heads/condlanenet_head.py", line 444, in forward_test masks = self.mask_head(mask_branch, mask_params, num_ins) File "/usr/local/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(input, **kwargs) File "/content/gdrive/My Drive/LaneDetection/conditional-lane-detection/mmdet/models/dense_heads/condlanenet_head.py", line 119, in forward x = torch.cat([locations, x], dim=1) RuntimeError: Sizes of tensors must match except in dimension 2. Got 80 and 40 (The offending index is 0)

Please help me figure out what is wrong.

Thanks in advance.

[bsangee08]

Dataset path:

TuSimple Dataset installation as mentioned in dataset.md was confusing as the directory structure I got was different from what is mentioned in the installation when I ran the code. So I made dataset root to point to my tusimple-test.

Am I facing the issue due to this?

[Gooddz1]

求指导

[Gooddz1]

解决了吗

[h-somehow]

I meet the same question.

After debugging, I found that locations.shape is (1, 1 40, 100) and x.shape is (1, 64, 80, 200) and locations.shape is decided by /conditional-lane-detection/configs/condlanenet/tusimple/ tusimple_large_train.py :72 location_configs=dict(size=(batch_size, 1, 40, 100), device='cuda:0'))

so, I changed it to location_configs=dict(size=(batch_size, 1, 80, 200), device='cuda:0')) to match the size. And the result seems to be correct.

[{"name":"Accuracy","value":0.9654015183,"order":"desc"},{"name":"FP","value":0.0200934579,"order":"asc"},{"name":"FN","value":0.0350167745,"order":"asc"},{"name":"F1","value":0.9723876298,"order":"asc"}]

By the way , neither the smalll size nor medium size model causes the error. If anyone have a clue about x.shape's change please tell me:smile:

[Gooddz1]

I meet the same question.

After debugging, I found that locations.shape is (1, 1 40, 100) and x.shape is (1, 64, 80, 200) and locations.shape is decided by /conditional-lane-detection/configs/condlanenet/tusimple/ tusimple_large_train.py :72 location_configs=dict(size=(batch_size, 1, 40, 100), device='cuda:0'))

so, I changed it to location_configs=dict(size=(batch_size, 1, 80, 200), device='cuda:0')) to match the size. And the result seems to be correct.

[{"name":"Accuracy","value":0.9654015183,"order":"desc"},{"name":"FP","value":0.0200934579,"order":"asc"},{"name":"FN","value":0.0350167745,"order":"asc"},{"name":"F1","value":0.9723876298,"order":"asc"}]

By the way , neither the smalll size nor medium size model causes the error. If anyone have a clue about x.shape's change please tell me😄 非常感谢，还有个问题 怎么输出它的性能指标 [{"name":"Accuracy","value":0.9654015183,"order":"desc"},{"name":"FP","value":0.0200934579,"order":"asc"},{"name":"FN","value":0.0350167745,"order":"asc"},{"name":"F1","value":0.9723876298,"order":"asc"}]