复现项目的问题？

[YangBo0411]

你好，请问项目还更新吗？按照您的思路，在YOLOv9进行复现时，出现了ValueError: Expected more than 1 value per channel when training的错误，请问您有遇到过相似的问题吗？具体错误代码如下： Traceback (most recent call last): File "E:\paper3 multi task learning\yolov9-multiv5\multi_train_dual.py", line 716, in main(opt) File "E:\paper3 multi task learning\yolov9-multiv5\multi_train_dual.py", line 610, in main train(opt.hyp, opt, device, callbacks) File "E:\paper3 multi task learning\yolov9-multiv5\multi_train_dual.py", line 121, in train model = Model(cfg, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create File "E:\paper3 multi task learning\yolov9-multiv5\models\yolo.py", line 618, in init m.stride = torch.tensor([s / x.shape[-2] for x in forward(torch.zeros(1, ch, s, s))]) # forward File "E:\paper3 multi task learning\yolov9-multiv5\models\yolo.py", line 617, in forward = lambda x: self.forward(x)[0] File "E:\paper3 multi task learning\yolov9-multiv5\models\yolo.py", line 632, in forward return self._forward_once(x, profile, visualize) # single-scale inference, train File "E:\paper3 multi task learning\yolov9-multiv5\models\yolo.py", line 531, in _forward_once x = m(x) # run File "E:\software\anaconda\envs\multiyolo\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "E:\software\anaconda\envs\multiyolo\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl return forward_call(*args, **kwargs) File "E:\paper3 multi task learning\yolov9-multiv5\models\yolo.py", line 65, in forward return self.out(feat) File "E:\software\anaconda\envs\multiyolo\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "E:\software\anaconda\envs\multiyolo\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl return forward_call(*args, **kwargs) File "E:\software\anaconda\envs\multiyolo\lib\site-packages\torch\nn\modules\container.py", line 217, in forward input = module(input) File "E:\software\anaconda\envs\multiyolo\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "E:\software\anaconda\envs\multiyolo\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl return forward_call(*args, **kwargs) File "E:\paper3 multi task learning\yolov9-multiv5\models\common.py", line 1288, in forward feat1 = F.interpolate(self.conv1(self.pool1(x)), (h, w), mode='bilinear', align_corners=True) File "E:\software\anaconda\envs\multiyolo\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "E:\software\anaconda\envs\multiyolo\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl return forward_call(*args, **kwargs) File "E:\paper3 multi task learning\yolov9-multiv5\models\common.py", line 54, in forward return self.act(self.bn(self.conv(x))) File "E:\software\anaconda\envs\multiyolo\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "E:\software\anaconda\envs\multiyolo\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl return forward_call(*args, **kwargs) File "E:\software\anaconda\envs\multiyolo\lib\site-packages\torch\nn\modules\batchnorm.py", line 175, in forward return F.batch_norm( File "E:\software\anaconda\envs\multiyolo\lib\site-packages\torch\nn\functional.py", line 2480, in batch_norm _verify_batch_size(input.size()) File "E:\software\anaconda\envs\multiyolo\lib\site-packages\torch\nn\functional.py", line 2448, in _verify_batch_size raise ValueError(f"Expected more than 1 value per channel when training, got input size {size}") ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 64, 1, 1])