MultiSEAM加到yolov7中报错

[gitdjz]

大佬，这是咋回事啊？ Traceback (most recent call last): File "D:\PycharmProjects\yolov7\models\yolo.py", line 892, in model = Model(opt.cfg).to(device) File "D:\PycharmProjects\yolov7\models\yolo.py", line 547, in init m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward File "D:\PycharmProjects\yolov7\models\yolo.py", line 602, in forward return self.forward_once(x, profile) # single-scale inference, train File "D:\PycharmProjects\yolov7\models\yolo.py", line 628, in forward_once x = m(x) # run File "D:\condaenv\pytorch\lib\site-packages\torch\nn\modules\module.py", line 1110, in _call_impl return forward_call(*input, **kwargs) File "D:\PycharmProjects\yolov7\models\common.py", line 3033, in forward y0 = self.DCovN0(x) File "D:\condaenv\pytorch\lib\site-packages\torch\nn\modules\module.py", line 1110, in _call_impl return forward_call(*input, **kwargs) File "D:\condaenv\pytorch\lib\site-packages\torch\nn\modules\container.py", line 141, in forward input = module(input) File "D:\condaenv\pytorch\lib\site-packages\torch\nn\modules\module.py", line 1110, in _call_impl return forward_call(*input, **kwargs) File "D:\condaenv\pytorch\lib\site-packages\torch\nn\modules\batchnorm.py", line 168, in forward return F.batch_norm( File "D:\condaenv\pytorch\lib\site-packages\torch\nn\functional.py", line 2419, in batch_norm _verify_batch_size(input.size()) File "D:\condaenv\pytorch\lib\site-packages\torch\nn\functional.py", line 2387, in _verify_batch_size raise ValueError("Expected more than 1 value per channel when training, got input size {}".format(size)) ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 256, 1, 1])

[liiicon]

请问你解决了嘛