ahhhxxx
ahhhxxx
运行train.py想自己像YOLOv5y一样训练模型训练报错 'Got {}, but numpy array, torch tensor, or caffe2 blob name are expected.'.format(type(x))) NotImplementedError: Got , but numpy array, torch tensor, or caffe2 blob name are expected.
大佬您好,我运行detect.py报错 x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous() RuntimeError: shape '[1, 3, 85, 80, 64]' is invalid for input of size 655360 运行train.py拿来训练也报错,是不是这不能拿来训练或者测试呢?
is:issue is:open detect,大佬您好为什么运行detect.py报错 return flops * img_size[0] / stride * img_size[1] / stride UnboundLocalError: local variable 'flops' referenced before assignment 
File "D:\Anaconda3\envs\y55\lib\site-packages\torch\serialization.py", line 851, in _load result = unpickler.load() ModuleNotFoundError: No module named 'small_model_mod'
AttributeError: 'list' object has no attribute 'seek'. You can only torch.load from a file that is seekable. Please pre-load the data into a buffer like io.BytesIO and try to load...