You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Traceback (most recent call last):
File "train.py", line 213, in
multi_scale=opt.multi_scale,
File "train.py", line 56, in train
cutoff = load_darknet_weights(model, weights + 'darknet53.conv.74')
File "/tmp/YOLOv3-Codecraft-2019-master/models.py", line 292, in load_darknet_weights
bn_b = torch.from_numpy(weights[ptr:ptr + num_b]).view_as(bn_layer.bias)
RuntimeError: shape '[32]' is invalid for input of size 28
尝试使用您的模型训练,遇到如下问题,请问是我的pytorch版本安错了吗,谢谢!
The text was updated successfully, but these errors were encountered:
Traceback (most recent call last):
File "train.py", line 213, in
multi_scale=opt.multi_scale,
File "train.py", line 56, in train
cutoff = load_darknet_weights(model, weights + 'darknet53.conv.74')
File "/tmp/YOLOv3-Codecraft-2019-master/models.py", line 292, in load_darknet_weights
bn_b = torch.from_numpy(weights[ptr:ptr + num_b]).view_as(bn_layer.bias)
RuntimeError: shape '[32]' is invalid for input of size 28
尝试使用您的模型训练,遇到如下问题,请问是我的pytorch版本安错了吗,谢谢!
The text was updated successfully, but these errors were encountered: