RuntimeError: shape '[128, 64, 3, 3]' is invalid for input of size 7067 训练v3报错

[xiaomujiang]

python train.py --cfg cfg/yolov3-hand.cfg --data data/oxfordhand.data --weights weights/yolov3.weights --epochs 100 --batch-size 32

Traceback (most recent call last):
File "train.py", line 542, in
train() # train normally
File "train.py", line 143, in train
cutoff = load_darknet_weights(model, weights)
File "/mnt/sdl/x/prune/yolov3-channel-and-layer-pruning/models.py", line 353, in load_darknet_weights
conv_w = torch.from_numpy(weights[ptr:ptr + num_w]).view_as(conv_layer.weight)
RuntimeError: shape '[128, 64, 3, 3]' is invalid for input of size 7067