run purne.py error

[broliao]

when I run prune.py with follow parameter,
Namespace(cfg='cfg/yolov3-spp.cfg', img_size=608, overall_ratio=0.5, perlayer_ratio=0.1, save='prune_0.5_0.1', weights='weights/best.pt')
Using CUDA device0 _CudaDeviceProperties(name='GeForce GTX 1060 6GB', total_memory=6078MB)

i get the error:

Traceback (most recent call last):
File "/home/broliao/桌面/yolov3-slimyolov3/prune.py", line 396, in
opt.perlayer_ratio,
File "/home/broliao/桌面/yolov3-slimyolov3/prune.py", line 344, in test
inf_out, train_out = pruned_model(imgs) # inference and training outputs
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 493, in call
result = self.forward(*input, **kwargs)
File "/home/broliao/桌面/yolov3-slimyolov3/models.py", line 226, in forward
x = torch.cat([layer_outputs[i] for i in layers], 1)
RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 1. Got 13 and 28 in dimension 2 at /pytorch/aten/src/THC/generic/THCTensorMath.cu:71

who can help me?thanks a lot.

[ASONG0506]

in "models.py"
comment this line
layer_outputs[layers[1]] = F.interpolate(layer_outputs[layers[1]], scale_factor=[0.5, 0.5])

[broliao]

@ASONG0506 thanks for your reply, I will try it.

[May-forever]

when I run prune.py with follow parameter,
Namespace(cfg='cfg/yolov3-spp.cfg', img_size=608, overall_ratio=0.5, perlayer_ratio=0.1, save='prune_0.5_0.1', weights='weights/best.pt')
Using CUDA device0 _CudaDeviceProperties(name='GeForce GTX 1060 6GB', total_memory=6078MB)

i get the error:

Traceback (most recent call last):
File "/home/broliao/桌面/yolov3-slimyolov3/prune.py", line 396, in
opt.perlayer_ratio,
File "/home/broliao/桌面/yolov3-slimyolov3/prune.py", line 344, in test
inf_out, train_out = pruned_model(imgs) # inference and training outputs
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 493, in call
result = self.forward(*input, **kwargs)
File "/home/broliao/桌面/yolov3-slimyolov3/models.py", line 226, in forward
x = torch.cat([layer_outputs[i] for i in layers], 1)
RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 1. Got 13 and 28 in dimension 2 at /pytorch/aten/src/THC/generic/THCTensorMath.cu:71

who can help me?thanks a lot.

师兄，你好，我在win10上配置了这个工程，用来修剪我自己的网络（不是YOLOv3），但是报了下面这个错，你能帮我看看问题出在哪吗?先谢谢师兄了

[zbyuan]

@broliao @ASONG0506
hai I have encountered the same mistake, have you solved it?