Runtime Error

[jagadeesh09]

Hi

I have encountered this error while running the code. After getting the information about the filters which are to be pruned, while pruning the filters this issue occured.

/usr/local/lib/python2.7/dist-packages/torchvision/transforms/transforms.py:156: UserWarning: The use of the transforms.Scale transform is deprecated, please use transforms.Resize instead.
  "please use transforms.Resize instead.")
/usr/local/lib/python2.7/dist-packages/torchvision/transforms/transforms.py:397: UserWarning: The use of the transforms.RandomSizedCrop transform is deprecated, please use transforms.RandomResizedCrop instead.
  "please use transforms.RandomResizedCrop instead.")
Accuracy : 0.9248
Number of prunning iterations to reduce 67% filters 5
Ranking filters.. 
Layers that will be prunned {0: 5, 2: 4, 5: 7, 7: 6, 10: 25, 12: 24, 14: 19, 17: 42, 19: 50, 21: 66, 24: 72, 26: 74, 28: 118}
Prunning filters.. 
Traceback (most recent call last):
  File "finetune.py", line 270, in <module>
    fine_tuner.prune()
  File "finetune.py", line 228, in prune
    model = prune_vgg16_conv_layer(model, layer_index, filter_index)
  File "/disk2/jagadeesh/pytorch-pruning/prune.py", line 33, in prune_vgg16_conv_layer
    bias = conv.bias)
  File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/conv.py", line 278, in __init__
    False, _pair(0), groups, bias)
  File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/conv.py", line 34, in __init__
    if bias:
  File "/usr/local/lib/python2.7/dist-packages/torch/autograd/variable.py", line 125, in __bool__
    torch.typename(self.data) + " is ambiguous")
RuntimeError: bool value of Variable objects containing non-empty torch.FloatTensor is ambiguous```

Thanks

[guangzhili]

@jagadeesh09 The type of parameter "bias" in torch.nn.Conv2d should be bool(Check API at http://pytorch.org/docs/master/nn.html), but conv.bias is FloatTensor, change to bias = True if conv.bias is not None, otherwise False.

[MrLinNing]

Hi , I meet the problem, can your help me solved it

Accuracy : 0.9852
Number of prunning iterations to reduce 67% filters 5 
Ranking filters.
Layers that will be prunned {0: 4, 2: 10, 5: 6, 7: 7, 10: 24, 12: 19, 14: 18, 17: 59, 19: 62, 21: 58, 24: 71, 26: 87
Prunning filters..
Traceback (most recent call last):
    File "finetune.py", line 270, in <module>
    fine_tuner.prune()
    File "finetune.py", line 228, in prune
        model = prune_vgg16_conv_layer(model, layer_index, filter_index)
   File "/home/linning/pytorch_test/pytorch-pruning/prune.py", line 14, in prune_vgg16_conv_layer
        _, conv = model._modules.items()[layer_index]
TypeError: 'odict_items' object does not support indexing

[XUHUAKing]

@MrLinNing _modules will return OrderedDict() object which does not support indexing, try this instead: _, conv = list(model._modules.items())[layer_index]

[RgZhangLihao]

@XUHUAKing I met this problem, but I don't know how to solve it: Accuracy: 0.98 Number of prunning iterations to reduce 67% filters 5 Ranking filters.. Layers that will be prunned {28: 59, 24: 139, 26: 135, 21: 54, 17: 55, 19: 52, 14: 11, 12: 5, 10: 2} Prunning filters.. Traceback (most recent call last): File "finetune.py", line 269, in fine_tuner.prune() File "finetune.py", line 227, in prune model = prune_vgg16_conv_layer(model, layer_index, filter_index) File "/home/share2/zhanglihao/pytorch-pruning/prune.py", line 14, in prune_vgg16_convlayer , conv = list(model._modules.items())[layer_index] IndexError: list index out of range

Can you help me? Thanks!

[XUHUAKing]

@RgZhangLihao I am not sure of your error because I didn't meet this when I ran my own modified program.

However, in my program, I added constraint if module.weight.data.size(0) <= 1: #skip pruning this layer when cutting filters, to ensure during the pruning, I would not delete an entire layer, which may affect the layer index within your model in the future and cause your error.

This is just my guess, hope this help.

[fbiying87]

@XUHUAKing I have the same issue with the list index out of the range. Can you share the prune.py script with me, as I don't know where to put the if condition exactly. Thanks!

[Pyramiding]

@jagadeesh09 The type of parameter "bias" in torch.nn.Conv2d should be bool(Check API at http://pytorch.org/docs/master/nn.html), but conv.bias is FloatTensor, change to bias = True if conv.bias is not None, otherwise False.

If I want to use trained bias parameters, how to do ?