Runtime Error about pytorch-pruning HOT 7 OPEN

@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.

from pytorch-pruning.

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

from pytorch-pruning.

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

from pytorch-pruning.

@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_conv_layer
_, conv = list(model._modules.items())[layer_index]
IndexError: list index out of range

Can you help me? Thanks!

from pytorch-pruning.

@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.

from pytorch-pruning.

@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!

from pytorch-pruning.

@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 ?

from pytorch-pruning.