NING LAM

In neural combinatorial optimization jupyter notebook ``` TypeError Traceback (most recent call last) in () ----> 1 tsp_20_train.train_and_validate(5) in train_and_validate(self, n_epochs) 30 inputs = inputs.cuda() 31 ---> 32 R, probs,...

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...

sorry,I have the same problem, I added it: next_new_conv = torch.nn.Conv2d(in_channels = next_conv.in_channels - 1, out_channels = next_conv.out_channels, kernel_size = next_conv.kernel_size, stride = next_conv.stride, padding = next_conv.padding, dilation = next_conv.dilation,...

thank you! @liuzhuang13 Why you used subgradient? did you try directly defining loss ?

I can get this, the pruned model size is 9.3M which is not 2.2M? @angelamin @kaishijeng is it same as your model? 

Can your method balance the GPU memory usage ? I find this problem. 

How to get the compressed_SqueezeNet.net？

 How to solve this problem ？ thank you.

Additionally, there is a puzzling issue in [this tutorial](https://github.com/privacytrustlab/ml_privacy_meter/blob/master/tutorials/white_box_attack.ipynb). For the CIFAR-10 dataset, although the training accuracy is relatively high, at over 80%, the testing accuracy is quite poor, at...

 hi，I run the python script，why the final accuracy is 0.0974？