NING LAM

RuntimeError: backward_input can only be called in training mode

2

In pointer network jupyter notebook, ``` /pytorch_test/env2/lib/python2.7/site-packages/ipykernel_launcher.py:46: UserWarning: invalid index of a 0-dim tensor. This will be an error in PyTorch 0.5. Use tensor.item() to convert a 0-dim tensor to...

qusetion about cifar.py

1


experiment result

17

Hello peterliht， I ran through your code according to the instructions, did not modify any parameters, but found that the results vary greatly. What parameters did you modify before releasing...

How to use muti-gpus ？

1

what's the command to use muti-gpus?

AttributeError: 'CIFAR10' object has no attribute 'train_labels'

5

``` Files already downloaded and verified Traceback (most recent call last): File "/Federated-Learning-PyTorch/src/sampling.py", line 282, in d = cifar_noniid(dataset_train, num) File "/Federated-Learning-PyTorch/src/sampling.py", line 248, in cifar_noniid labels = np.array(dataset.train_labels) AttributeError:...

Why not using the GPUs to train ?

1

Hello, you did a wonderful job, and why not using GPUs to train ? Does the training procedure of GPU is slower than that of CPU?

local subgradient = S*torch.sign(weight)

3

L1 sparsity should be torch.abs(weight), can you detail more about it? ` local subgradient = S*torch.sign(weight) `

m.weight.grad.data.add_(args.s*torch.sign(m.weight.data)) # L1

2

main.py文件当中，L1正则化应该是torch.abs而不是torch.sign吧 `m.weight.grad.data.add_(args.s*torch.sign(m.weight.data)) # L1 `