srviest / char-cnn-text-classification-pytorch Goto Github PK

I am trying the code, but precision is not improving. Model keeps on selecting only one of the classes:

Thanks

This line should call getClassWeight()
It currently calls the deprecated name for the function get_class_weight()

I have been able to run the model as is but it simply not converging!
For how many epochs I should run the model?

Hi! I am using Pytorch 1.0.0 with Python 2.7 and I get the error below when running python train.py command:

Implicit dimension choice for log_softmax has been deprecated. Change the call to include dim=X as an argument.
x = self.log_softmax(x)
train.py:120: UserWarning: torch.nn.utils.clip_grad_norm is now deprecated in favor of torch.nn.utils.clip_grad_norm_.
torch.nn.utils.clip_grad_norm(model.parameters(), args.max_norm)
Traceback (most recent call last):
File "train.py", line 282, in
main()
File "train.py", line 279, in main
train(train_loader, dev_loader, model, args)
File "train.py", line 137, in train
loss.data[0],
IndexError: invalid index of a 0-dim tensor. Use tensor.item() to convert a 0-dim tensor to a Python number

How to fix this? Thanks!

I changed a data set, and the rest is consistent with your code, but the result above appears. I don't know the reason, please kindly answer for me in your busy schedule, thank you

When I was training, I met a problem.
File "train.py", line 278, in <module> main() File "train.py", line 275, in main train(train_loader, dev_loader, model, args) File "train.py", line 97, in train model = torch.nn.DataParallel(model).cuda() File "/usr/local/lib/python3.5/dist-packages/torch/nn/parallel/data_parallel.py", line 47, in __init__ output_device = device_ids[0] IndexError: list index out of range
please help me!