Git Product home page Git Product logo

dialogpt-mmi-decoder's People

Contributors

lholten avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

dialogpt-mmi-decoder's Issues

Running environment

Hi,
Thank you very much for this great work. Could you share your running environment(python version / pip list)? With Python3.7 and PyTorch 1.3.1 for Cuda 10.1 I got the runtime error

usr >> hello
Traceback (most recent call last):
  File "interact.py", line 116, in <module>
    my_response = generate_message(my_message_list)
  File "interact.py", line 98, in generate_message
    result = _get_response(total_input[:, -1:], past)
  File "interact.py", line 47, in _get_response
    output_token = torch.multinomial(F.softmax(output_token, dim=-1), num_samples=1)
RuntimeError: "multinomial_kernel_cuda" not implemented for 'Half'

I imagine this wouldn't happen if I use the same environment.
Thank you.

Hangs while running interact.py

When I run interact.py, the process just waits for a long time and then gets killed. It just gets stuck at line 16.
Any idea why this could be happening?

IndexError: Target -1 is out of bounds.

I get this error when running interact.py:

usr >> Hi, how's it going?

---------------------------------------------------------------------------

IndexError                                Traceback (most recent call last)

<ipython-input-54-e36819c98f47> in <module>()
      4         my_message = input('usr >> ')
      5         append_messages(my_message_list, [my_message])
----> 6         my_response = generate_message(my_message_list)
      7         print('bot >>', my_response)
      8         append_messages(my_message_list, [my_response])

<ipython-input-39-b33e0e46d913> in generate_message(message_list, focus_last_message)
    104     for i in range(num_samples):
    105         result = _get_response(total_input[:, -1:], past)
--> 106         score = _score_response(result[0].to(device_r), total_input_reversed.to(device_r))
    107         results.append(result + (score,))
    108 

<ipython-input-39-b33e0e46d913> in _score_response(output_token, correct_token)
     67     labels = torch.cat((mask, correct_token), dim=1)
     68 
---> 69     loss, _, _ = reverse_model(inputs, labels=labels)
     70 
     71     return -loss.float()

/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
    530             result = self._slow_forward(*input, **kwargs)
    531         else:
--> 532             result = self.forward(*input, **kwargs)
    533         for hook in self._forward_hooks.values():
    534             hook_result = hook(self, input, result)

/usr/local/lib/python3.6/dist-packages/transformers/modeling_gpt2.py in forward(self, input_ids, past, attention_mask, token_type_ids, position_ids, head_mask, inputs_embeds, labels)
    610             # Flatten the tokens
    611             loss_fct = CrossEntropyLoss()
--> 612             loss = loss_fct(shift_logits.view(-1, shift_logits.size(-1)), shift_labels.view(-1))
    613             outputs = (loss,) + outputs
    614 

/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
    530             result = self._slow_forward(*input, **kwargs)
    531         else:
--> 532             result = self.forward(*input, **kwargs)
    533         for hook in self._forward_hooks.values():
    534             hook_result = hook(self, input, result)

/usr/local/lib/python3.6/dist-packages/torch/nn/modules/loss.py in forward(self, input, target)
    914     def forward(self, input, target):
    915         return F.cross_entropy(input, target, weight=self.weight,
--> 916                                ignore_index=self.ignore_index, reduction=self.reduction)
    917 
    918 

/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py in cross_entropy(input, target, weight, size_average, ignore_index, reduce, reduction)
   2019     if size_average is not None or reduce is not None:
   2020         reduction = _Reduction.legacy_get_string(size_average, reduce)
-> 2021     return nll_loss(log_softmax(input, 1), target, weight, None, ignore_index, None, reduction)
   2022 
   2023 

/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py in nll_loss(input, target, weight, size_average, ignore_index, reduce, reduction)
   1836                          .format(input.size(0), target.size(0)))
   1837     if dim == 2:
-> 1838         ret = torch._C._nn.nll_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index)
   1839     elif dim == 4:
   1840         ret = torch._C._nn.nll_loss2d(input, target, weight, _Reduction.get_enum(reduction), ignore_index)

IndexError: Target -1 is out of bounds.
Python 3.6.9 (default, Nov  7 2019, 10:44:02) 
[GCC 8.3.0] on linux

Name: torch
Version: 1.4.0

Name: transformers
Version: 2.8.0

I'm running this on a Google Colab notebook.

Thanks!

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.