fast_abs_rl

fast_abs_rl copied to clipboard

raise RuntimeError("Mismatch in shape: grad_output[" RuntimeError: Mismatch in shape: grad_output[0] has a shape of torch.Size([1]) and output[0] has a shape of torch.Size([]).

5

deer how to solve it？in the rl.py autograd.backward( [critic_loss] + losses, [torch.ones(1).to(critic_loss.device)]*(1+len(losses)), ) raise that problem

xxz-wow

Hello Chen, Thanks for providing this code. It seems really helpful for my current research. However, I am having issues with making this code work. I have setup the environment...

bnaman50

scatter_add

10

In scatter_add function "source" parameter is not working , "src" should be used instead of "source".

ghost

Error while start training abstractor

3

Hi @ChenRocks , can you please check this issue? I tried to train your model with my own dataset in Vietnamese. It's OK at step 1 (train_word2vec.py) and step 2...

ithieund

Hi developer, Based on your model, the abstractor should be able to generate summaries, then together with ground truth summaries, the reward is calculated and fed to extractor. So how...

qiana0223

I want to ask you a question. Can I run these codes in cuda-10.1 pytorch-1.4.0 python-3.8 ?

1

Clearloveyuan

I am trying to run it using windows anaconda environment. i have install perl.it is running. Getting these error. Can anyone please help me.

tohidarehman1988

leonardyeoxl

I have been banging my head against a wall to get this working with my own dataset. I have successfully trained the word2vec model and the extraction labels but run...

Alx-AI

In https://github.com/ChenRocks/fast_abs_rl/blob/master/make_extraction_labels.py#L47 you split articles and abstracts into sentences to compute the labels for extraction. However `t.split()` splits into words, and not sentences. Is this a bug? If not, how...

fran-babylon