lijierui

A mismatch between the implementation and the paper

3

In the implementation of the decoder, here in linguistic-style-transfer-pytorch/linguistic_style_transfer_pytorch/model.py, in this function "def generate_sentences(self, input_sentences, latent_emb, inference=False):" starting from Line 428, it seems that you are concatenating the content &...

Several possible bugs

1

I've been using this codebase to handle some new datasets, it did help me a lot, but I found a few places where there might be bugs or unclear descriptions....

Will numbers not in the question be treated as constants automatically?

2

Hi, I checked the documentation and didn't find any notes for constants. So will numbers not in the problem text, but in the equations, be automatically treated as constants and...

I'm training on my custom training set with 9k+ data points using the following hyperparameters on 3 GPUs: --per_device_train_batch_size 3 \ --gradient_accumulation_steps 1 \ --max_steps 1600 \ Which should be...