Ha YongWook

Hello. In `dcgan.py` [generator_model()](https://github.com/jacobgil/keras-dcgan/blob/060363909ad375545f25296b39253e019c3c5a55/dcgan.py#L17), the model uses `tanh` for not only last layer but every layer. [Original paper](https://arxiv.org/pdf/1511.06434.pdf%C3%AF%C2%BC%E2%80%B0) said, it's recommended to use ReLU for every layer except the last...

Hello. Thank you for sharing your code. It's marvellous. When I build my own vocab file, I found tqdm does not show the progress bar. So I added some codes...

The handler only gets the correct value from cuda:0.

2

### 🐛 Describe the bug I am using 2 GPU. Torchserve inference returns correct values only for predictions run on cuda:0. ### Error logs ``` x = "text to embed"...

https://github.com/luopeixiang/im2latex/blob/cd80800b70621847315e09fc9b760b5281f1a9f7/model/position_embedding.py#L43 I found your code little bit strange. I think this code should have been changed like below. ``` sinusoid[:,::2] = torch.sin(scaled_time) sinusoid[:,1::2] = torch.cos(scaled_time) ``` Do I misunderstand your...

안녕하세요. 귀한 한글 문장 분리기 잘 이용하고 있습니다. ```python original_text = "연속지(連續紙) 상에 인쇄를 하는 프린터" new_text = kss.split_sentences(original_text) new_text > 연속지(連續紙) 상에 인쇄를 하는 프린터 new_text == original_text >...

change: reduce memory consumption

2

We don't need to load all the tokens into memory. We can write tokens of the appropriate length directly to the output file. This change is necessary when preparing large...

Hello. Slidev project is really cool and I am appropriate for this. I found that the container is not working properly because of crlf ending of `entrypoint.sh`. I could manage...

2nd element of recon_loss?

3

Hello, I'm a student studying deep learning. First of all, Your code is really helpful to learn about VAE. Thank you very much. I've got a question. I'm curious about...

I added model saver for both encoder and decoder. It saves architecture to json file, and weights to .weights extension.

I tried to use DataParallel wrapper for the `_model` but failed with massive memory warning. The warning is like below. ``` /pytorch/aten/src/ATen/native/cudnn/RNN.cpp:1266: UserWarning: RNN module weights are not part of...