TextGAN-PyTorch

TextGAN-PyTorch copied to clipboard

Where generated text is stored?

2

I checked files are being produced by the name of samples_MLE in sample folder but they consist of numbers. I guess they are the tokens of the individual word, if...

ghost

Hello everyone, I have a short question about the onehot encoding. From my understanding, every character is onehot encoded and the resulting tensor is fed for training. My question is,...

FabienCharmet

Can transformer be a generator?

1

I notice that generator the porject use is only LSTMGenerator, i wonder if a basic transformer can be a generator? Hope your response, thanks!

fuweifu-vtoo

The loss in the code (batchPGLoss) for sentigan is as follows: ``` loss = -torch.sum(pred * (1 - reward)) ``` why two negative signs? if (1-reward) =Penalty, and we are...

anindyasdas

1.On category text generation, the k_label is set to 2 then the model generats two types of text. So there are two scores of each metric in the outputs.Could you...

CCCa1cai

Sentigan generates repetitive samples

5

Hi I run sentigan with my dataset. It has 48000 recoeds. After 150 epochs for MLE training and 1000 epochs for ADV training, sentigan generate repetitive samples. Why?

BJavid

Generate samples using pre-trained model.

4

Once I restore a model by directly changing `pretrained_gen_path` and `pretrained_dis_path` in `config.py`. How do I then only generate samples and not have the model train again ?

IbrahimSahibzada

I have trained the model on the oracle synthetic data but now I want to generate samples on the trained model, how can I do it?

anujwwt

My GPU model is 2080Ti . But it will raise an error:RuntimeError: CUDA out of memory. Tried to allocate 1.43 GiB (GPU 4; 10.76 GiB total capacity; 4.20 GiB already...

xuefeng199507

Sentigan generates repetitive samples

1

Hi I run sentigan with my dataset. It has 48000 recoeds. After 150 epochs for MLE training and 1000 epochs for ADV training, sentigan generate repetitive samples. Why?

BJavid