Po-Chih Huang

Sorry, since I am graduated from school, I don't have the access to the workstation. If you are working with deep learning, it's really important and convenient to have your...

Nope.

For instance, if a sample in training set is ('How is the weather?', 'It's sunny.'). To train a reversed model, you need to reverse the data into ('It's sunny.', 'How...

Sorry, I don't get the point about the meaning of 'environment'. If your intent is to ask for the RL algorithm, I used policy gradient in this repo.

Can you describe more detail of your question? Thanks.

I suggest you to go for the [official tutorial](https://www.tensorflow.org/install/gpu). This is a very important part for deep learning.

This is the pre-trained model. You need to download it.

The deep learning technique itself is unstable. Maybe you'll get better result after training again.

1. If the checkpoint exists, saver can restore the trained parameters 2. build_model will construct the graph for training, build_generator will construct the graph for inferring. The most of the...

我是用 papaer reward 的第一和第三項，不會爆掉