提交 d9596b26 编写于 作者: W wangyang59

minor change on gan tutorial

上级 79856704
...@@ -12,7 +12,7 @@ The generator and discriminator take turn to be trained using SGD. The objective ...@@ -12,7 +12,7 @@ The generator and discriminator take turn to be trained using SGD. The objective
## Implementation of GAN Model Structure ## Implementation of GAN Model Structure
Since GAN model involves multiple neural networks, it requires to use paddle python API. So the code walk-through below can also partially serve as an introduction to the usage of Paddle Python API. Since GAN model involves multiple neural networks, it requires to use paddle python API. So the code walk-through below can also partially serve as an introduction to the usage of Paddle Python API.
There are three networks defined in gan_conf.py, namely generator_training, discriminator_training and generator. The relationship to the model structure we defined above is that discriminator_training is the discriminator, generator is the generator, and the generator_training combined the generator and discriminator since training generator would require the discriminator to provide loss function. This relationship is described in the following code There are three networks defined in gan_conf.py, namely **generator_training**, **discriminator_training** and **generator**. The relationship to the model structure we defined above is that **discriminator_training** is the discriminator, **generator** is the generator, and the **generator_training** combined the generator and discriminator since training generator would require the discriminator to provide loss function. This relationship is described in the following code
```python ```python
if is_generator_training: if is_generator_training:
noise = data_layer(name="noise", size=noise_dim) noise = data_layer(name="noise", size=noise_dim)
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册