Hui 7f0e442d8b 循环的最后一个元素和下一次循环的第一个元素时间不连续
steps = np.linspace(start, end, TIME_STEP, dtype=np.float32)
其中默认参数endpoint=True,也就是说这一次循环的最后一个元素和下一次循环的第一个元素是一致的,按照RNN传递的state的特点,应该保证输入是关于时间连续的,所以不应该有相邻的时间是一致的情况,这可能不是想要的,所以我认为这里是一个小bug。
2018-11-30 21:49:23 +08:00
2017-05-08 12:33:25 +10:00
2017-05-06 01:18:56 +10:00
a3c
2018-01-18 22:29:43 +11:00


pyTorch Tutorials

In these tutorials for pyTorch, we will build our first Neural Network and try to build some advanced Neural Network architectures developed recent years.

Thanks for liufuyang's notebook files which is a great contribution to this tutorial.

For Chinese speakers: All methods mentioned below have their video and text tutorial in Chinese. Visit 莫烦 Python for more. You can watch my Youtube channel as well.

Regression

Classification

CNN

RNN

Autoencoder

GAN (Generative Adversarial Nets)

Dropout

Batch Normalization

Donation

If this does help you, please consider donating to support me for better tutorials. Any contribution is greatly appreciated!

Languages
Jupyter Notebook 98%
Python 2%