This is the samplest project in deeplearning with tensorflow. Downloan MNIST_data by yourself and copy it in this program's file. VAE(Variational AutoEncoder):1 hidden layer, put it with the file of MNIST_data together. Using relu and increasing batch_size can reduce cost. 'layer' is a one hidden layer network, and increases accuracy from fistsoftmax's 92% to 98%.
-
Notifications
You must be signed in to change notification settings - Fork 0
u784799i/firstsoftmax
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
No description, website, or topics provided.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published