Skip to content

Instantly share code, notes, and snippets.

@prabindh

prabindh/cudnngru-test.py

Created May 12, 2019 14:05
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save prabindh/9565a34e43358fd44b4992891c883f37 to your computer and use it in GitHub Desktop.
Save prabindh/9565a34e43358fd44b4992891c883f37 to your computer and use it in GitHub Desktop.
Download ZIP
CUDNNGRU
Raw
cudnngru-test.py
CuDNNGRU stateful implementation, TensorFlow backend
Layers: (300,80,150) -- (encoder, latent, decoder) -- (selu, tanh, tanh)
return_sequences=True for all layers
GaussianNoise + Dropout at (=after) input, AlphaDropout at encoder, Dropout at latent
BatchNormalization between encoder and latent, latent and decoder
Output: TimeDistributed(Dense(units=input_dim, activation='linear'))
batch_size=25, timesteps=400, input_dim=16 - 25 separate, 10-min sequences fed 400 timesteps (=1 sec) at a time (as 10*60=600 'windows' in parallel, non-shuffled)
reset_states() applied before testing on new x25 10-min sequences
model.fit, or train_on_batch for training
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment