2martens/masterthesis
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Fixed coding style

Browse Source 
Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
Jim Martens
2019-03-25 14:32:08 +01:00
parent 9a08ea3bb9
commit 6835c284af
1 changed files with 25 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
src/twomartens/masterthesis/aae/train.py
View File

@ -468,8 +468,10 @@ def train(dataset: tf.data.Dataset,
'z_discriminator': model.ZDiscriminator(), 'z_discriminator': model.ZDiscriminator(),
'x_discriminator': model.XDiscriminator(), 'x_discriminator': model.XDiscriminator(),
# define optimizers # define optimizers
'decoder_optimizer': tf.train.AdamOptimizer(learning_rate=checkpointables['learning_rate_var'], beta1=0.5, beta2=0.999), 'decoder_optimizer': tf.train.AdamOptimizer(learning_rate=checkpointables['learning_rate_var'],
'enc_dec_optimizer': tf.train.AdamOptimizer(learning_rate=checkpointables['learning_rate_var'], beta1=0.5, beta2=0.999), beta1=0.5, beta2=0.999),
'enc_dec_optimizer': tf.train.AdamOptimizer(learning_rate=checkpointables['learning_rate_var'],
beta1=0.5, beta2=0.999),
'z_discriminator_optimizer': tf.train.AdamOptimizer(learning_rate=checkpointables['learning_rate_var'], 'z_discriminator_optimizer': tf.train.AdamOptimizer(learning_rate=checkpointables['learning_rate_var'],
beta1=0.5, beta2=0.999), beta1=0.5, beta2=0.999),
'x_discriminator_optimizer': tf.train.AdamOptimizer(learning_rate=checkpointables['learning_rate_var'], 'x_discriminator_optimizer': tf.train.AdamOptimizer(learning_rate=checkpointables['learning_rate_var'],
@ -606,7 +608,6 @@ def _train_one_epoch(epoch: int,
global_step_decoder: tf.Variable, global_step_decoder: tf.Variable,
global_step_enc_dec: tf.Variable, global_step_enc_dec: tf.Variable,
epoch_var: tf.Variable) -> Dict[str, float]: epoch_var: tf.Variable) -> Dict[str, float]:
with summary_ops_v2.always_record_summaries(): with summary_ops_v2.always_record_summaries():
epoch_var.assign(epoch) epoch_var.assign(epoch)
epoch_start_time = time.time() epoch_start_time = time.time()