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

Added debug flag

Browse Source 
Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
Jim Martens
2019-04-17 12:55:51 +02:00
parent 80d4861a4b
commit d3e212ab32
3 changed files with 41 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
src/twomartens/masterthesis/aae/run.py
View File

@ -42,7 +42,8 @@ def run_simple(dataset: tf.data.Dataset,
channels: int = 1,
zsize: int = 32,
batch_size: int = 128,
verbose: bool = True) -> None:
verbose: bool = False,
debug: bool = False) -> None:
"""
Runs the trained auto-encoder for given data set.
@ -55,7 +56,8 @@ def run_simple(dataset: tf.data.Dataset,
channels: number of channels in input image (default: 1)
zsize: size of the intermediary z (default: 32)
batch_size: size of each batch (default: 128)
verbose: if True prints train progress info to console (default: True)
verbose: if True training progress is printed to console (default: False)
debug: if True summaries are collected (default: False)
"""
# checkpointed tensors and variables
@ -77,6 +79,7 @@ def run_simple(dataset: tf.data.Dataset,
outputs = _run_one_epoch_simple(dataset,
batch_size=batch_size,
global_step=global_step,
debug=debug,
**checkpointables)
if verbose:
@ -88,6 +91,7 @@ def run_simple(dataset: tf.data.Dataset,
def _run_one_epoch_simple(dataset: tf.data.Dataset,
batch_size: int,
debug: bool,
encoder: model.Encoder,
decoder: model.Decoder,
global_step: tf.Variable) -> Dict[str, float]:
@ -98,12 +102,12 @@ def _run_one_epoch_simple(dataset: tf.data.Dataset,
for x in dataset:
reconstruction_loss, x_decoded, z = _run_enc_dec_step_simple(encoder=encoder,
decoder=decoder,
inputs=x,
global_step=global_step)
decoder=decoder,
inputs=x,
global_step=global_step)
enc_dec_loss_avg(reconstruction_loss)
if int(global_step % train.LOG_FREQUENCY) == 0:
if int(global_step % train.LOG_FREQUENCY) == 0 and debug:
comparison = K.concatenate([x[:int(batch_size / 2)], x_decoded[:int(batch_size / 2),
z[:int(batch_size / 2)]]], axis=0)
grid = util.prepare_image(comparison.cpu(), nrow=int(batch_size / 2))
@ -126,7 +130,8 @@ def _run_one_epoch_simple(dataset: tf.data.Dataset,
def _run_enc_dec_step_simple(encoder: model.Encoder, decoder: model.Decoder,
inputs: tf.Tensor,
global_step: tf.Variable) -> Tuple[tf.Tensor, tf.Tensor, tf.Tensor]:
global_step: tf.Variable,
debug: bool) -> Tuple[tf.Tensor, tf.Tensor, tf.Tensor]:
"""
Runs the encoder and decoder jointly for one step (one batch).
@ -135,6 +140,7 @@ def _run_enc_dec_step_simple(encoder: model.Encoder, decoder: model.Decoder,
decoder: instance of decoder model
inputs: inputs from data set
global_step: the global step variable
debug: if True summaries are collected
Returns:
tuple of reconstruction loss, reconstructed input, latent space value
@ -144,7 +150,7 @@ def _run_enc_dec_step_simple(encoder: model.Encoder, decoder: model.Decoder,
reconstruction_loss = tf.losses.log_loss(inputs, x_decoded)
if int(global_step % train.LOG_FREQUENCY) == 0:
if int(global_step % train.LOG_FREQUENCY) == 0 and debug:
summary_ops_v2.scalar(name='reconstruction_loss', tensor=reconstruction_loss,
step=global_step)

36
src/twomartens/masterthesis/aae/train.py
View File

@ -52,7 +52,8 @@ def train_simple(dataset: tf.data.Dataset,
lr: float = 0.002,
train_epoch: int = 80,
batch_size: int = 128,
verbose: bool = True) -> None:
verbose: bool = False,
debug: bool = False) -> None:
"""
Trains auto-encoder for given data set.
@ -72,7 +73,8 @@ def train_simple(dataset: tf.data.Dataset,
lr: initial learning rate (default: 0.002)
train_epoch: number of epochs to train (default: 80)
batch_size: size of each batch (default: 128)
verbose: if True prints train progress info to console (default: True)
verbose: if True training progress is printed to console (default: False)
debug: if True summaries are collected (default: False)
"""
# checkpointed tensors and variables
@ -115,6 +117,7 @@ def train_simple(dataset: tf.data.Dataset,
_epoch = epoch + previous_epochs
outputs = _train_one_epoch_simple(_epoch, dataset,
verbose=verbose,
debug=debug,
batch_size=batch_size,
**checkpointables)
@ -138,6 +141,7 @@ def train_simple(dataset: tf.data.Dataset,
def _train_one_epoch_simple(epoch: int,
dataset: tf.data.Dataset,
verbose: bool,
debug: bool,
batch_size: int,
learning_rate_var: tf.Variable,
decoder: model.Decoder,
@ -166,10 +170,11 @@ def _train_one_epoch_simple(epoch: int,
optimizer=enc_dec_optimizer,
inputs=x,
global_step_enc_dec=global_step_enc_dec,
global_step=global_step)
global_step=global_step,
debug=debug)
enc_dec_loss_avg(reconstruction_loss)
if int(global_step % LOG_FREQUENCY) == 0 and verbose:
if int(global_step % LOG_FREQUENCY) == 0 and debug:
comparison = K.concatenate([x[:int(batch_size / 2)], x_decoded[:int(batch_size / 2)],
z[:int(batch_size/2)]], axis=0)
grid = util.prepare_image(comparison.cpu(), nrow=int(batch_size/2))
@ -194,17 +199,22 @@ def _train_enc_dec_step_simple(encoder: model.Encoder, decoder: model.Decoder,
optimizer: tf.train.Optimizer,
inputs: tf.Tensor,
global_step: tf.Variable,
global_step_enc_dec: tf.Variable) -> Tuple[tf.Tensor, tf.Tensor, tf.Tensor]:
global_step_enc_dec: tf.Variable,
debug: bool) -> Tuple[tf.Tensor, tf.Tensor, tf.Tensor]:
"""
Trains the encoder and decoder jointly for one step (one batch).
:param encoder: instance of encoder model
:param decoder: instance of decoder model
:param optimizer: instance of chosen optimizer
:param inputs: inputs from data set
:param global_step: the global step variable
:param global_step_enc_dec: global step variable for enc_dec
:return: tuple of reconstruction loss, reconstructed input, z value
Args:
encoder: instance of encoder model
decoder: instance of decoder model
optimizer: instance of chosen optimizer
inputs: inputs from data set
global_step: the global step variable
global_step_enc_dec: global step variable for enc_dec
debug: if True summaries are collected
Returns:
tuple of reconstruction loss, reconstructed input, z value
"""
with tf.GradientTape() as tape:
z = encoder(inputs)
@ -214,7 +224,7 @@ def _train_enc_dec_step_simple(encoder: model.Encoder, decoder: model.Decoder,
enc_dec_grads = tape.gradient(reconstruction_loss,
encoder.trainable_variables + decoder.trainable_variables)
if int(global_step % LOG_FREQUENCY) == 0:
if int(global_step % LOG_FREQUENCY) == 0 and debug:
summary_ops_v2.scalar(name='reconstruction_loss', tensor=reconstruction_loss,
step=global_step)
for grad, variable in zip(enc_dec_grads, encoder.trainable_variables + decoder.trainable_variables):

5
src/twomartens/masterthesis/main.py
View File

@ -32,6 +32,7 @@ def main() -> None:
)
parser.add_argument("--verbose", default=False, action="store_true", help="provide to get extra output")
parser.add_argument("--debug", default=False, action="store_true", help="provide to collect tensorboard summaries")
parser.add_argument('--version', action='version', version='2martens Masterthesis 0.1.0')
sub_parsers = parser.add_subparsers(dest="action")
sub_parsers.required = True
@ -128,7 +129,7 @@ def _use(args: argparse.Namespace) -> None:
f"{args.summary_path}/use/category-{category}/{args.iteration}"
)
with use_summary_writer.as_default():
run.run_simple(coco_data, iteration=args.iteration_trained,
run.run_simple(coco_data, iteration=args.iteration_trained, debug=args.debug,
weights_prefix=f"{args.weights_path}/category-{category_trained}",
zsize=64, verbose=args.verbose, channels=3, batch_size=batch_size)
@ -151,7 +152,7 @@ def _auto_encoder_train(args: argparse.Namespace) -> None:
with train_summary_writer.as_default():
train.train_simple(coco_data, iteration=args.iteration,
weights_prefix=f"{args.weights_path}/category-{category}",
zsize=64, lr=0.0001, verbose=args.verbose,
zsize=64, lr=0.0001, verbose=args.verbose, debug=args.debug,
channels=3, train_epoch=args.num_epochs, batch_size=batch_size)