Skip to content

Vnet benchmark fix #369

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
nvpstr merged 2 commits into from
Jan 15, 2020
Merged

Vnet benchmark fix #369

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6ca9637
Improve the way profiling is performed
pribalta Jan 10, 2020
8a86378
Cosmetics
pribalta Jan 10, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion TensorFlow/Segmentation/VNet/Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,6 @@ ADD . /workspace/vnet
WORKDIR /workspace/vnet

RUN pip install --upgrade pip
RUN pip install --user git+https://github.com/NVIDIA/dllogger
RUN pip install --disable-pip-version-check -r requirements.txt


4 changes: 2 additions & 2 deletions TensorFlow/Segmentation/VNet/hooks/profiling_hook.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,6 @@ def before_run(self, run_context):

def end(self, session):
deltas = [self._timestamps[i + 1] - self._timestamps[i] for i in range(len(self._timestamps) - 1)]
self._logger.log(step=self._step, data={
'average_throughput_' + 'train' if self._training else 'test': self._global_batch_size / np.mean(deltas)})
self._logger.log(step=(), data={
'average_throughput_train' if self._training else 'average_throughput_test': self._global_batch_size / np.mean(deltas)})
self._logger.flush()
2 changes: 1 addition & 1 deletion TensorFlow/Segmentation/VNet/hooks/train_hook.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@ def after_run(self,
run_context,
run_values):
if self._step % self._log_every == 0:
self._logger.log(step=self._step, data={'total_loss': run_values.results[0]})
self._logger.log(step=(self._step,), data={'total_loss': str(run_values.results[0])})
self._step += 1

def end(self, session):
Expand Down
18 changes: 14 additions & 4 deletions TensorFlow/Segmentation/VNet/main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,7 +87,7 @@ def main(_):

run_config = tf.estimator.RunConfig(
save_summary_steps=None,
save_checkpoints_steps=dataset.train_steps * FLAGS.train_epochs,
save_checkpoints_steps=None if FLAGS.benchmark else dataset.train_steps * FLAGS.train_epoch,
save_checkpoints_secs=None,
tf_random_seed=None,
session_config=config,
Expand All @@ -112,22 +112,32 @@ def main(_):
if hvd.rank() == 0:
train_hooks += [TrainHook(FLAGS.log_every, DLLogger)]

DLLogger.log(step=tuple(), data={"training": "START"})

estimator.train(
input_fn=lambda: dataset.train_fn(FLAGS.augment),
steps=steps,
hooks=train_hooks)

DLLogger.log(step=tuple(), data={"training": "FINISHED"})

if 'evaluate' in FLAGS.exec_mode:
if hvd.rank() == 0:
if FLAGS.train_split >= 1.0:
raise ValueError("Missing argument: --train_split < 1.0")

DLLogger.log(step=tuple(), data={"evaluating": "START"})

result = estimator.evaluate(
input_fn=dataset.eval_fn,
steps=dataset.eval_steps,
hooks=[])
DLLogger.log(step=tuple(), data={'background_dice': result['background dice']})
DLLogger.log(step=tuple(), data={'anterior_dice': result['Anterior dice']})
DLLogger.log(step=tuple(), data={'posterior_dice': result['Posterior dice']})

DLLogger.log(step=tuple(), data={"evaluating": "FINISH"})

DLLogger.log(step=tuple(), data={'background_dice': str(result['background dice'])})
DLLogger.log(step=tuple(), data={'anterior_dice': str(result['Anterior dice'])})
DLLogger.log(step=tuple(), data={'posterior_dice': str(result['Posterior dice'])})

if 'predict' in FLAGS.exec_mode:
count = 1
Expand Down
1 change: 1 addition & 0 deletions TensorFlow/Segmentation/VNet/requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,3 +2,4 @@ SimpleITK==1.1.0
requests
googledrivedownloader
tf2onnx
git+git://github.com/NVIDIA/dllogger#egg=dllogger