Skip to content

Fix prints in DSP-aware pruning #1396

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
JanFSchulte merged 1 commit into from
Nov 1, 2025
Merged

Fix prints in DSP-aware pruning #1396

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 1 addition & 1 deletion hls4ml/optimization/dsp_aware_pruning/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,7 +66,7 @@ def optimize_keras_model_for_hls4ml(
cutoff_bad_trials (int): After how many bad trials (performance below threshold),
should model pruning / weight sharing stop
directory (string): Directory to store temporary results
tuner (str): Tuning algorithm, choose between Bayesian, Hyperband and None
tuner (str): Tuning algorithm, choose between Bayesian, Hyperband and Manual
knapsack_solver (str): Algorithm to solve Knapsack problem when optimizing;
default usually works well; for very large networks, greedy algorithm might be more suitable
regularization_range (list): List of suitable hyperparameters for weight decay
Expand Down
10 changes: 5 additions & 5 deletions hls4ml/optimization/dsp_aware_pruning/keras/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,7 +76,7 @@ def optimize_model(
cutoff_bad_trials (int): After how many bad trials (performance below threshold),
should model pruning / weight sharing stop
directory (string): Directory to store temporary results
tuner (str): Tuning algorithm, choose between Bayesian, Hyperband and None
tuner (str): Tuning algorithm, choose between Bayesian, Hyperband and Manual
knapsack_solver (str): Algorithm to solve Knapsack problem when optimizing;
default usually works well; for very large networks, greedy algorithm might be more suitable
regularization_range (list): List of suitable hyperparameters for weight decay
Expand Down Expand Up @@ -232,10 +232,10 @@ def optimize_model(
if verbose:
val_res = optimizable_model.evaluate(validation_dataset, verbose=0, return_dict=False)
t = time.time() - start_time
avg_loss = round(epoch_loss_avg.result(), 3)
print(f'Epoch: {epoch + 1} - Time: {t}s - Average training loss: {avg_loss}')
print(f'Epoch: {epoch + 1} - learning_rate: {optimizable_model.optimizer.learning_rate.numpy()}')
print(f'Epoch: {epoch + 1} - Validation loss: {val_res[0]} - Performance on validation set: {val_res[1]}')
avg_loss = epoch_loss_avg.result()
tf.print(f'Epoch: {epoch + 1} - Time: {t}s - Average training loss: {avg_loss}')
tf.print(f'Epoch: {epoch + 1} - learning_rate: {optimizable_model.optimizer.learning_rate.numpy()}')
tf.print(f'Epoch: {epoch + 1} - Validation loss: {val_res[0]} - Performance on validation set: {val_res[1]}')

# Check if model works after pruning
pruned_performance = optimizable_model.evaluate(validation_dataset, verbose=0, return_dict=False)[-1]
Expand Down
Loading