DIA
/
enose_2025
2
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

tess

main
ifiguero 2025-03-16 20:32:03 -03:00
parent 15af3d3745
commit 48cecaa8cf
1 changed files with 3 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
TrainerClass.py
View File

@ -199,7 +199,6 @@ class eNoseTrainer:
model.compile(optimizer=keras.optimizers.Adam(learning_rate=config['lr']), loss='mse') model.compile(optimizer=keras.optimizers.Adam(learning_rate=config['lr']), loss='mse')
return model return model
def train_model_conv1D(config): def train_model_conv1D(config):
X_trainc1D = ray.get(X_train_ref) X_trainc1D = ray.get(X_train_ref)
Y_trainc1D = ray.get(Y_train_ref) Y_trainc1D = ray.get(Y_train_ref)
@ -217,7 +216,7 @@ class eNoseTrainer:
validation_data=(X_testc1D, Y_testc1D), validation_data=(X_testc1D, Y_testc1D),
epochs=config['epochs'], epochs=config['epochs'],
batch_size=config['batch_size'], batch_size=config['batch_size'],
verbose=0, verbose=1,
callbacks=[early_stopping] callbacks=[early_stopping]
) )
@ -226,7 +225,7 @@ class eNoseTrainer:
tune.report({'mse': mse}) tune.report({'mse': mse})
config_space = { config_space = {
'filters': tune.choice([32, 64, 128]), 'filters': tune.choice([16, 32, 64]),
'kernel_size': tune.choice([3, 5]), 'kernel_size': tune.choice([3, 5]),
'pool_size': tune.choice([2, 3]), 'pool_size': tune.choice([2, 3]),
'dense_units': tune.choice([32, 64, 128]), 'dense_units': tune.choice([32, 64, 128]),
@ -240,7 +239,7 @@ class eNoseTrainer:
# analysis = tune.run(train_model, config=config_space, num_samples=num_samples, scheduler=scheduler) # analysis = tune.run(train_model, config=config_space, num_samples=num_samples, scheduler=scheduler)
analysis = tune.run( tune.with_parameters(train_model_conv1D), config=config_space, num_samples=num_samples, scheduler=scheduler, max_concurrent_trials=3 ) analysis = tune.run( tune.with_parameters(train_model_conv1D), config=config_space, num_samples=num_samples, scheduler=scheduler, max_concurrent_trials=3 )
best_config = analysis.get_best_config(metric='mse', mode='min') best_config = analysis.get_best_config(metric='mse', mode='min')
best_model = build_model_conv1D(best_config, X_train_ref.shape[1:], Y_train_ref.shape[1]) best_model = build_model_conv1D(best_config, X_train_orig.shape[1:], Y_train_orig.shape[1])
ray.internal.free([X_train_ref, Y_train_ref, X_test_ref, Y_test_ref]) ray.internal.free([X_train_ref, Y_train_ref, X_test_ref, Y_test_ref])