#Phase 1 -with batch BatchNormalizationN
# Instantiate the model
model = PConvUnet(vgg_weights='vgg16_pytorch2keras.h5')
#coco_phase1weights.45-0.42
#phase_1_rect_coco_weights.45-0.38.h5
#coco_phase1weights.45-0.38
model.load("coco_phase1coco_2017_phase_1_weights.43-1.08.h5",
train_bn=False,
lr=0.00005)
FOLDER = './phase_2_coco_2017_data_log/logs/coco_phase2'
# Run training for certain amount of epochs
model.fit_generator(
train_generator,
steps_per_epoch=10000,
validation_data=val_generator,
validation_steps=1000,
epochs=50,
verbose=1,
callbacks=[
TensorBoard(log_dir=FOLDER, write_graph=False),
ModelCheckpoint(FOLDER + '_weights.{epoch:02d}-{loss:.2f}.h5',
monitor='val_loss',
save_best_only=True,
save_weights_only=True),
LambdaCallback(on_epoch_end=lambda epoch, logs: plot_callback(model)),
TQDMCallback()
])
model.fit_generator(
generator,
steps_per_epoch=2000,
epochs=10,
callbacks=[
TensorBoard(
log_dir='./coco_2017_data/logs/single_image_test',
write_graph=False
),
ModelCheckpoint(
'./coco_2017_data/logs/single_image_test/coco_2017_weights.{epoch:02d}-{loss:.2f}.h5',
monitor='loss',
save_best_only=True,
save_weights_only=True
),
LambdaCallback(
on_epoch_end=lambda epoch, logs: plot_sample_data(
masked_img,
model.predict(
[
np.expand_dims(masked_img,0),
np.expand_dims(mask,0)
]
)[0]
,
img,
middle_title='Prediction'
)
)
],
)
plt.savefig(r'/misc/home/u2592/image/img_{i}_{pred_time}.png'.format(
i=i, pred_time=pred_time))
plt.close()
"""## Phase 1 - with batch normalization"""
model = PConvUnet(
vgg_weights='/misc/home/u2592/data/pytorch_to_keras_vgg16.h5')
model.load('/misc/home/u2592/data/phase2/weights.20-0.07.h5',
train_bn=False,
lr=0.00005)
FOLDER = r'/misc/home/u2592/data/phase2'
# Run training for certain amount of epochs
model.fit_generator(
train_generator,
steps_per_epoch=3522,
validation_data=val_generator,
validation_steps=499,
epochs=20,
verbose=0,
callbacks=[
TensorBoard(log_dir=FOLDER, write_graph=False),
ModelCheckpoint(
'/misc/home/u2592/data/phase2/weights.{epoch:02d}-{loss:.2f}.h5',
monitor='val_loss',
save_best_only=True,
save_weights_only=True),
TQDMCallback()
])