def create_and_fit_model():
# Create the model.
input_shape = (CONFIG.IMAGE_TARGET_HEIGHT, CONFIG.IMAGE_TARGET_WIDTH, 1)
base_model = create_base_cnn(input_shape, dropout=True)
head_input_shape = (128, )
head_model1 = create_head(head_input_shape, dropout=True, name="height")
head_model2 = create_head(head_input_shape, dropout=True, name="weight")
model_input = layers.Input(shape=(CONFIG.IMAGE_TARGET_HEIGHT,
CONFIG.IMAGE_TARGET_WIDTH, 1))
features = base_model(model_input)
model_output1 = head_model1(features)
model_output2 = head_model2(features)
model = Model(inputs=model_input, outputs=[model_output1, model_output2])
best_model_path = str(DATA_DIR / f'outputs/{MODEL_CKPT_FILENAME}')
checkpoint_callback = tf.keras.callbacks.ModelCheckpoint(
filepath=best_model_path,
monitor="val_loss",
save_best_only=True,
verbose=1)
training_callbacks = [
AzureLogCallback(run),
create_tensorboard_callback(),
checkpoint_callback,
]
optimizer = get_optimizer(CONFIG.USE_ONE_CYCLE,
lr=CONFIG.LEARNING_RATE,
n_steps=len(paths_training) / CONFIG.BATCH_SIZE)
# Compile the model.
model.compile(optimizer=optimizer,
loss={
'height': 'mse',
'weight': 'mse'
},
loss_weights={
'height': CONFIG.HEIGHT_IMPORTANCE,
'weight': CONFIG.WEIGHT_IMPORTANCE
},
metrics={
'height': ["mae"],
'weight': ["mae"]
})
# Train the model.
model.fit(dataset_training.batch(CONFIG.BATCH_SIZE),
validation_data=dataset_validation.batch(CONFIG.BATCH_SIZE),
epochs=CONFIG.EPOCHS,
callbacks=training_callbacks,
verbose=2)
def create_and_fit_model():
# Create the model.
input_shape = (CONFIG.IMAGE_TARGET_HEIGHT, CONFIG.IMAGE_TARGET_WIDTH,
NUM_INPUT_CHANNELS)
model = create_cnn(input_shape, dropout=CONFIG.USE_DROPOUT)
model.summary()
best_model_path = str(DATA_DIR / f'outputs/{MODEL_CKPT_FILENAME}')
checkpoint_callback = tf.keras.callbacks.ModelCheckpoint(
filepath=best_model_path,
monitor="val_loss",
save_best_only=True,
verbose=1)
dataset_batches = dataset_training.batch(CONFIG.BATCH_SIZE)
training_callbacks = [
AzureLogCallback(run),
create_tensorboard_callback(),
checkpoint_callback,
]
if getattr(CONFIG, 'USE_WANDB', False):
setup_wandb()
wandb.init(project="ml-project", entity="cgm-team")
wandb.config.update(CONFIG)
training_callbacks.append(
WandbCallback(log_weights=True,
log_gradients=True,
training_data=dataset_batches))
optimizer = get_optimizer(CONFIG.USE_ONE_CYCLE,
lr=CONFIG.LEARNING_RATE,
n_steps=len(paths_training) / CONFIG.BATCH_SIZE)
# Compile the model.
model.compile(optimizer=optimizer, loss="mse", metrics=["mae"])
# Train the model.
model.fit(dataset_training.batch(CONFIG.BATCH_SIZE),
validation_data=dataset_validation.batch(CONFIG.BATCH_SIZE),
epochs=CONFIG.EPOCHS,
callbacks=training_callbacks,
verbose=2)
def create_and_fit_model():
# Create the base model
base_model = get_base_model(workspace, DATA_DIR)
base_model.summary()
assert base_model.output_shape == (None, 128)
# Create the head
head_input_shape = (128 * CONFIG.N_ARTIFACTS, )
head_model = create_head(head_input_shape, dropout=CONFIG.USE_DROPOUT)
# Implement artifact flow through the same model
model_input = layers.Input(shape=(CONFIG.IMAGE_TARGET_HEIGHT,
CONFIG.IMAGE_TARGET_WIDTH,
CONFIG.N_ARTIFACTS))
features_list = []
for i in range(CONFIG.N_ARTIFACTS):
features_part = model_input[:, :, :, i:i + 1]
features_part = base_model(features_part)
features_list.append(features_part)
concatenation = tf.keras.layers.concatenate(features_list, axis=-1)
assert concatenation.shape.as_list() == tf.TensorShape(
(None, 128 * CONFIG.N_ARTIFACTS)).as_list()
model_output = head_model(concatenation)
model = models.Model(model_input, model_output)
model.summary()
best_model_path = str(DATA_DIR / f'outputs/{MODEL_CKPT_FILENAME}')
checkpoint_callback = callbacks.ModelCheckpoint(filepath=best_model_path,
monitor="val_loss",
save_best_only=True,
verbose=1)
training_callbacks = [
AzureLogCallback(run),
create_tensorboard_callback(),
checkpoint_callback,
]
optimizer = get_optimizer(CONFIG.USE_ONE_CYCLE,
lr=CONFIG.LEARNING_RATE,
n_steps=len(paths_training) / CONFIG.BATCH_SIZE)
# Compile the model.
model.compile(optimizer=optimizer, loss="mse", metrics=["mae"])
# Train the model.
model.fit(dataset_training.batch(CONFIG.BATCH_SIZE),
validation_data=dataset_validation.batch(CONFIG.BATCH_SIZE),
epochs=CONFIG.EPOCHS,
callbacks=training_callbacks,
verbose=2)
if CONFIG.EPOCHS_TUNE:
# Un-freeze
for layer in base_model._layers:
layer.trainable = True
# Adjust learning rate
optimizer = tf.keras.optimizers.Nadam(
learning_rate=CONFIG.LEARNING_RATE_TUNE)
model.compile(optimizer=optimizer, loss="mse", metrics=["mae"])
logger.info('Start fine-tuning')
model.fit(dataset_training.batch(CONFIG.BATCH_SIZE),
validation_data=dataset_validation.batch(CONFIG.BATCH_SIZE),
epochs=CONFIG.EPOCHS_TUNE,
callbacks=training_callbacks,
verbose=2)