wandb_callback = WandbCallback(save_model=False)
frozen_callbacks.append(wandb_callback)
# use custom yolo_loss Lambda layer.
model.compile(
optimizer=Adam(lr=1e-3),
loss={
"yolo_loss": lambda y_true, y_pred: y_pred
},
)
print("Train on {} samples, val on {} samples, with batch size {}.".
format(num_train, num_val, BATCH_SIZE))
history = model.fit_generator(
data_generator_wrapper(lines[:num_train], BATCH_SIZE, INPUT_SHAPE,
anchors, num_classes),
steps_per_epoch=max(1, num_train // BATCH_SIZE),
validation_data=data_generator_wrapper(lines[num_train:],
BATCH_SIZE, INPUT_SHAPE,
anchors, num_classes),
validation_steps=max(1, num_val // BATCH_SIZE),
epochs=epoch1,
initial_epoch=0,
callbacks=frozen_callbacks,
)
model.save_weights(os.path.join(log_dir, "trained_weights_stage_1.h5"))
# Unfreeze and continue training, to fine-tune.
# Train longer if the result is unsatisfactory.
full_callbacks = [logging, checkpoint, reduce_lr, early_stopping]
optimizer=Adam(lr=1e-3),
loss={
# use custom yolo_loss Lambda layer.
"yolo_loss": lambda y_true, y_pred: y_pred
},
)
batch_size = 32
print(
"Train on {} samples, val on {} samples, with batch size {}.".format(
num_train, num_val, batch_size
)
)
history = model.fit_generator(
data_generator_wrapper(
lines[:num_train], batch_size, input_shape, anchors, num_classes
),
steps_per_epoch=max(1, num_train // batch_size),
validation_data=data_generator_wrapper(
lines[num_train:], batch_size, input_shape, anchors, num_classes
),
validation_steps=max(1, num_val // batch_size),
epochs=epoch1,
initial_epoch=0,
callbacks=[logging, checkpoint],
)
model.save(os.path.join(log_dir, "trained_weights_stage_1.h5"))
step1_train_loss = history.history["loss"]
file = open(os.path.join(log_dir_time, "step1_loss.npy"), "w")
# Adjust num epochs to your dataset. This step is enough to obtain a decent model.
if FLAGS.train_step1:
model.compile(
optimizer=Adam(lr=1e-4),
loss={
# use custom yolo_loss Lambda layer.
'yolo_loss': lambda y_true, y_pred: y_pred
})
batch_size = 32
print('Train on {} samples, val on {} samples, with batch size {}.'.
format(num_train, num_val, batch_size))
history = model.fit_generator(
data_generator_wrapper(lines[:num_train],
batch_size,
input_shape,
anchors,
num_classes,
random=FLAGS.is_augment),
steps_per_epoch=max(1, num_train // batch_size),
validation_data=data_generator_wrapper(lines[num_train:],
batch_size,
input_shape,
anchors,
num_classes,
random=False),
validation_steps=max(1, num_val // batch_size),
epochs=epoch1,
initial_epoch=0,
callbacks=[logging, checkpoint])
model.save_weights(os.path.join(log_dir, 'trained_weights_stage_1.h5'))
