save_best_only=True,
period=5,
)
reduce_lr = ReduceLROnPlateau(
monitor="val_loss",
factor=0.1,
patience=3,
verbose=1)
early_stopping = EarlyStopping(
monitor="val_loss", min_delta=0, patience=10, verbose=1
)
val_split = FLAGS.val_split
with open(FLAGS.annotation_file) as f:
lines = f.readlines()
lines = ChangeToOtherMachine(lines)
np.random.seed(42)
np.random.shuffle(lines)
np.random.seed(None)
num_val = int(len(lines) * val_split)
num_train = len(lines) - num_val
# Train with frozen layers first, to get a stable loss.
# Adjust num epochs to your dataset. This step is enough to obtain a not
# bad model.
if True:
model.compile(
optimizer=Adam(lr=1e-3),
loss={
# use custom yolo_loss Lambda layer.
"yolo_loss": lambda y_true, y_pred: y_pred
reduce_lr = ReduceLROnPlateau(monitor='val_loss',
factor=0.1,
patience=3,
verbose=1)
early_stopping = EarlyStopping(monitor='val_loss',
min_delta=0,
patience=10,
verbose=1)
val_split = FLAGS.val_split
with open(FLAGS.annotation_file) as f:
lines = f.readlines()
# This step makes sure that the path names correspond to the local machine
# This is important if annotation and training are done on different machines (e.g. training on AWS)
lines = ChangeToOtherMachine(lines, remote_machine='')
np.random.shuffle(lines)
num_val = int(len(lines) * val_split)
num_train = len(lines) - num_val
# Train with frozen layers first, to get a stable loss.
# Adjust num epochs to your dataset. This step is enough to obtain a decent model.
if True:
model.compile(
optimizer=Adam(lr=1e-3),
loss={
# use custom yolo_loss Lambda layer.
'yolo_loss': lambda y_true, y_pred: y_pred
})
batch_size = 32
reduce_lr = ReduceLROnPlateau(monitor="val_loss",
factor=0.1,
patience=3,
verbose=1)
early_stopping = EarlyStopping(monitor="val_loss",
min_delta=0,
patience=10,
verbose=1)
val_split = FLAGS.val_split
with open(FLAGS.annotation_file) as f:
lines = f.readlines()
# This step makes sure that the path names correspond to the local machine
# This is important if annotation and training are done on different machines (e.g. training on AWS)
lines = ChangeToOtherMachine(lines, repo="gtav-vision", remote_machine="")
np.random.shuffle(lines)
num_val = int(len(lines) * val_split)
num_train = len(lines) - num_val
# Train with frozen layers first, to get a stable loss.
# Adjust num epochs to your dataset. This step is enough to obtain a decent model.
frozen_callbacks = [logging, checkpoint]
if _has_wandb:
wandb.init(project="TrainYourOwnYOLO",
config=vars(FLAGS),
sync_tensorboard=False)
wandb_callback = WandbCallback(save_model=False)
frozen_callbacks.append(wandb_callback)