init_epoch = 0
# In[6]:
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"] = str(0)
# TensorFlow wizardry
config = tf.ConfigProto()
# Don't pre-allocate memory; allocate as-needed
config.gpu_options.allow_growth = True
# Only allow a total of half the GPU memory to be allocated
config.gpu_options.per_process_gpu_memory_fraction = 1.0
# Create a session with the above options specified.
k.tensorflow_backend.set_session(tf.Session(config=config))
xnet = HourglassNet(num_classes=16, num_stacks=num_stacks, num_channels=256, inres=(256, 256),outres=(64, 64))
if resume:
xnet.resume_train(batch_size=batch_size,
model_path=model_path,
init_epoch=init_epoch, epochs=args.epochs)
else:
xnet.build_model(show=True)
xnet.train(epochs=epochs, model_path=model_path, batch_size=batch_size)
# -k.set_session(tf.Session(config=config))
tf.compat.v1.keras.backend.set_session(tf.compat.v1.Session(config=config))"""
if args.tiny:
xnet = HourglassNet(num_classes=16,
num_stacks=args.num_stack,
num_channels=128,
inres=(192, 192),
outres=(48, 48))
else:
xnet = HourglassNet(num_classes=16,
num_stacks=args.num_stack,
num_channels=256,
inres=(256, 256),
outres=(64, 64))
if args.resume:
xnet.resume_train(batch_size=args.batch_size,
model_json=args.resume_model_json,
model_weights=args.resume_model,
init_epoch=args.init_epoch,
epochs=epochs)
else:
xnet.build_model(mobile=args.mobile, show=True)
# NameError: name 'epochs' is not defined
# -xnet.train(epochs=epochs, model_path=model_path, batch_size=batch_size)
xnet.train(epochs=args.epochs,
model_path=args.model_path,
batch_size=args.batch_size)
image_aug_str=args.augment,
pickle_name=args.pickle,
optimizer_str=args.optimizer,
learning_rate=args.learning_rate,
activation_str=args.activation)
training_start = time.time()
# TODO Save all model parameters in JSON for easy resuming and parsing later on
if args.resume:
print("\n\nResume training start: {}\n".format(time.ctime()))
hgnet.resume_train(args.batch, args.model_save, args.resume_json, args.resume_weights, \
args.resume_epoch, args.epochs, args.resume_subdir, args.subset, new_run=args.resume_with_new_run)
else:
hgnet.build_model(show=True)
print("\n\nTraining start: {}\n".format(time.ctime()))
print("Hourglass blocks: {:2d}, epochs: {:3d}, batch size: {:2d}, subset: {:.2f}".format(\
args.hourglass, args.epochs, args.batch, args.subset))
hgnet.train(args.batch, args.model_save, args.epochs, args.subset,
args.notes)
print("\n\nTraining end: {}\n".format(time.ctime()))
training_end = time.time()
setup_time = training_start - setup_start
training_time = training_end - training_start
# Only allow a total of half the GPU memory to be allocated
config.gpu_options.per_process_gpu_memory_fraction = 1.0
# Create a session with the above options specified.
tf.compat.v1.keras.backend.set_session(tf.compat.v1.Session(config=config))
if args.tiny:
xnet = HourglassNet(num_classes=16,
num_stacks=args.num_stack,
num_channels=128,
inres=(192, 192),
outres=(48, 48))
else:
xnet = HourglassNet(num_classes=11,
num_stacks=args.num_stack,
num_channels=16,
inres=(256, 256),
outres=(64, 64))
if args.resume:
xnet.resume_train(batch_size=args.batch_size,
model_json=args.resume_model_json,
model_weights=args.resume_model,
init_epoch=args.init_epoch,
epochs=args.epochs)
else:
xnet.build_model(mobile=args.mobile, show=False)
xnet.train(epochs=args.epochs,
model_path=args.model_path,
batch_size=args.batch_size)
