# Multi-gpu setup:
basemodel = model
if args.gpus > 1: model = multi_gpu_model(model, gpus=args.gpus)
# Optimizer
optimizer = Adam(lr=args.lr, amsgrad=True)
# Compile the model
print(
'\n\n\n', 'Compiling model..', runID, '\n\n\tGPU ' +
(str(args.gpus) + ' gpus' if args.gpus > 1 else args.gpuids) +
'\t\tBatch size [ ' + str(args.bs) + ' ] ' + ' \n\n')
model.compile(loss=depth_loss_function, optimizer=optimizer)
print('Ready for training!\n')
# Callbacks
if args.data == 'nyu':
callbacks = get_nyu_callbacks(model, basemodel, train_generator,
test_generator, runPath)
# Start training
model.fit_generator(train_generator,
callbacks=callbacks,
validation_data=test_generator,
epochs=args.epochs,
shuffle=True)
# Save the final trained model:
basemodel.save(runPath + '/model.h5')
# Compile the model
print(
'\n\n\n', 'Compiling model..', runID, '\n\n\tGPU ' +
(str(args.gpus) + ' gpus' if args.gpus > 1 else args.gpuids) +
'\t\tBatch size [ ' + str(args.bs) + ' ] ' + ' \n\n')
model.compile(loss=depth_loss_function, optimizer=optimizer)
print('Ready for training!\n')
# Callbacks
# 訓練中にモデル内部の状態と統計量を可視化する際に，コールバックを使う
# ここではTensorBoardを用いて訓練とテストの評価値を動的にグラフ化し，可視化する。
callbacks = []
if args.data == 'nyu':
callbacks = get_nyu_callbacks(model, basemodel, train_generator,
test_generator,
load_test_data() if args.full else None,
runPath)
if args.data == 'unreal':
callbacks = get_nyu_callbacks(model, basemodel, train_generator,
test_generator,
load_test_data() if args.full else None,
runPath)
if args.data == 'eyemodel':
callbacks = get_eyemodel_callbacks(model,
basemodel,
train_generator,
test_generator,
load_test_data() if args.full else None,
runPath,
minDepth=args.mindepth,
maxDepth=args.maxdepth,
rfanet_x = RFDN()
x = Input(shape=(120, 160, 3))
out = rfanet_x(x)
parallel_model = Model(inputs=x, outputs=out)
parallel_model.compile(loss=depth_loss_function,
optimizer=optimizer,
metrics=metrics)
parallel_model.summary()
print('Ready for training!\n')
# Callbacks
callbacks = get_nyu_callbacks(parallel_model,
train_generator,
val_generator,
runPath,
totaL_epochs=args.epochs,
warmup_epoch=5,
batch_size=args.bs,
lr=args.lr,
val_loss="val_loss_sirmse_baseline")
# Start training
parallel_model.fit(train_generator,
validation_data=val_generator,
callbacks=callbacks,
epochs=args.epochs,
shuffle=True,
batch_size=args.bs,
verbose=1)
optimizer = Adam(lr=args.lr, amsgrad=True)
# Compile the model
print(
'\n\n\n', 'Compiling model..', runID, '\n\n\tGPU ' +
(str(args.gpus) + ' gpus' if args.gpus > 1 else args.gpuids) +
'\t\tBatch size [ ' + str(args.bs) + ' ] ' + ' \n\n')
model.compile(loss=loss, optimizer=optimizer)
print('Ready for training!\n')
# Callbacks
callbacks = []
if args.data == 'nyu':
callbacks = get_nyu_callbacks(model, basemodel, train_generator,
test_generator,
load_test_data() if args.full else None,
runPath)
if args.data == 'unreal':
callbacks = get_nyu_callbacks(model, basemodel, train_generator,
test_generator,
load_test_data() if args.full else None,
runPath)
if args.data == 'megadepth':
callbacks = get_nyu_callbacks(
model,
basemodel,
train_generator,
test_generator,
load_test_data() if args.full else None,
runPath,
depth_norm=lambda x: (x - np.min(x)) / (1e-10 + np.max(x) - np.min(x)),
# Compile the model
print(
'\n\n\n', 'Compiling model..', runID, '\n\n\tGPU ' +
(str(args.gpus) + ' gpus' if args.gpus > 1 else args.gpuids) +
'\t\tBatch size [ ' + str(args.bs) + ' ] ' + ' \n\n')
model.compile(loss=depth_loss_function, optimizer=optimizer)
print('Ready for training!\n')
# Callbacks
callbacks = []
if args.data == 'nyu':
callbacks = get_nyu_callbacks(model,
basemodel,
train_generator,
test_generator,
load_test_data() if args.full else None,
runPath,
save_checkpoint_period=args.save_period)
if args.data == 'unreal':
callbacks = get_nyu_callbacks(model, basemodel, train_generator,
test_generator,
load_test_data() if args.full else None,
runPath)
if args.data == 'own':
callbacks = get_nyu_callbacks(model,
basemodel,
train_generator,
test_generator,
load_test_data() if args.full else None,
runPath,
