def build_model():
'''Reconstruct a trined model from saved data.
'''
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
with open("models/2020-03-06-16-21-20/topology.txt", "r") as topology:
num_filters = tuple(map(int, topology.readline()[1:-1].split(', ')))
input_shape = (None, None, 3)
model = Autoencoder(input_shape=input_shape, num_filters=num_filters)
model = model.build()
model.load_weights("models/2020-03-06-16-21-20/weights.h5")
model.compile(optimizer="adam", loss="MSE", metrics=["accuracy"])
return model
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu
with open(args.topology, "r") as topology:
num_filters = tuple(map(int, topology.readline()[1:-1].split(', ')))
files = glob.glob(os.path.join(args.file_dir, "*.png"))
input_shape = (None, None, 3)
# Reconstruct model from saved weights
model = Autoencoder(input_shape=input_shape, num_filters=num_filters)
model = model.build()
print(model.summary())
model.load_weights(args.weights)
model.compile(optimizer="adam", loss="MSE", metrics=["accuracy"])
# Generate time stamp for unique id of the result
time_stamp = "{date:%Y-%m-%d-%H-%M-%S}".format(date=datetime.datetime.now())
# Pass images to network
for file, i in zip(files, range(len(files))):
inp_img = cv2.imread(file) / 255
inp_img = np.expand_dims(inp_img, axis=0)
out_img = model.predict(inp_img)
inp_img = np.squeeze(inp_img, axis=0)
out_img = np.squeeze(out_img, axis=0)
train_ds = dataloader.load_and_patch(files[0], "fit", args.patch_shape, args.n_patches, args.batch_size,
args.prefetch, args.num_parallel_calls, shuffle=None, repeat=True)
valid_ds = dataloader.load_and_patch(files[1], "fit", args.patch_shape, args.n_patches, args.batch_size,
args.prefetch, args.num_parallel_calls, shuffle=None, repeat=True)
test_ds, test_gt = dataloader.load_and_patch(test_files, "inf", num_parallel_calls=args.num_parallel_calls, batch_size=8)
input_shape = (None, None, 3)
model = Autoencoder(input_shape=input_shape, num_filters=num_filters)
model = model.build()
print(model.summary())
if args.train_continue:
model.load_weights(args.weights_path)
# Train the model
model.compile(optimizer=optimizer, loss="MSE", metrics=['accuracy'])
history = model.fit(train_ds,
steps_per_epoch=500,
epochs=args.n_epochs,
validation_data=valid_ds,
validation_steps=250,
callbacks=callbacks(model_path, test_ds, test_gt),
verbose=1)