print("Validation ground truth dataset dtype", valid_gd_dataset.dtype)
valid_in_dataset = readRawDataset(config["dataset_valid_mra_path"],
config["dataset_valid_size"],
config["image_size_x"],
config["image_size_y"],
config["image_size_z"], 'uint16')
print("Validation input image dataset shape", valid_in_dataset.shape)
print("Validation input image dataset dtype", valid_in_dataset.dtype)
# ----- PreProcessing -----
# Intensity normalisation
print("Apply intensity normalisation to input image dataset")
train_in_dataset = intensityNormalisation(train_in_dataset, 'float32')
valid_in_dataset = intensityNormalisation(valid_in_dataset, 'float32')
print("Training input image dataset dtype", train_in_dataset.dtype)
print("Validation input image dataset dtype", valid_in_dataset.dtype)
train_in_dataset = reshapeDataset(train_in_dataset)
train_gd_dataset = reshapeDataset(train_gd_dataset)
valid_in_dataset = reshapeDataset(valid_in_dataset)
valid_gd_dataset = reshapeDataset(valid_gd_dataset)
# ----- Model training -----
# Callbacks
tensorboardCB = TensorBoard(log_dir=config["logs_folder"],
histogram_freq=0,
write_graph=True,
print("Testing ground truth dataset dtype", test_gd_dataset.dtype)
test_in_dataset = readRawDataset(config["dataset_test_mra_path"],
config["dataset_test_size"],
config["image_size_x"],
config["image_size_y"],
config["image_size_z"], 'uint16')
print("Training input image dataset shape", test_in_dataset.shape)
print("Training input image dataset dtype", test_in_dataset.dtype)
# ----- PreProcessing -----
# Intensity normalisation
print("Apply intensity normalisation to input image dataset")
test_in_dataset = intensityNormalisation(test_in_dataset, 'float32')
print("Testing input image dataset dtype", test_in_dataset.dtype)
# ----- Evaluation and prediction -----
print("Generate prediction")
test_in_dataset = reshapeDataset(test_in_dataset)
test_gd_dataset = reshapeDataset(test_gd_dataset)
print(model.metrics_names)
print(model.evaluate(test_in_dataset, test_gd_dataset))
prediction = model.predict(test_in_dataset)
for count in range(prediction.shape[0]):