TASK_NAME = 'UNet_training_generator_{}epochs'.format(N_EPOCHS)
TASK_FOLDER_PATH = os.path.join(CHECKPOINT_FOLDER_PATH, TASK_NAME)
if not os.path.exists(TASK_FOLDER_PATH):
os.makedirs(TASK_FOLDER_PATH)
#TRAINING_WEIGHTS_FILEPATH = os.path.join(TASK_FOLDER_PATH,
# '{}_weights_training{}.hdf5'.format(model.name, TASK_NAME))
TRAINING_WEIGHTS_FILEPATH = os.path.join(CHECKPOINT_FOLDER_PATH,
'retrained_UNet_500+250epochs.hdf5')
fname_test = [os.path.join(TRAIN_VAL_TEST_DIR, "Xy_test.npz")]
model.load_weights(TRAINING_WEIGHTS_FILEPATH)
prediction_steps, n_evts_test = get_n_iterations(fname_test,
batch_size=BATCH_SIZE)
print("prediction steps per epoch:{}, n events:{}".format(
prediction_steps, n_evts_test))
print('INFERENCE STEP')
parallel_model = multi_gpu_model(model, gpus=2)
test_data_gen = data_generator(fname_test,
batch_size=BATCH_SIZE,
ftarget=lambda y: y)
def inference_step(network_model, test_data_generator, predict_steps):
y_pred = list()
TRAINING_WEIGHTS_FILEPATH = os.path.join(
TASK_FOLDER_PATH,
'{}_weights_training{}.hdf5'.format(model.name, TASK_NAME))
HISTORY_FILEPATH = os.path.join(
TASK_FOLDER_PATH, '{}_history{}.pkl'.format(model.name, TASK_NAME))
MODEL_JSON_FILEPATH = os.path.join(TASK_FOLDER_PATH,
'{}.json'.format(model.name))
fname_train = [
os.path.join(TRAIN_VAL_TEST_DIR, "Xy_train_stratified_dist.npz")
]
fname_val = [os.path.join(TRAIN_VAL_TEST_DIR, "Xy_val_stratified_dist.npz")]
steps_per_epoch, n_events = get_n_iterations(fname_train,
batch_size=BATCH_SIZE)
print("training steps per epoc:{}, number of events:{}".format(
steps_per_epoch, n_events))
validation_steps, n_evts_val = get_n_iterations(fname_val,
batch_size=BATCH_SIZE)
print("validation steps per epoch:{}, number of events:{}".format(
validation_steps, n_evts_val))
def ohe(values):
values_reshaped = values.reshape(-1, 1)
onehot_encoder = OneHotEncoder(sparse=False)
onehot_encoded = onehot_encoder.fit_transform(values_reshaped)
return onehot_encoded
