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()
for _ in tqdm(range(predict_steps)):
X_batch, _ = next(test_data_generator)
Y_batch_pred = network_model.predict_on_batch(X_batch)
y_pred.append(Y_batch_pred.ravel())
y_pred = np.vstack(np.asarray(y_pred))
return y_pred
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))
# prediction_steps, n_evts_test = get_n_iterations(fname_test, batch_size=BATCH_SIZE)
# print(prediction_steps, n_evts_test)
training_generator = data_generator(fname_train,
batch_size=BATCH_SIZE,
ftarget=lambda y: y)
validation_generator = data_generator(fname_val,
batch_size=BATCH_SIZE,
ftarget=lambda y: y)
# data_dir = DATA_DIR_IH
training_history = train_neural_network(model,
training_generator,
steps_per_epoch,
validation_generator,
validation_steps,
batch_size=BATCH_SIZE,
epochs=N_EPOCHS)
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
training_generator = data_generator(fname_train,
data_key='x',
label_key='dist',
batch_size=BATCH_SIZE,
fdata=lambda y: y,
ftarget=ohe)
validation_generator = data_generator(fname_val,
data_key='x',
label_key='dist',
batch_size=BATCH_SIZE,
fdata=lambda y: y,
ftarget=ohe)
training_history = train_neural_network(model,
training_generator,
steps_per_epoch,
validation_generator,
validation_steps,
steps_per_epoch, n_events = get_n_iterations(fname_train,
batch_size=BATCH_SIZE)
print(steps_per_epoch, n_events)
# validation_steps, n_evts_val = get_n_iterations(fnames_val[:N_FILES], batch_size=BATCH_SIZE)
# print(validation_steps, n_evts_val)
prediction_steps, n_evts_test = get_n_iterations(fname_test,
batch_size=BATCH_SIZE)
print(prediction_steps, n_evts_test)
validation_steps, n_evts_val = get_n_iterations(fname_test,
batch_size=BATCH_SIZE)
print(validation_steps, n_evts_val)
training_generator = data_generator(fname_train,
batch_size=BATCH_SIZE,
ftarget=lambda y: y)
validation_generator = data_generator(fname_val,
batch_size=BATCH_SIZE,
fdata=get_Time_Coord,
ftarget=process_cosz)
# data_dir = DATA_DIR_IH
model = get_unet()
model.summary()
training_history = train_neural_network(model,
training_generator,
steps_per_epoch,
validation_generator,