'Do you want to use the model trained on cosine distances [c] or on raw SVM predictions [r]?',
'c', 'r'):
cosine = True
model = load_model(config.lstm_model_1)
else:
cosine = False
model = load_model(config.lstm_model_577)
time_steps = model.get_config()[0]['config']['batch_input_shape'][1]
held_out = config.get_seg_data('held_out')
X_held = np.load(held_out['y'])
y_held = np.load(held_out['y_true_lm'])
if cosine:
print("Computing the distances")
X_held = compute_distance(X_held, cosine_distances)
else:
y_held = np.append(0, y_held)
X = split_to_time_steps(X_held)
y_true = split_to_time_steps(y_held)
y_pred = model.predict(X)
plot_thresholds(y_true.flatten(),
y_pred.flatten(),
False,
average_type="binary")
print("Loading the data")
train = config.get_seg_data('train')
held_out = config.get_seg_data('held_out')
X_train_or = np.load(train['y'])
y_train_or = np.load(train['y_true_lm'])
X_held_out = np.load(held_out['y'])
y_held_out = np.load(held_out['y_true_lm'])
print("Computing the distances on test data")
X_held_out = compute_distance(X_held_out, cosine_distances)
# Split the 2D matrix to 3D matrix of dimensions [samples, time_steps, features]
X_held_out = split_to_time_steps(X_held_out)
# Split the 1D vector to 2D matrix of dimensions: [samples, time_steps]
y_held_out = split_to_time_steps(y_held_out)
y_held_out = np.reshape(y_held_out,
(y_held_out.shape[0], y_held_out.shape[1], 1))
# Append 0 value to the beginning of y so the values represent if there was a boundary between current sample and
# the previous one, not the current and next
y_train_or = np.append(0, y_train_or)
shuffling_epochs = 2
for i in range(shuffling_epochs):
print("Shuffling epoch " + str(i) + "/" + str(shuffling_epochs))
[X_train, y_train] = shuffle_the_data(X_train_or, y_train_or)
if first_option('Do you want to use the model trained on cosine distances [c] or on raw SVM predictions [r]?',
'c', 'r'):
cosine = True
model = load_model(config.lstm_model_1)
T = 0.41
else:
cosine = False
model = load_model(config.lstm_model_577)
T = 0.48
time_steps = model.get_config()[0]['config']['batch_input_shape'][1]
test = config.get_seg_data('test')
X_test = np.load(test['y'])
y_test = np.load(test['y_true_lm'])
if cosine:
print("Computing the distances")
X_test = compute_distance(X_test, cosine_distances)
else:
y_test = np.append(0, y_test)
X = split_to_time_steps(X_test)
y_true = split_to_time_steps(y_test)
y_pred = model.predict(X) > T
print_measurements(y_true, y_pred)
# LSTM part
if first_option(
'Do you want to use the model trained on cosine distances [c] or on raw SVM predictions [r]?',
'c', 'r'):
print("Computing the distances")
X = compute_distance(X, cosine_distances)
model = load_model(config.lstm_model_1)
T = 0.41
# y_true = y_true[1:]
assert len(X) == len(
y_true), "Dimensions do not match: y.shape = " + str(
y_true.shape) + " X.shape = " + str(X.shape)
else:
cosine = False
model = load_model(config.lstm_model_577)
T = 0.48
time_steps = model.get_config()[0]['config']['batch_input_shape'][1]
X = split_to_time_steps(X)
y_true = split_to_time_steps(y_true)
y_pred = model.predict(X) > T
P, R, F, S = prfs(y_true.flatten(), y_pred.flatten(), average='binary')
print('F1 = %.3f (P = %.3f, R = %.3f)' % (F, P, R))
# plot_thresholds_pk(y_true, y_pred)
print_measurements(y_true, y_pred, k=5) # TODO: optimize k