def fit(self, X, valid_X=None):
# Input size:
# n_samples
# n_timesteps
# n_features
if self.input_checking:
X = rnn_check_array(X)
self.n_features = X[0].shape[-1]
# Regression features
self.input_size_ = self.n_features
self.output_size_ = self.n_features
X_sym = T.tensor3('x')
y_sym = T.tensor3('y')
X_mask_sym = T.matrix('x_mask')
y_mask_sym = T.matrix('y_mask')
self.layers_ = []
self.layer_sizes_ = [self.input_size_]
self.layer_sizes_.extend(self.hidden_layer_sizes)
self.layer_sizes_.append(self.output_size_)
self.training_loss_ = []
if valid_X is not None:
self.validation_loss_ = []
if self.input_checking:
valid_X = rnn_check_array(valid_X)
best_valid_loss = np.inf
best_train_loss = np.inf
try:
for itr in range(self.max_iter):
print("Starting pass %d through the dataset" % itr)
total_train_loss = 0
for i, j in minibatch_indices(X, self.minibatch_size):
X_n, y_n, X_mask, y_mask = make_regression(X[i:j])
if not hasattr(self, 'fit_function'):
# This is here to make debugging easier
X_sym.tag.test_value = X_n
y_sym.tag.test_value = y_n
X_mask_sym.tag.test_value = X_mask
y_mask_sym.tag.test_value = y_mask
print("Building model!")
print("Minibatch X size %s" % str(X_n.shape))
print("Minibatch y size %s" % str(y_n.shape))
self._setup_functions(X_sym, y_sym, X_mask_sym,
y_mask_sym, self.layer_sizes_)
train_loss = self.fit_function(X_n, y_n, X_mask, y_mask)
total_train_loss += train_loss
current_train_loss = total_train_loss / len(X)
print("Training loss %f" % current_train_loss)
self.training_loss_.append(current_train_loss)
if valid_X is not None:
total_valid_loss = 0
for i, j in minibatch_indices(valid_X, self.minibatch_size):
valid_X_n, valid_y_n, _, _ = make_regression(
valid_X[i:j], self.window_size,
self.prediction_size)
valid_loss = self.loss_function(valid_X_n, valid_y_n)
total_valid_loss += valid_loss
current_valid_loss = total_valid_loss / len(valid_X)
print("Validation loss %f" % current_valid_loss)
self.validation_loss_.append(current_valid_loss)
if (itr % self.save_frequency) == 0:
f = open(self.model_save_name + "_snapshot.pkl", 'wb')
cPickle.dump(self, f, protocol=2)
f.close()
if current_train_loss < best_train_loss:
best_train_loss = current_train_loss
f = open(self.model_save_name + "_train_best.pkl", 'wb')
cPickle.dump(self, f, protocol=2)
f.close()
if itr == (self.max_iter - 1):
f = open(self.model_save_name + "_last.pkl", 'wb')
cPickle.dump(self, f, protocol=2)
f.close()
# Shortcircuit if statement
if valid_X is not None and current_valid_loss < best_valid_loss:
best_valid_loss = current_valid_loss
f = open(self.model_save_name + "_valid_best.pkl", 'wb')
cPickle.dump(self, f, protocol=2)
f.close()
except KeyboardInterrupt:
print("User cancelled, saving last model!")
f = open(self.model_save_name + "_interrupt.pkl", 'wb')
cPickle.dump(self, f, protocol=2)
f.close()
def fit(self, X, valid_X=None):
# Input size:
# n_samples
# n_timesteps
# n_features
if self.input_checking:
X = rnn_check_array(X)
self.n_features = X[0].shape[-1]
# Regression features
self.input_size_ = self.n_features
self.output_size_ = self.n_features
X_sym = T.tensor3('x')
y_sym = T.tensor3('y')
X_mask_sym = T.matrix('x_mask')
y_mask_sym = T.matrix('y_mask')
self.layers_ = []
self.layer_sizes_ = [self.input_size_]
self.layer_sizes_.extend(self.hidden_layer_sizes)
self.layer_sizes_.append(self.output_size_)
self.training_loss_ = []
if valid_X is not None:
self.validation_loss_ = []
if self.input_checking:
valid_X = rnn_check_array(valid_X)
best_valid_loss = np.inf
best_train_loss = np.inf
try:
for itr in range(self.max_iter):
print("Starting pass %d through the dataset" % itr)
total_train_loss = 0
for i, j in minibatch_indices(X, self.minibatch_size):
X_n, y_n, X_mask, y_mask = make_regression(X[i:j])
if not hasattr(self, 'fit_function'):
# This is here to make debugging easier
X_sym.tag.test_value = X_n
y_sym.tag.test_value = y_n
X_mask_sym.tag.test_value = X_mask
y_mask_sym.tag.test_value = y_mask
print("Building model!")
print("Minibatch X size %s" % str(X_n.shape))
print("Minibatch y size %s" % str(y_n.shape))
self._setup_functions(X_sym, y_sym, X_mask_sym,
y_mask_sym, self.layer_sizes_)
train_loss = self.fit_function(X_n, y_n, X_mask, y_mask)
total_train_loss += train_loss
current_train_loss = total_train_loss / len(X)
print("Training loss %f" % current_train_loss)
self.training_loss_.append(current_train_loss)
if valid_X is not None:
total_valid_loss = 0
for i, j in minibatch_indices(valid_X,
self.minibatch_size):
valid_X_n, valid_y_n, _, _ = make_regression(
valid_X[i:j], self.window_size,
self.prediction_size)
valid_loss = self.loss_function(valid_X_n, valid_y_n)
total_valid_loss += valid_loss
current_valid_loss = total_valid_loss / len(valid_X)
print("Validation loss %f" % current_valid_loss)
self.validation_loss_.append(current_valid_loss)
if (itr % self.save_frequency) == 0:
f = open(self.model_save_name + "_snapshot.pkl", 'wb')
cPickle.dump(self, f, protocol=2)
f.close()
if current_train_loss < best_train_loss:
best_train_loss = current_train_loss
f = open(self.model_save_name + "_train_best.pkl",
'wb')
cPickle.dump(self, f, protocol=2)
f.close()
if itr == (self.max_iter - 1):
f = open(self.model_save_name + "_last.pkl", 'wb')
cPickle.dump(self, f, protocol=2)
f.close()
# Shortcircuit if statement
if valid_X is not None and current_valid_loss < best_valid_loss:
best_valid_loss = current_valid_loss
f = open(self.model_save_name + "_valid_best.pkl", 'wb')
cPickle.dump(self, f, protocol=2)
f.close()
except KeyboardInterrupt:
print("User cancelled, saving last model!")
f = open(self.model_save_name + "_interrupt.pkl", 'wb')
cPickle.dump(self, f, protocol=2)
f.close()
def fit(self, X, y, valid_X=None, valid_y=None):
if self.input_checking:
X, y = rnn_check_array(X, y)
input_size = X[0].shape[1]
# Assume that class values are sequential! and start from 0
highest_class = np.max([np.max(d) for d in y])
lowest_class = np.min([np.min(d) for d in y])
if lowest_class != 0:
raise ValueError("Labels must start from 0!")
# Create a list of all classes, then get uniques
# sum(lists, []) is list concatenation
all_classes = np.unique(sum([list(np.unique(d)) for d in y], []))
# +1 to include endpoint
output_size = len(np.arange(lowest_class, highest_class + 1))
X_sym = T.tensor3('x')
y_sym = T.tensor3('y')
X_mask = T.matrix('x_mask')
y_mask = T.matrix('y_mask')
self.layers_ = []
self.layer_sizes_ = [input_size]
self.layer_sizes_.extend(self.hidden_layer_sizes)
self.layer_sizes_.append(output_size)
if not hasattr(self, 'fit_function'):
print("Building model!")
self._setup_functions(X_sym, y_sym, X_mask, y_mask,
self.layer_sizes_)
self.training_loss_ = []
if valid_X is not None:
self.validation_loss_ = []
if self.input_checking:
valid_X, valid_y = rnn_check_array(valid_X, valid_y)
for vy in valid_y:
if not np.in1d(np.unique(vy), all_classes).all():
raise ValueError(
"Validation set contains classes not in training"
"set! Training set classes: %s\n, Validation set \
classes: %s" % (all_classes, np.unique(vy)))
best_valid_loss = np.inf
best_train_loss = np.inf
try:
for itr in range(self.max_iter):
print("Starting pass %d through the dataset" % itr)
total_train_loss = 0
for i, j in minibatch_indices(X, self.minibatch_size):
X_n, y_n, X_mask, y_mask = make_minibatch(X[i:j], y[i:j],
output_size)
train_loss = self.fit_function(X_n, y_n, X_mask, y_mask)
total_train_loss += train_loss
current_train_loss = total_train_loss / len(X)
print("Training loss %f" % current_train_loss)
self.training_loss_.append(current_train_loss)
if valid_X is not None:
total_valid_loss = 0
for i, j in minibatch_indices(valid_X, self.minibatch_size):
valid_X_n, valid_y_n, X_mask, y_mask = make_minibatch(
valid_X[i:j], valid_y[i:j], output_size)
valid_loss = self.loss_function(valid_X_n, valid_y_n,
X_mask, y_mask)
total_valid_loss += valid_loss
current_valid_loss = total_valid_loss / len(valid_X)
print("Validation loss %f" % current_valid_loss)
self.validation_loss_.append(current_valid_loss)
if (itr % self.save_frequency) == 0:
f = open(self.model_save_name + "_snapshot.pkl", 'wb')
cPickle.dump(self, f, protocol=2)
f.close()
if current_train_loss < best_train_loss:
best_train_loss = current_train_loss
f = open(self.model_save_name + "_train_best.pkl", 'wb')
cPickle.dump(self, f, protocol=2)
f.close()
if itr == (self.max_iter - 1):
f = open(self.model_save_name + "_last.pkl", 'wb')
cPickle.dump(self, f, protocol=2)
f.close()
# Shortcircuit if statement
if valid_X is not None and current_valid_loss < best_valid_loss:
best_valid_loss = current_valid_loss
f = open(self.model_save_name + "_valid_best.pkl", 'wb')
cPickle.dump(self, f, protocol=2)
f.close()
except KeyboardInterrupt:
print("User cancelled, saving last model!")
f = open(self.model_save_name + "_interrupt.pkl", 'wb')
cPickle.dump(self, f, protocol=2)
f.close()
def fit(self, X, y, valid_X=None, valid_y=None):
if self.input_checking:
X, y = rnn_check_array(X, y)
input_size = X[0].shape[1]
# Assume that class values are sequential! and start from 0
highest_class = np.max([np.max(d) for d in y])
lowest_class = np.min([np.min(d) for d in y])
if lowest_class != 0:
raise ValueError("Labels must start from 0!")
# Create a list of all classes, then get uniques
# sum(lists, []) is list concatenation
all_classes = np.unique(sum([list(np.unique(d)) for d in y], []))
# +1 to include endpoint
output_size = len(np.arange(lowest_class, highest_class + 1))
X_sym = T.tensor3('x')
y_sym = T.tensor3('y')
X_mask = T.matrix('x_mask')
y_mask = T.matrix('y_mask')
self.layers_ = []
self.layer_sizes_ = [input_size]
self.layer_sizes_.extend(self.hidden_layer_sizes)
self.layer_sizes_.append(output_size)
if not hasattr(self, 'fit_function'):
print("Building model!")
self._setup_functions(X_sym, y_sym, X_mask, y_mask,
self.layer_sizes_)
self.training_loss_ = []
if valid_X is not None:
self.validation_loss_ = []
if self.input_checking:
valid_X, valid_y = rnn_check_array(valid_X, valid_y)
for vy in valid_y:
if not np.in1d(np.unique(vy), all_classes).all():
raise ValueError(
"Validation set contains classes not in training"
"set! Training set classes: %s\n, Validation set \
classes: %s" % (all_classes, np.unique(vy)))
best_valid_loss = np.inf
best_train_loss = np.inf
try:
for itr in range(self.max_iter):
print("Starting pass %d through the dataset" % itr)
total_train_loss = 0
for i, j in minibatch_indices(X, self.minibatch_size):
X_n, y_n, X_mask, y_mask = make_minibatch(
X[i:j], y[i:j], output_size)
train_loss = self.fit_function(X_n, y_n, X_mask, y_mask)
total_train_loss += train_loss
current_train_loss = total_train_loss / len(X)
print("Training loss %f" % current_train_loss)
self.training_loss_.append(current_train_loss)
if valid_X is not None:
total_valid_loss = 0
for i, j in minibatch_indices(valid_X,
self.minibatch_size):
valid_X_n, valid_y_n, X_mask, y_mask = make_minibatch(
valid_X[i:j], valid_y[i:j], output_size)
valid_loss = self.loss_function(
valid_X_n, valid_y_n, X_mask, y_mask)
total_valid_loss += valid_loss
current_valid_loss = total_valid_loss / len(valid_X)
print("Validation loss %f" % current_valid_loss)
self.validation_loss_.append(current_valid_loss)
if (itr % self.save_frequency) == 0:
f = open(self.model_save_name + "_snapshot.pkl", 'wb')
cPickle.dump(self, f, protocol=2)
f.close()
if current_train_loss < best_train_loss:
best_train_loss = current_train_loss
f = open(self.model_save_name + "_train_best.pkl",
'wb')
cPickle.dump(self, f, protocol=2)
f.close()
if itr == (self.max_iter - 1):
f = open(self.model_save_name + "_last.pkl", 'wb')
cPickle.dump(self, f, protocol=2)
f.close()
# Shortcircuit if statement
if valid_X is not None and current_valid_loss < best_valid_loss:
best_valid_loss = current_valid_loss
f = open(self.model_save_name + "_valid_best.pkl", 'wb')
cPickle.dump(self, f, protocol=2)
f.close()
except KeyboardInterrupt:
print("User cancelled, saving last model!")
f = open(self.model_save_name + "_interrupt.pkl", 'wb')
cPickle.dump(self, f, protocol=2)
f.close()
