def my_data(self):
# load training data
train_images = util.np.load(
os.path.join(self.args.data_dir, 'fmnist_train_data.npy'))
train_labels = util.np.load(
os.path.join(self.args.data_dir, 'fmnist_train_labels.npy'))
train_labels = tf.Session().run(tf.one_hot(train_labels, 10))
# normalize data
train_images = train_images / 255
# set up test set
test_images, train_images = util.split_data(train_images,
self.test_set_size)
test_labels, train_labels = util.split_data(train_labels,
self.test_set_size)
# set up validation set
train_images, train_labels = util.shuffler(train_images, train_labels)
validation_images, train_images = util.split_data(
train_images, self.validation_set_size)
validation_labels, train_labels = util.split_data(
train_labels, self.validation_set_size)
data = {
"train_images": train_images,
"train_labels": train_labels,
"test_images": test_images,
"test_labels": test_labels,
"validation_images": validation_images,
"validation_labels": validation_labels
}
return data
def my_data(self):
# load training data
train_images = util.np.load(
os.path.join(self.args.data_dir, 'cifar_images.npy'))
# normalize data
train_images = train_images / 255
# reshape to fit input tensor
train_images = np.reshape(
train_images,
[-1, 32, 32, 3
]) # `-1` means "everything not otherwise accounted for"
# load training labels
train_labels = util.np.load(
os.path.join(self.args.data_dir, 'cifar_labels.npy'))
train_images, train_labels = util.shuffler(train_images, train_labels)
# convert labels to one-hots
train_labels = tf.Session().run(tf.one_hot(train_labels, 100))
# set up test set
test_images, train_images = util.split_data(train_images,
self.test_set_size)
test_labels, train_labels = util.split_data(train_labels,
self.test_set_size)
# set up validation set
validation_images, train_images = util.split_data(
train_images, self.validation_set_size)
validation_labels, train_labels = util.split_data(
train_labels, self.validation_set_size)
data = {
"train_images": train_images,
"train_labels": train_labels,
"test_images": test_images,
"test_labels": test_labels,
"validation_images": validation_images,
"validation_labels": validation_labels
}
return data
def train_classifier(ae_path_prefix):
tf.reset_default_graph()
params = {
'path_prefix': ae_path_prefix,
"starter_learning_rate": .001,
"reduction_rate": 0.70,
"reg_scale": 0.0001,
"batch_size": 128,
}
m = model.Model(params)
# split into train, validation, and test
train_im_num = m.train_images.shape[0]
test_im_num = m.test_images.shape[0]
val_im_num = m.validation_images.shape[0]
mean_cross_entropy = tf.reduce_mean(m.cross_entropy)
# Define network operations
network_train_op = m.network_train_op()
confusion_matrix_op = m.confusion_matrix_op()
batch_size = m.batch_size
with tf.Session() as session:
session.run(tf.global_variables_initializer())
best_val_ce = sys.maxsize
counter = 0
avg_val_cs = 0
for epoch in range(m.epochs):
print('Epoch: ' + str(epoch))
# shuffle data each epoch before training
train_images, train_labels = util.shuffler(m.train_images, m.train_labels)
# run gradient steps and report mean loss on train data
ce_vals = []
for i in range(train_im_num // batch_size):
batch_xs = train_images[i * batch_size:(i + 1) * batch_size, :]
batch_ys = np.squeeze(train_labels[i * batch_size:(i + 1) * batch_size, :])
_, train_ce = session.run(
[network_train_op, mean_cross_entropy], {
m.ae_x: batch_xs,
m.y: batch_ys
})
ce_vals.append(train_ce)
avg_train_ce = sum(ce_vals) / len(ce_vals)
print('TRAIN CROSS ENTROPY: ' + str(avg_train_ce))
# report mean validation loss
ce_vals = []
conf_mxs = []
for i in range(val_im_num // batch_size):
batch_xs = m.validation_images[i * batch_size:(i + 1) * batch_size, :]
batch_ys = np.squeeze(m.validation_labels[i * batch_size:(i + 1) * batch_size, :])
val_ce, conf_matrix = session.run(
[mean_cross_entropy, confusion_matrix_op], {
m.ae_x: batch_xs,
m.y: batch_ys
})
ce_vals.append(val_ce)
conf_mxs.append(conf_matrix)
avg_val_ce = sum(ce_vals) / len(ce_vals)
print('VALIDATION CROSS ENTROPY: ' + str(avg_val_ce))
print('VALIDATION ACCURACY: ' + str(sum(sum(conf_mxs).diagonal()) / val_im_num))
print('VALIDATION CONFUSION MATRIX:')
print(str(sum(conf_mxs)))
# report mean test loss
ce_vals = []
conf_mxs = []
for i in range(test_im_num // batch_size):
batch_xs = m.test_images[i * batch_size:(i + 1) * batch_size, :]
batch_ys = np.squeeze(m.test_labels[i * batch_size:(i + 1) * batch_size, :])
test_ce, conf_matrix = session.run(
[mean_cross_entropy, confusion_matrix_op], {
m.ae_x: batch_xs,
m.y: batch_ys
})
ce_vals.append(test_ce)
conf_mxs.append(conf_matrix)
avg_test_ce = sum(ce_vals) / len(ce_vals)
print('TEST CROSS ENTROPY: ' + str(avg_test_ce))
print('TEST ACCURACY: ' + str(sum(sum(conf_mxs).diagonal()) / test_im_num))
if avg_val_ce > best_val_ce:
counter += 1
elif avg_val_ce < best_val_ce:
best_val_ce = avg_val_ce
counter = 0
if counter > m.early_stopping:
break
path_prefix = m.saver.save(
session,
os.path.join(m.args.model_dir, "homework_2"),
global_step=m.global_step_tensor)
train_op = m.train_op()
confusion_matrix_op = m.confusion_matrix_op()
with tf.Session() as session:
session.run(tf.global_variables_initializer())
best_val_ce = sys.maxsize
counter = 0
avg_val_cs = 0
batch_size = m.batch_size
for epoch in range(m.epochs):
print('Epoch: ' + str(epoch))
# shuffle data each epoch before training
train_images, train_labels = util.shuffler(m.train_images,
m.train_labels)
# run gradient steps and report mean loss on train data
ce_vals = []
for i in range(train_im_num // batch_size):
batch_xs = train_images[i * batch_size:(i + 1) * batch_size, :]
batch_ys = train_labels[i * batch_size:(i + 1) * batch_size, :]
_, train_ce = session.run([train_op, mean_cross_entropy], {
m.x: batch_xs,
m.y: batch_ys
})
ce_vals.append(train_ce)
avg_train_ce = sum(ce_vals) / len(ce_vals)
print('TRAIN CROSS ENTROPY: ' + str(avg_train_ce))
# report mean validation loss