correct_pred = tf.equal(tf.argmax(model, 1), tf.argmax(outputs, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
cifar = Cifar(batch_size=batch_size)
cifar.create_resized_test_set(dim=n_classes)
init = tf.initialize_all_variables()
with tf.Session() as sess:
sess.run(init)
run_options = tf.RunOptions(report_tensor_allocations_upon_oom=True)
for epoch in range(no_of_epochs):
for i in tqdm(range(cifar.no_of_batches),
desc="Epoch {}".format(epoch),
unit=" batch "):
this_batch = cifar.batch(i)
input_batch, out = helper.reshape_batch(this_batch,
(image_size, image_size),
n_classes)
sess.run([optimizer],
feed_dict={
pretrained.x: input_batch,
outputs: out
},
options=run_options)
acc, loss = sess.run([accuracy, cost],
feed_dict={
pretrained.x: input_batch,
outputs: out
#outputs = tf.placeholder(tf.float32, [None, n_classes])
# ====================
# config dataset
# ====================
print('Prepare dataset')
train_dataset = Cifar(batch_size = batch_size)
init = tf.initialize_all_variables()
trian_features = None
train_label = None
with tf.Session(config=config) as sess:
sess.run(init)
for i in tqdm(range(20), unit=" batch "):
this_batch = train_dataset.batch(i)
train_X, train_y = helper.reshape_batch(this_batch, (image_size, image_size), n_classes)
train_y = [np.argmax(element) for element in train_y]
features = sess.run(
[extractor],
feed_dict={
model.input_images: train_X
})
if trian_features is None:
trian_features = features[0]
train_label = train_y
else:
trian_features = np.concatenate((trian_features, features[0]), axis=0)
train_label += train_y