def do_train(sess,X_input, Y_input, X_validation, Y_validation):
ground_truth_tensor_name = 'ground_truth'
mini_batch_size = 256
n_train = X_input.shape[0]
graph = create_graph()
train_step, cross_entropy = add_final_training_ops(
graph, len(classes), FLAGS.final_tensor_name,
ground_truth_tensor_name)
init = tf.initialize_all_variables()
sess.run(init)
evaluation_step = add_evaluation_step(graph, FLAGS.final_tensor_name, ground_truth_tensor_name)
bottleneck_tensor = graph.get_tensor_by_name(ensure_name_has_port(BOTTLENECK_TENSOR_NAME))
ground_truth_tensor = graph.get_tensor_by_name(ensure_name_has_port(ground_truth_tensor_name))
i=0
epocs = 20
validation_acc_vector = []
training_acc_vector = []
cross_entropy_vector = []
for epoch in xrange(epocs):
shuffledRange = np.random.permutation(n_train)
y_one_hot_train = encode_one_hot(len(classes), Y_input)
y_one_hot_validation = encode_one_hot(len(classes), Y_validation)
shuffledX = X_input[shuffledRange,:]
shuffledY = y_one_hot_train[shuffledRange]
for Xi, Yi in iterate_mini_batches(shuffledX, shuffledY, mini_batch_size):
sess.run(train_step,
feed_dict={bottleneck_tensor: Xi,
ground_truth_tensor: Yi})
is_last_step = (i + 1 == FLAGS.how_many_training_steps)
if (i % FLAGS.eval_step_interval) == 0 or is_last_step:
train_accuracy, cross_entropy_value = sess.run(
[evaluation_step, cross_entropy],
feed_dict={bottleneck_tensor: Xi,
ground_truth_tensor: Yi})
validation_accuracy = sess.run(
evaluation_step,
feed_dict={bottleneck_tensor: X_validation,
ground_truth_tensor: y_one_hot_validation})
print('%s: Step %d: Train accuracy = %.1f%%, Cross entropy = %f, Validation accuracy = %.1f%%' %
(datetime.now(), i, train_accuracy * 100, cross_entropy_value, validation_accuracy * 100))
cross_entropy_vector.append(cross_entropy_value)
training_acc_vector.append(train_accuracy * 100)
validation_acc_vector.append(validation_accuracy * 100)
i+=1
print("cross entropy vector length is "+str(len(cross_entropy_vector)))
""" plotting the training accuarcy vs iterations """
x_ax = np.arange(0,len(cross_entropy_vector))
fig, ax = plt.subplots(nrows = 1, ncols = 1)
ax.plot(x_ax, training_acc_vector)
plt.xlabel('Iterations')
plt.ylabel('Training Accuracy')
plt.title('Training Accuracy vs Number of Iterations')
fig.savefig('training_acc.jpg')
plt.close(fig)
""" plotting the validation accuarcy vs iterations """
x_ax = np.arange(0,len(cross_entropy_vector))
fig, ax = plt.subplots(nrows = 1, ncols = 1)
ax.plot(x_ax, validation_acc_vector)
plt.xlabel('Iterations')
plt.ylabel('Validation Accuracy')
plt.title('Validation Accuracy vs Number of Iterations')
fig.savefig('validation_acc.jpg')
plt.close(fig)
""" plotting the cross-entropy error vs iterations """
x_ax = np.arange(0,len(cross_entropy_vector))
fig, ax = plt.subplots(nrows = 1, ncols = 1)
ax.plot(x_ax, cross_entropy_vector)
plt.xlabel('Iterations')
plt.ylabel('Cross Entropy value')
plt.title('Cross Entropy Value vs Number of Iterations')
fig.savefig('cross_entropy_value.jpg')
plt.close(fig)
""" calculating the test_set accuracy """
test_accuracy = sess.run(
evaluation_step,
feed_dict={bottleneck_tensor: X_test_pool3,
ground_truth_tensor: encode_one_hot(len(classes), y_test_pool3)})
print('Final test accuracy = %.1f%%' % (test_accuracy * 100))
def do_train(sess, X_input, Y_input, X_validation, Y_validation):
mini_batch_size = 10
n_train = X_input.shape[0]
graph = create_graph()
LAYER_WEIGHTS_NAME = "layer_weights"
LAYER_BIASES_NAME = "layer_biases"
# Initialize tensorflow variable for the training process
bottleneck_tensor_train = tf.placeholder(
tf.float32, [mini_batch_size, BOTTLENECK_TENSOR_SIZE],
name=BOTTLENECK_TENSOR_TRAIN_NAME)
ground_truth_tensor_train = tf.placeholder(
tf.float32, [mini_batch_size, len(classes)],
name=GROUND_TRUTH_TENSOR_TRAIN)
layer_weights = tf.Variable(tf.truncated_normal(
[BOTTLENECK_TENSOR_SIZE, len(classes)], stddev=0.001),
name=LAYER_WEIGHTS_NAME)
layer_biases = tf.Variable(tf.zeros([len(classes)]),
name=LAYER_BIASES_NAME)
# Initialize tensorflow variable for the validating process
bottleneck_tensor_validation = tf.placeholder(
tf.float32, [mini_batch_size, BOTTLENECK_TENSOR_SIZE])
ground_truth_tensor_validation = tf.placeholder(
tf.float32, [mini_batch_size, len(classes)])
# Initialize tensorflow variable for the testing process
bottleneck_tensor_test = tf.placeholder(tf.float32,
[10000, BOTTLENECK_TENSOR_SIZE],
name=BOTTLENECK_TENSOR_TEST_NAME)
ground_truth_tensor_test = tf.placeholder(tf.float32,
[10000, len(classes)],
name=GROUND_TRUTH_TENSOR_TEST)
# draw the graph for the last layer
train_step, cross_entropy = add_final_training_ops(
graph, bottleneck_tensor_train, ground_truth_tensor_train,
layer_weights, layer_biases)
evaluation_step_validation = add_evaluation_step(
graph, bottleneck_tensor_validation, ground_truth_tensor_validation,
layer_weights, layer_biases)
evaluation_step_test = add_evaluation_step(graph, bottleneck_tensor_test,
ground_truth_tensor_test,
layer_weights, layer_biases)
init = tf.initialize_all_variables()
sess.run(init)
i = 0
epocs = 1
for epoch in range(epocs):
shuffledRange = np.random.permutation(n_train)
y_one_hot_train = encode_one_hot(len(classes), Y_input)
y_one_hot_validation = encode_one_hot(len(classes), Y_validation)
shuffledX = X_input[shuffledRange, :]
shuffledY = y_one_hot_train[shuffledRange]
for Xi, Yi in iterate_mini_batches(shuffledX, shuffledY,
mini_batch_size):
_, cross_entropy_value = sess.run([train_step, cross_entropy],
feed_dict={
bottleneck_tensor_train: Xi,
ground_truth_tensor_train: Yi
})
# Every so often, print out how well the graph is training.
is_last_step = (i + 1 == FLAGS.how_many_training_steps)
if (i % FLAGS.eval_step_interval) == 0 or is_last_step:
train_accuracy = sess.run(evaluation_step_validation,
feed_dict={
bottleneck_tensor_validation: Xi,
ground_truth_tensor_validation:
Yi
})
validation_accuracy = sess.run(evaluation_step_test,
feed_dict={
bottleneck_tensor_test:
X_validation,
ground_truth_tensor_test:
y_one_hot_validation
})
print(
'%s: Step %d: Train accuracy = %.1f%%, Cross entropy = %f, Validation accuracy = %.1f%%'
% (datetime.now(), i, train_accuracy * 100,
cross_entropy_value, validation_accuracy * 100))
i += 1
test_accuracy = sess.run(evaluation_step_test,
feed_dict={
bottleneck_tensor_test:
X_test_pool3,
ground_truth_tensor_test:
encode_one_hot(len(classes), y_test_pool3)
})
print('Final test accuracy = %.1f%%' % (test_accuracy * 100))
def do_train(sess, X_input, Y_input, X_validation, Y_validation,
X_sample_pool3):
ground_truth_tensor_name = 'ground_truth'
mini_batch_size = 1
n_train = X_input.shape[0]
graph = create_graph()
train_step, cross_entropy = add_final_training_ops(
graph, len(classes), FLAGS.final_tensor_name, ground_truth_tensor_name)
t_vars = tf.trainable_variables()
final_vars = [var for var in t_vars if 'final_' in var.name]
saver = tf.train.Saver(final_vars, max_to_keep=10)
init = tf.initialize_all_variables()
sess.run(init)
evaluation_step = add_evaluation_step(graph, FLAGS.final_tensor_name,
ground_truth_tensor_name)
# Get some layers we'll need to access during training.
bottleneck_tensor = graph.get_tensor_by_name(
ensure_name_has_port(BOTTLENECK_TENSOR_NAME))
ground_truth_tensor = graph.get_tensor_by_name(
ensure_name_has_port(ground_truth_tensor_name))
saver.restore(sess,
tf.train.latest_checkpoint(os.getcwd() + "/train/test2/"))
result_tensor = graph.get_tensor_by_name(
ensure_name_has_port(FLAGS.final_tensor_name))
''' # Uncomment this line for calculating the inception score
splits=10
preds=[]
print(X_sample_pool3)
for Xj, Yj in iterate_mini_batches(X_sample_pool3,np.zeros([X_sample_pool3.shape[0],10]),mini_batch_size):
pred = sess.run(result_tensor,feed_dict={bottleneck_tensor: Xj})
preds.append(pred)
preds = np.concatenate(preds, 0)
argmax = preds.argmax(axis=1)
scores = []
# Calculating the inception score
for i in range(splits):
part = preds[argmax==i]
logp= np.log(part)
self = np.sum(part*logp,axis=1)
cross = np.mean(np.dot(part,np.transpose(logp)),axis=1)
diff = self - cross
kl = np.mean(self - cross)
kl1 = []
for j in range(splits):
diffj = diff[(j * diff.shape[0] // splits):((j+ 1) * diff.shape[0] //splits)]
kl1.append(np.exp(diffj.mean()))
print("category: %s scores_mean = %.2f, scores_std = %.2f" % (classes[i], np.mean(kl1),np.std(kl1)))
scores.append(np.exp(kl))
print("scores_mean = %.2f, scores_std = %.2f" % (np.mean(scores),
np.std(scores)))
''' # Uncomment this line for calculating the inception score
# The block commented out below has to be uncommented for transfer learning and the block above has to be commented
# ''' # Comment this line when doing transfer learning
i = 0
epocs = 1
for epoch in range(epocs):
shuffledRange = np.random.permutation(n_train)
y_one_hot_train = encode_one_hot(len(classes), Y_input)
y_one_hot_validation = encode_one_hot(len(classes), Y_validation)
shuffledX = X_input[shuffledRange, :]
shuffledY = y_one_hot_train[shuffledRange]
for Xi, Yi in iterate_mini_batches(shuffledX, shuffledY,
mini_batch_size):
sess.run(train_step,
feed_dict={
bottleneck_tensor: Xi,
ground_truth_tensor: Yi
})
# Every so often, print out how well the graph is training.
is_last_step = (i + 1 == FLAGS.how_many_training_steps)
if (i % FLAGS.eval_step_interval) == 0 or is_last_step:
train_accuracy, cross_entropy_value = sess.run(
[evaluation_step, cross_entropy],
feed_dict={
bottleneck_tensor: Xi,
ground_truth_tensor: Yi
})
if (i % 1000) == 0:
saver.save(sess, os.getcwd() + "/train/test2/", global_step=i)
i += 1
validation_accuracy = 0
for Xj, Yj in iterate_mini_batches(X_validation, y_one_hot_validation,
mini_batch_size):
validation_accuracy = validation_accuracy + sess.run(
evaluation_step,
feed_dict={
bottleneck_tensor: Xj,
ground_truth_tensor: Yj
})
validation_accuracy = validation_accuracy / X_validation.shape[0]
print(
'%s: Step %d: Train accuracy = %.1f%%, Cross entropy = %f, Validation accuracy = %.1f%%'
% (datetime.now(), i, train_accuracy * 100, cross_entropy_value,
validation_accuracy * 100))
for Xi, Yi in iterate_mini_batches(
X_test_pool3, encode_one_hot(len(classes), y_test_pool3),
mini_batch_size):
test_accuracy = sess.run(evaluation_step,
feed_dict={
bottleneck_tensor: Xi,
ground_truth_tensor: Yi
})
print('Final test accuracy = %.1f%%' % (test_accuracy * 100))