def testNoBatchNormScaleByDefault(self):
height, width = 299, 299
num_classes = 1000
inputs = tf.placeholder(tf.float32, (1, height, width, 3))
with tf.contrib.slim.arg_scope(inception.inception_v4_arg_scope()):
inception.inception_v4(inputs, num_classes, is_training=False)
self.assertEqual(tf.global_variables('.*/BatchNorm/gamma:0$'), [])
def testBatchNormScale(self):
height, width = 299, 299
num_classes = 1000
inputs = tf.placeholder(tf.float32, (1, height, width, 3))
with tf.contrib.slim.arg_scope(
inception.inception_v4_arg_scope(batch_norm_scale=True)):
inception.inception_v4(inputs, num_classes, is_training=False)
gamma_names = set(
v.op.name for v in tf.global_variables('.*/BatchNorm/gamma:0$'))
self.assertGreater(len(gamma_names), 0)
for v in tf.global_variables('.*/BatchNorm/moving_mean:0$'):
self.assertIn(v.op.name[:-len('moving_mean')] + 'gamma', gamma_names)
def testVariablesSetDevice(self):
batch_size = 5
height, width = 299, 299
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
# Force all Variables to reside on the device.
with tf.variable_scope('on_cpu'), tf.device('/cpu:0'):
inception.inception_v4(inputs, num_classes)
with tf.variable_scope('on_gpu'), tf.device('/gpu:0'):
inception.inception_v4(inputs, num_classes)
for v in tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope='on_cpu'):
self.assertDeviceEqual(v.device, '/cpu:0')
for v in tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope='on_gpu'):
self.assertDeviceEqual(v.device, '/gpu:0')
def testVariablesSetDevice(self):
batch_size = 5
height, width = 299, 299
num_classes = 1000
inputs = tf.random.uniform((batch_size, height, width, 3))
# Force all Variables to reside on the device.
with tf.compat.v1.variable_scope('on_cpu'), tf.device('/cpu:0'):
inception.inception_v4(inputs, num_classes)
with tf.compat.v1.variable_scope('on_gpu'), tf.device('/gpu:0'):
inception.inception_v4(inputs, num_classes)
for v in tf.compat.v1.get_collection(
tf.compat.v1.GraphKeys.GLOBAL_VARIABLES, scope='on_cpu'):
self.assertDeviceEqual(v.device, '/cpu:0')
for v in tf.compat.v1.get_collection(
tf.compat.v1.GraphKeys.GLOBAL_VARIABLES, scope='on_gpu'):
self.assertDeviceEqual(v.device, '/gpu:0')
def testTrainEvalWithReuse(self):
train_batch_size = 5
eval_batch_size = 2
height, width = 150, 150
num_classes = 1000
with self.test_session() as sess:
train_inputs = tf.random_uniform((train_batch_size, height, width, 3))
inception.inception_v4(train_inputs, num_classes)
eval_inputs = tf.random_uniform((eval_batch_size, height, width, 3))
logits, _ = inception.inception_v4(eval_inputs,
num_classes,
is_training=False,
reuse=True)
predictions = tf.argmax(logits, 1)
sess.run(tf.global_variables_initializer())
output = sess.run(predictions)
self.assertEquals(output.shape, (eval_batch_size,))
def testTrainEvalWithReuse(self):
train_batch_size = 5
eval_batch_size = 2
height, width = 150, 150
num_classes = 1000
with self.test_session() as sess:
train_inputs = tf.random_uniform((train_batch_size, height, width, 3))
inception.inception_v4(train_inputs, num_classes)
eval_inputs = tf.random_uniform((eval_batch_size, height, width, 3))
logits, _ = inception.inception_v4(eval_inputs,
num_classes,
is_training=False,
reuse=True)
predictions = tf.argmax(logits, 1)
sess.run(tf.global_variables_initializer())
output = sess.run(predictions)
self.assertEquals(output.shape, (eval_batch_size,))
def testBuildPreLogitsNetwork(self):
batch_size = 5
height, width = 299, 299
num_classes = None
inputs = tf.random_uniform((batch_size, height, width, 3))
net, end_points = inception.inception_v4(inputs, num_classes)
self.assertTrue(net.op.name.startswith('InceptionV4/Logits/AvgPool'))
self.assertListEqual(net.get_shape().as_list(), [batch_size, 1, 1, 1536])
self.assertFalse('Logits' in end_points)
self.assertFalse('Predictions' in end_points)
def testBuildPreLogitsNetwork(self):
batch_size = 5
height, width = 299, 299
num_classes = None
inputs = tf.random_uniform((batch_size, height, width, 3))
net, end_points = inception.inception_v4(inputs, num_classes)
self.assertTrue(net.op.name.startswith('InceptionV4/Logits/AvgPool'))
self.assertListEqual(net.get_shape().as_list(), [batch_size, 1, 1, 1536])
self.assertFalse('Logits' in end_points)
self.assertFalse('Predictions' in end_points)
def classify(checkpoints_dir, images,logo_names=[""], reuse=False):
image_size = inception.inception_v4.default_image_size
probabilities_list = []
processed_image_list = []
images_list = []
output_probabilities = []
for image in images:
image = tf.image.decode_jpeg(image, channels=3)
#image = tf.image.resize_image_with_crop_or_pad(image, 299, 299)
processed_image = inception_preprocessing.preprocess_image(image,
image_size,
image_size,
is_training=False)
#processed_images = tf.expand_dims(processed_image, 0)
images_list.append(image)
processed_image_list.append(processed_image)
with slim.arg_scope(inception_utils.inception_arg_scope()):
logits, _ = inception.inception_v4(processed_image_list,
#num_classes=2,
reuse=reuse,
is_training=False,
logo_names= logo_names)
probabilities = []
output_probabilities = []
for logo_name in logo_names:
probabilities.append(tf.nn.softmax(logits[logo_name]))
if tf.gfile.IsDirectory(checkpoints_dir):
checkpoints_dir = tf.train.latest_checkpoint(checkpoints_dir)
init_fn = slim.assign_from_checkpoint_fn(
checkpoints_dir,
slim.get_model_variables('InceptionV4'),
ignore_missing_vars=True)
with tf.Session() as sess:
init_fn(sess)
output_probabilities = sess.run([images_list,
processed_image_list]
+ probabilities)[2:]
output_dict = {}
print "range(len(output_probabilities): ", range(len(output_probabilities))
for index in range(len(output_probabilities)):
print 'logo_names[index]:[{}]'.format(logo_names[index])
print('type logo_names[index]',type(logo_names[index]));
if logo_names[index] == "":
print "here???????????????????"
output_dict [logo_names[index]] = output_probabilities[index]
else:
output_dict [logo_names[index]] = output_probabilities[index]
print "output_dict [""]: ", output_dict [""].shape
print "final 0,780 prob output_dict [""]: ", output_dict[""][0][780];
output_dict[""] = np.argsort(output_dict[""], axis=1)[:, ::-1][:, :5]
print "final output_dict [""]: ", output_dict [""]
return output_dict
def testBuildWithoutAuxLogits(self):
batch_size = 5
height, width = 299, 299
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, endpoints = inception.inception_v4(inputs, num_classes,
create_aux_logits=False)
self.assertFalse('AuxLogits' in endpoints)
self.assertTrue(logits.op.name.startswith('InceptionV4/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
def predict(image, version='V3'):
tf.reset_default_graph()
# Process the image
raw_image, processed_image = process_image(image)
class_names = imagenet.create_readable_names_for_imagenet_labels()
# Create a placeholder for the images
X = tf.placeholder(tf.float32, [None, 299, 299, 3], name="X")
#inception_v3 function returns logits and end_points dictionary
#logits are output of the network before applying softmax activation
if version.upper() == 'V3':
model_ckpt_path = INCEPTION_V3_CKPT_PATH
with slim.arg_scope(inception.inception_v3_arg_scope()):
# Set the number of classes and is_training parameter
logits, end_points = inception.inception_v3(
X, num_classes=1001, is_training=False)
elif version.upper() == 'V4':
model_ckpt_path = INCEPTION_V4_CKPT_PATH
with slim.arg_scope(inception.inception_v3_arg_scope()):
# Set the number of classes and is_training parameter
# Logits
logits, end_points = inception.inception_v4(
X, num_classes=1001, is_training=False)
predictions = end_points.get('Predictions', 'No key named predictions')
saver = tf.train.Saver()
with tf.Session() as sess:
saver.restore(sess, model_ckpt_path)
prediction_values = predictions.eval({X: processed_image})
try:
# Add an index to predictions and then sort by probability
prediction_values = [
(i, prediction)
for i, prediction in enumerate(prediction_values[0, :])
]
prediction_values = sorted(
prediction_values, key=lambda x: x[1], reverse=True)
# Plot the image
# plot_color_image(raw_image)
plot_color_image(image)
print("Using Inception_{} CNN\nPrediction: Probability\n".format(
version))
# Display the image and predictions
for i in range(5):
predicted_class = class_names[prediction_values[i][0]]
probability = prediction_values[i][1]
print("{}: {:.2f}%".format(predicted_class, probability * 100))
# If the predictions do not come out right
except:
print(predictions)
def testBuildWithoutAuxLogits(self):
batch_size = 5
height, width = 299, 299
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, endpoints = inception.inception_v4(inputs, num_classes,
create_aux_logits=False)
self.assertFalse('AuxLogits' in endpoints)
self.assertTrue(logits.op.name.startswith('InceptionV4/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
def testHalfSizeImages(self):
batch_size = 5
height, width = 150, 150
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, end_points = inception.inception_v4(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV4/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
pre_pool = end_points['Mixed_7d']
self.assertListEqual(pre_pool.get_shape().as_list(),
[batch_size, 3, 3, 1536])
def testGlobalPool(self):
batch_size = 2
height, width = 400, 600
num_classes = 1000
inputs = tf.random.uniform((batch_size, height, width, 3))
logits, end_points = inception.inception_v4(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV4/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
pre_pool = end_points['Mixed_7d']
self.assertListEqual(pre_pool.get_shape().as_list(),
[batch_size, 11, 17, 1536])
def testHalfSizeImages(self):
batch_size = 5
height, width = 150, 150
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, end_points = inception.inception_v4(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV4/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
pre_pool = end_points['Mixed_7d']
self.assertListEqual(pre_pool.get_shape().as_list(),
[batch_size, 3, 3, 1536])
def testEvaluation(self):
batch_size = 2
height, width = 299, 299
num_classes = 1000
with self.test_session() as sess:
eval_inputs = tf.random_uniform((batch_size, height, width, 3))
logits, _ = inception.inception_v4(eval_inputs,
num_classes,
is_training=False)
predictions = tf.argmax(logits, 1)
sess.run(tf.global_variables_initializer())
output = sess.run(predictions)
self.assertEquals(output.shape, (batch_size,))
def testEvaluation(self):
batch_size = 2
height, width = 299, 299
num_classes = 1000
with self.test_session() as sess:
eval_inputs = tf.random_uniform((batch_size, height, width, 3))
logits, _ = inception.inception_v4(eval_inputs,
num_classes,
is_training=False)
predictions = tf.argmax(logits, 1)
sess.run(tf.global_variables_initializer())
output = sess.run(predictions)
self.assertEquals(output.shape, (batch_size, ))
def testUnknownBatchSize(self):
batch_size = 1
height, width = 299, 299
num_classes = 1000
with self.test_session() as sess:
inputs = tf.placeholder(tf.float32, (None, height, width, 3))
logits, _ = inception.inception_v4(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV4/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[None, num_classes])
images = tf.random_uniform((batch_size, height, width, 3))
sess.run(tf.global_variables_initializer())
output = sess.run(logits, {inputs: images.eval()})
self.assertEquals(output.shape, (batch_size, num_classes))
def testUnknownBatchSize(self):
batch_size = 1
height, width = 299, 299
num_classes = 1000
with self.test_session() as sess:
inputs = tf.placeholder(tf.float32, (None, height, width, 3))
logits, _ = inception.inception_v4(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV4/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[None, num_classes])
images = tf.random_uniform((batch_size, height, width, 3))
sess.run(tf.global_variables_initializer())
output = sess.run(logits, {inputs: images.eval()})
self.assertEquals(output.shape, (batch_size, num_classes))
def __call__(self, x_input, batch_size=None, is_training=False):
"""Constructs model and return probabilities for given input."""
reuse = True if self.built else None
with slim.arg_scope(inception.inception_v4_arg_scope()):
with tf.variable_scope(self.ckpt):
logits, end_points = inception.inception_v4(
x_input, num_classes=self.num_classes, is_training=is_training,
reuse=reuse)
preds = tf.argmax(logits, axis=1)
self.built = True
self.logits = logits
self.preds = preds
return logits
def testAllEndPointsShapes(self):
batch_size = 5
height, width = 299, 299
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
_, end_points = inception.inception_v4(inputs, num_classes)
endpoints_shapes = {
'Conv2d_1a_3x3': [batch_size, 149, 149, 32],
'Conv2d_2a_3x3': [batch_size, 147, 147, 32],
'Conv2d_2b_3x3': [batch_size, 147, 147, 64],
'Mixed_3a': [batch_size, 73, 73, 160],
'Mixed_4a': [batch_size, 71, 71, 192],
'Mixed_5a': [batch_size, 35, 35, 384],
# 4 x Inception-A blocks
'Mixed_5b': [batch_size, 35, 35, 384],
'Mixed_5c': [batch_size, 35, 35, 384],
'Mixed_5d': [batch_size, 35, 35, 384],
'Mixed_5e': [batch_size, 35, 35, 384],
# Reduction-A block
'Mixed_6a': [batch_size, 17, 17, 1024],
# 7 x Inception-B blocks
'Mixed_6b': [batch_size, 17, 17, 1024],
'Mixed_6c': [batch_size, 17, 17, 1024],
'Mixed_6d': [batch_size, 17, 17, 1024],
'Mixed_6e': [batch_size, 17, 17, 1024],
'Mixed_6f': [batch_size, 17, 17, 1024],
'Mixed_6g': [batch_size, 17, 17, 1024],
'Mixed_6h': [batch_size, 17, 17, 1024],
# Reduction-A block
'Mixed_7a': [batch_size, 8, 8, 1536],
# 3 x Inception-C blocks
'Mixed_7b': [batch_size, 8, 8, 1536],
'Mixed_7c': [batch_size, 8, 8, 1536],
'Mixed_7d': [batch_size, 8, 8, 1536],
# Logits and predictions
'AuxLogits': [batch_size, num_classes],
'global_pool': [batch_size, 1, 1, 1536],
'PreLogitsFlatten': [batch_size, 1536],
'Logits': [batch_size, num_classes],
'Predictions': [batch_size, num_classes]
}
self.assertItemsEqual(list(endpoints_shapes.keys()),
list(end_points.keys()))
for endpoint_name in endpoints_shapes:
expected_shape = endpoints_shapes[endpoint_name]
self.assertTrue(endpoint_name in end_points)
self.assertListEqual(
end_points[endpoint_name].get_shape().as_list(),
expected_shape)
def __call__(self, x_input):
"""Constructs model and return probabilities for given input."""
reuse = True if self.built else None
x_input = image_normalize(x_input, normalization_method[3])
with slim.arg_scope(inception.inception_v4_arg_scope()):
_, end_points = inception.inception_v4(
x_input,
num_classes=self.num_classes,
is_training=False,
reuse=reuse)
self.built = True
output = end_points['Predictions']
# Strip off the extra reshape op at the output
probs = output.op.inputs[0]
return output
def inception_v4(inputs, is_training, opts):
with slim.arg_scope(inception.inception_v4_arg_scope(
weight_decay=opts.weight_decay,
use_batch_norm=opts.use_batch_norm,
batch_norm_decay=opts.batch_norm_decay,
batch_norm_epsilon=opts.batch_norm_epsilon,
activation_fn=tf.nn.relu)):
return inception.inception_v4(
inputs,
num_classes=opts.num_classes,
is_training=is_training,
dropout_keep_prob=opts.dropout_keep_prob,
reuse=None,
create_aux_logits=opts.create_aux_logits,
global_pool=opts.global_pool)
def use_fined_model(self):
image_size = inception.inception_v4.default_image_size
batch_size = 3
flowers_data_dir = "../../data/flower"
train_dir = '/tmp/inception_finetuned/'
with tf.Graph().as_default():
tf.logging.set_verbosity(tf.logging.INFO)
dataset = flowers.get_split('train', flowers_data_dir)
images, images_raw, labels = self.load_batch(dataset,
height=image_size,
width=image_size)
# Create the model, use the default arg scope to configure the batch norm parameters.
with slim.arg_scope(inception.inception_v4_arg_scope()):
logits, _ = inception.inception_v4(
images, num_classes=dataset.num_classes, is_training=True)
probabilities = tf.nn.softmax(logits)
checkpoint_path = tf.train.latest_checkpoint(train_dir)
init_fn = slim.assign_from_checkpoint_fn(
checkpoint_path, slim.get_variables_to_restore())
with tf.Session() as sess:
with slim.queues.QueueRunners(sess):
sess.run(tf.initialize_local_variables())
init_fn(sess)
np_probabilities, np_images_raw, np_labels = sess.run(
[probabilities, images_raw, labels])
for i in range(batch_size):
image = np_images_raw[i, :, :, :]
true_label = np_labels[i]
predicted_label = np.argmax(np_probabilities[i, :])
predicted_name = dataset.labels_to_names[
predicted_label]
true_name = dataset.labels_to_names[true_label]
plt.figure()
plt.imshow(image.astype(np.uint8))
plt.title('Ground Truth: [%s], Prediction [%s]' %
(true_name, predicted_name))
plt.axis('off')
plt.show()
return
def run_inference_on_image(image):
"""Runs inference on an image.
Args:
image: Image file name.
Returns:
Nothing
"""
dest_directory = FLAGS.model_dir
image_size = inception.inception_v4.default_image_size
if not tf.gfile.Exists(image):
tf.logging.fatal('File does not exist %s', image)
image_string = tf.gfile.FastGFile(image, 'rb').read()
with tf.Graph().as_default():
image = tf.image.decode_jpeg(image_string, channels=3)
processed_image = inception_preprocessing.preprocess_image(
image, image_size, image_size, is_training=False)
processed_images = tf.expand_dims(processed_image, 0)
# Create the model, use the default arg scope to configure the batch
# norm parameters.
with slim.arg_scope(inception.inception_v4_arg_scope()):
logits, _ = inception.inception_v4(
processed_images, num_classes=1001, is_training=False)
probabilities = tf.nn.softmax(logits)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(dest_directory, 'inception_v4.ckpt'),
slim.get_model_variables('InceptionV4'))
with tf.Session() as sess:
init_fn(sess)
probabilities = sess.run(probabilities)
probabilities = probabilities[0, 0:]
sorted_inds = [i[0] for i in sorted(
enumerate(-probabilities), key=lambda x:x[1])]
names = create_readable_names_for_imagenet_labels()
top_k = FLAGS.num_top_predictions
for i in range(top_k):
index = sorted_inds[i]
print('%s (score = %.5f)' % (names[index], probabilities[index]))
def testAllEndPointsShapes(self):
batch_size = 5
height, width = 299, 299
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
_, end_points = inception.inception_v4(inputs, num_classes)
endpoints_shapes = {'Conv2d_1a_3x3': [batch_size, 149, 149, 32],
'Conv2d_2a_3x3': [batch_size, 147, 147, 32],
'Conv2d_2b_3x3': [batch_size, 147, 147, 64],
'Mixed_3a': [batch_size, 73, 73, 160],
'Mixed_4a': [batch_size, 71, 71, 192],
'Mixed_5a': [batch_size, 35, 35, 384],
# 4 x Inception-A blocks
'Mixed_5b': [batch_size, 35, 35, 384],
'Mixed_5c': [batch_size, 35, 35, 384],
'Mixed_5d': [batch_size, 35, 35, 384],
'Mixed_5e': [batch_size, 35, 35, 384],
# Reduction-A block
'Mixed_6a': [batch_size, 17, 17, 1024],
# 7 x Inception-B blocks
'Mixed_6b': [batch_size, 17, 17, 1024],
'Mixed_6c': [batch_size, 17, 17, 1024],
'Mixed_6d': [batch_size, 17, 17, 1024],
'Mixed_6e': [batch_size, 17, 17, 1024],
'Mixed_6f': [batch_size, 17, 17, 1024],
'Mixed_6g': [batch_size, 17, 17, 1024],
'Mixed_6h': [batch_size, 17, 17, 1024],
# Reduction-A block
'Mixed_7a': [batch_size, 8, 8, 1536],
# 3 x Inception-C blocks
'Mixed_7b': [batch_size, 8, 8, 1536],
'Mixed_7c': [batch_size, 8, 8, 1536],
'Mixed_7d': [batch_size, 8, 8, 1536],
# Logits and predictions
'AuxLogits': [batch_size, num_classes],
'global_pool': [batch_size, 1, 1, 1536],
'PreLogitsFlatten': [batch_size, 1536],
'Logits': [batch_size, num_classes],
'Predictions': [batch_size, num_classes]}
self.assertItemsEqual(endpoints_shapes.keys(), end_points.keys())
for endpoint_name in endpoints_shapes:
expected_shape = endpoints_shapes[endpoint_name]
self.assertTrue(endpoint_name in end_points)
self.assertListEqual(end_points[endpoint_name].get_shape().as_list(),
expected_shape)
def testGlobalPoolUnknownImageShape(self):
batch_size = 1
height, width = 350, 400
num_classes = 1000
with self.test_session() as sess:
inputs = tf.placeholder(tf.float32, (batch_size, None, None, 3))
logits, end_points = inception.inception_v4(
inputs, num_classes, create_aux_logits=False)
self.assertTrue(logits.op.name.startswith('InceptionV4/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
pre_pool = end_points['Mixed_7d']
images = tf.random_uniform((batch_size, height, width, 3))
sess.run(tf.global_variables_initializer())
logits_out, pre_pool_out = sess.run([logits, pre_pool],
{inputs: images.eval()})
self.assertTupleEqual(logits_out.shape, (batch_size, num_classes))
self.assertTupleEqual(pre_pool_out.shape, (batch_size, 9, 11, 1536))
def testGlobalPoolUnknownImageShape(self):
batch_size = 2
height, width = 400, 600
num_classes = 1000
with self.test_session() as sess:
inputs = tf.placeholder(tf.float32, (batch_size, None, None, 3))
logits, end_points = inception.inception_v4(
inputs, num_classes, create_aux_logits=False)
self.assertTrue(logits.op.name.startswith('InceptionV4/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
pre_pool = end_points['Mixed_7d']
images = tf.random_uniform((batch_size, height, width, 3))
sess.run(tf.global_variables_initializer())
logits_out, pre_pool_out = sess.run([logits, pre_pool],
{inputs: images.eval()})
self.assertTupleEqual(logits_out.shape, (batch_size, num_classes))
self.assertTupleEqual(pre_pool_out.shape, (batch_size, 11, 17, 1536))
def testBuildLogits(self):
batch_size = 5
height, width = 299, 299
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, end_points = inception.inception_v4(inputs, num_classes)
auxlogits = end_points['AuxLogits']
predictions = end_points['Predictions']
self.assertTrue(auxlogits.op.name.startswith('InceptionV4/AuxLogits'))
self.assertListEqual(auxlogits.get_shape().as_list(),
[batch_size, num_classes])
self.assertTrue(logits.op.name.startswith('InceptionV4/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertTrue(predictions.op.name.startswith(
'InceptionV4/Logits/Predictions'))
self.assertListEqual(predictions.get_shape().as_list(),
[batch_size, num_classes])
def testBuildLogits(self):
batch_size = 5
height, width = 299, 299
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, end_points = inception.inception_v4(inputs, num_classes)
auxlogits = end_points['AuxLogits']
predictions = end_points['Predictions']
self.assertTrue(auxlogits.op.name.startswith('InceptionV4/AuxLogits'))
self.assertListEqual(auxlogits.get_shape().as_list(),
[batch_size, num_classes])
self.assertTrue(logits.op.name.startswith('InceptionV4/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertTrue(
predictions.op.name.startswith('InceptionV4/Logits/Predictions'))
self.assertListEqual(predictions.get_shape().as_list(),
[batch_size, num_classes])
def fine_tune_inception(self):
train_dir = '/tmp/inception_finetuned/'
image_size = inception.inception_v4.default_image_size
checkpoint_path = "../../data/trained_models/inception_v4/inception_v4.ckpt"
flowers_data_dir = "../../data/flower"
with tf.Graph().as_default():
tf.logging.set_verbosity(tf.logging.INFO)
dataset = flowers.get_split('train', flowers_data_dir)
images, _, labels = self.load_batch(dataset,
height=image_size,
width=image_size)
# Create the model, use the default arg scope to configure the batch norm parameters.
with slim.arg_scope(inception.inception_v4_arg_scope()):
logits, _ = inception.inception_v4(
images, num_classes=dataset.num_classes, is_training=True)
# Specify the loss function:
one_hot_labels = slim.one_hot_encoding(labels, dataset.num_classes)
total_loss = slim.losses.softmax_cross_entropy(
logits, one_hot_labels)
# total_loss = slim.losses.get_total_loss(add_regularization_losses=False)
# total_loss = slim.losses.get_total_loss()
# Create some summaries to visualize the training process:
tf.summary.scalar('losses/Total_Loss', total_loss)
# Specify the optimizer and create the train op:
optimizer = tf.train.AdamOptimizer(learning_rate=0.001)
train_op = slim.learning.create_train_op(total_loss, optimizer)
# Run the training:
number_of_steps = math.ceil(dataset.num_samples / 32) * 1
final_loss = slim.learning.train(
train_op,
logdir=train_dir,
init_fn=self.get_init_fn(checkpoint_path),
number_of_steps=number_of_steps)
print('Finished training. Last batch loss %f' % final_loss)
return
def getResult(photo_filenames):
labels = []
maps = getMaps(LABELS_TXT)
with tf.Graph().as_default():
tf.logging.set_verbosity(tf.logging.INFO)
input_x = tf.placeholder(dtype=tf.string)
image_raw = tf.image.decode_jpeg(input_x, channels=3)
processed_image = inception_preprocessing.preprocess_image(
image_raw, 320, 320, is_training=False)
processed_images = tf.expand_dims(processed_image, 0)
with slim.arg_scope(inception.inception_v4_arg_scope()):
logits, _ = inception.inception_v4(processed_images,
num_classes=100,
is_training=False)
probabilities = tf.nn.softmax(logits)
init_fn = slim.assign_from_checkpoint_fn(
checkpoint_path, slim.get_model_variables('InceptionV4'))
with tf.Session() as sess:
init_fn(sess)
with open(photo_filenames, 'rb') as g:
content = g.read()
probabilities_val = sess.run([probabilities],
feed_dict={input_x: content})
p_val = np.squeeze(probabilities_val)
#top_k = p_val.argsort()[-5:][::-1]
#print(top_k)
sorted_inds = [
i[0] for i in sorted(
enumerate(p_val), key=lambda x: x[1], reverse=True)
][:5]
label = ''
for indx in sorted_inds:
label += maps[str(indx)]
labels.append(label)
return labels, labels[0]
def use_inceptionv4(self):
image_size = inception.inception_v4.default_image_size
img_path = "../../data/misec_images/EnglishCockerSpaniel_simon.jpg"
checkpoint_path = "../../data/trained_models/inception_v4/inception_v4.ckpt"
with tf.Graph().as_default():
image_string = tf.read_file(img_path)
image = tf.image.decode_jpeg(image_string, channels=3)
processed_image = inception_preprocessing.preprocess_image(
image, image_size, image_size, is_training=False)
processed_images = tf.expand_dims(processed_image, 0)
# Create the model, use the default arg scope to configure the batch norm parameters.
with slim.arg_scope(inception.inception_v4_arg_scope()):
logits, _ = inception.inception_v4(processed_images,
num_classes=1001,
is_training=False)
probabilities = tf.nn.softmax(logits)
init_fn = slim.assign_from_checkpoint_fn(
checkpoint_path, slim.get_model_variables('InceptionV4'))
with tf.Session() as sess:
init_fn(sess)
np_image, probabilities = sess.run([image, probabilities])
probabilities = probabilities[0, 0:]
sorted_inds = [
i[0] for i in sorted(enumerate(-probabilities),
key=lambda x: x[1])
]
self.disp_names(sorted_inds, probabilities)
plt.figure()
plt.imshow(np_image.astype(np.uint8))
plt.axis('off')
plt.title(img_path)
plt.show()
return
def __init__(self, name):
super(Classifier, self).__init__(name)
maybe_download_and_extract()
import logging
from logging.handlers import RotatingFileHandler
file_handler = RotatingFileHandler(FLAGS.log,
maxBytes=1024 * 1024 * 100,
backupCount=20)
file_handler.setLevel(logging.INFO)
formatter = logging.Formatter(
"%(asctime)s - %(name)s - %(levelname)s - %(message)s")
file_handler.setFormatter(formatter)
self.logger.addHandler(file_handler)
self.names = imagenet.create_readable_names_for_imagenet_labels()
self.image_size = inception.inception_v4.default_image_size
self.image_str_placeholder = tf.placeholder(tf.string)
image = tf.image.decode_jpeg(self.image_str_placeholder, channels=3)
processed_image = inception_preprocessing.preprocess_image(
image, self.image_size, self.image_size, is_training=False)
processed_images = tf.expand_dims(processed_image, 0)
# Create the model, use the default arg scope to configure the
# batch norm parameters.
with slim.arg_scope(inception.inception_v4_arg_scope()):
logits, _ = inception.inception_v4(processed_images,
num_classes=1001,
is_training=False)
self.probabilities = tf.nn.softmax(logits)
dest_directory = FLAGS.model_dir
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(dest_directory, 'inception_v4.ckpt'),
slim.get_model_variables('InceptionV4'))
self.sess = tf.Session()
init_fn(self.sess)
def export():
with tf.Graph().as_default():
# build inference model
# imagenet labels
names = imagenet.create_readable_names_for_imagenet_labels()
names_tensor = tf.constant(list(names.values()))
names_lookup_table = tf.contrib.lookup.index_to_string_table_from_tensor(names_tensor)
# input transformation
serialized_tf_example = tf.placeholder(tf.string, name="tf_example")
feature_configs = {
"image/encoded": tf.FixedLenFeature(shape=[], dtype=tf.string),
}
tf_example = tf.parse_example(serialized_tf_example, feature_configs)
jpegs = tf_example["image/encoded"]
images = tf.map_fn(preprocess_image, jpegs, dtype=tf.float32)
# run inference
with slim.arg_scope(inception.inception_v4_arg_scope()):
# inception v4 models
logits, end_points = inception.inception_v4(images, num_classes=NUM_CLASSES, is_training=False)
# logits = tf.Print(logits, [logits])
probs = tf.nn.softmax(logits)
# transform output to topk result
topk_probs, topk_indices = tf.nn.top_k(probs, NUM_TOP_CLASSES)
topk_names = names_lookup_table.lookup(tf.to_int64(topk_indices))
init_fn = slim.assign_from_checkpoint_fn(
tf.train.latest_checkpoint(FLAGS.checkpoint_dir),
slim.get_model_variables(),
)
# sess config
config = tf.ConfigProto(
gpu_options={ "allow_growth": 1, },
allow_soft_placement=True,
log_device_placement=False,
)
with tf.Session(config=config) as sess:
init_fn(sess)
# # to print out all the tensornames in the attached layers to inception V3
# for node_tensor in tf.get_default_graph().as_graph_def().node:
# if str(node_tensor.name).startswith('InceptionV4/Logits'):
# print str(node_tensor.name)
prelogits = sess.graph.get_tensor_by_name("InceptionV4/Logits/Predictions:0")
# an optional alternative
# prelogits = end_points['PreLogitsFlatten']
# export inference model.
output_path = os.path.join(
tf.compat.as_bytes(FLAGS.output_dir),
tf.compat.as_bytes(str(FLAGS.model_version))
)
print("Exporting trained model to", output_path)
builder = tf.saved_model.builder.SavedModelBuilder(output_path)
# build the signature_def_map.
predict_inputs_tensor_info = tf.saved_model.utils.build_tensor_info(jpegs)
classes_output_tensor_info = tf.saved_model.utils.build_tensor_info(topk_names)
scores_output_tensor_info = tf.saved_model.utils.build_tensor_info(topk_probs)
prelogits_output_tensor_info = tf.saved_model.utils.build_tensor_info(prelogits)
prediction_signature = (
tf.saved_model.signature_def_utils.build_signature_def(
inputs={
"images": predict_inputs_tensor_info
},
outputs={
"classes": classes_output_tensor_info,
"scores": scores_output_tensor_info,
"prelogits": prelogits_output_tensor_info,
},
method_name=tf.saved_model.signature_constants.PREDICT_METHOD_NAME
)
)
legacy_init_op = tf.group(tf.tables_initializer(), name="legacy_init_op")
builder.add_meta_graph_and_variables(
sess, [tf.saved_model.tag_constants.SERVING],
signature_def_map={ "predict_images": prediction_signature, },
legacy_init_op=legacy_init_op
)
builder.save()
print("Successfully exported model to %s" % FLAGS.output_dir)
# checkpoints_dir = '/Users/zhangxin/data_public/goolenet/v4' # inception_v4.ckpt
checkpoints_dir = '/Users/zhangxin/gitlab/CarRecognition/_tmp/Train/zhangkan/inception_v4_recognition/'
img_file = '/Users/zhangxin/pic/car.jpg'
image_string = open(img_file, 'r').read()
with tf.Graph().as_default():
# url = 'https://upload.wikimedia.org/wikipedia/commons/7/70/EnglishCockerSpaniel_simon.jpg'
# image_string = urllib.urlopen(url).read()
image = tf.image.decode_jpeg(image_string, channels=3)
processed_image = inception_preprocessing.preprocess_image(image, image_size, image_size, is_training=False)
processed_images = tf.expand_dims(processed_image, 0)
# Create the model, use the default arg scope to configure the batch norm parameters.
with slim.arg_scope(inception.inception_v4_arg_scope()):
logits, _ = inception.inception_v4(processed_images, num_classes=1001, is_training=False)
probabilities = tf.nn.softmax(logits)
# init_fn = slim.assign_from_checkpoint_fn(
# os.path.join(checkpoints_dir, 'inception_v4.ckpt'),
# slim.get_model_variables('InceptionV4'))
with tf.Session() as sess:
init_fn(sess)
np_image, probabilities = sess.run([image, probabilities])
probabilities = probabilities[0, 0:]
sorted_inds = [i[0] for i in sorted(enumerate(-probabilities), key=lambda x:x[1])]
# plt.figure()
# plt.imshow(np_image.astype(np.uint8))
if os.path.isdir(images_conv_feats_save_path) is False:
os.mkdir(images_conv_feats_save_path)
if os.path.isdir(images_fc_feats_save_path) is False:
os.mkdir(images_fc_feats_save_path)
tf_image = tf.placeholder(tf.string, None)
image = tf.image.decode_jpeg(tf_image, channels=3)
processed_image = inception_preprocessing.preprocess_image(image,
image_size,
image_size,
is_training=False)
processed_images = tf.expand_dims(processed_image, 0)
with slim.arg_scope(inception.inception_v4_arg_scope()):
tf_feats_att, tf_feats_fc = inception.inception_v4(processed_images,
num_classes=1001,
is_training=False,
create_aux_logits=False)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'inception_v4.ckpt'),
slim.get_model_variables('InceptionV4'))
with tf.Session() as sess:
init_fn(sess)
for idx, image_path in enumerate(images_lists):
start_time = time.time()
image_name = os.path.basename(image_path)
url = 'file://' + image_path
image_string = urlopen(url).read()
# the network.
processed_image = inception_preprocessing.preprocess_image(
image, image_size, image_size, is_training=False)
#print processed_image
# Networks accept images in batches.
# The first dimension usually represents the batch size.
# In our case the batch size is one.
processed_images = tf.expand_dims(processed_image, 0)
# Create the model, use the default arg scope to configure
# the batch norm parameters. arg_scope is a very conveniet
# feature of slim library -- you can define default
# parameters for layers -- like stride, padding etc.
with slim.arg_scope(inception.inception_v4_arg_scope()):
logits, _ = inception.inception_v4(processed_images,
num_classes=1001,
is_training=False)
# In order to get probabilities we apply softmax on the output.
probabilities = tf.nn.softmax(logits)
# Create a function that reads the network weights
# from the checkpoint file that you downloaded.
# We will run it in session later.
#print slim.get_model_variables()
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'inception_v4.ckpt'),
slim.get_model_variables('InceptionV4'))
with tf.Session() as sess:
def main(_):
batch_shape = [FLAGS.batch_size, FLAGS.image_height, FLAGS.image_width, 3]
num_classes = 1001
# max_epsilon over checking
# get original images
origin_img_list=np.sort(glob.glob(FLAGS.origin_img_dir+"*.png"));
origin_imgs=np.zeros((len(origin_img_list),FLAGS.image_height,FLAGS.image_width,3),dtype=float);
for i in range(len(origin_img_list)):
origin_imgs[i]=imread(origin_img_list[i],mode='RGB').astype(np.float);
# get adv images
adv_img_list=np.sort(glob.glob(FLAGS.input_dir+"*.png"));
adv_imgs=np.zeros((len(adv_img_list),FLAGS.image_height,FLAGS.image_width,3),dtype=float);
for i in range(len(adv_img_list)):
adv_imgs[i]=imread(adv_img_list[i],mode='RGB').astype(np.float);
epsilon_list=np.linalg.norm(np.reshape(abs(origin_imgs-adv_imgs),[-1,FLAGS.image_height*FLAGS.image_width*3]),ord=np.inf,axis=1);
#print(epsilon_list);exit(1);
over_epsilon_list=np.zeros((len(origin_img_list),2),dtype=object);
cnt=0;
for i in range(len(origin_img_list)):
file_name=origin_img_list[i].split("/")[-1];
file_name=file_name.split(".")[0];
over_epsilon_list[i,0]=file_name;
if(epsilon_list[i]>FLAGS.max_epsilon):
over_epsilon_list[i,1]="1";
cnt+=1;
tf.logging.set_verbosity(tf.logging.INFO)
with tf.Graph().as_default():
# Prepare graph
x_input = tf.placeholder(tf.float32, shape=batch_shape)
if(FLAGS.checkpoint_file_name=="inception_v3.ckpt"):
with slim.arg_scope(inception.inception_v3_arg_scope()):
_, end_points = inception.inception_v3(
x_input, num_classes=num_classes, is_training=False)
predicted_labels = tf.argmax(end_points['Predictions'], 1)
elif(FLAGS.checkpoint_file_name=="inception_v4.ckpt"):
with slim.arg_scope(inception.inception_v4_arg_scope()):
_, end_points = inception.inception_v4(
x_input, num_classes=num_classes, is_training=False)
predicted_labels = tf.argmax(end_points['Predictions'], 1)
elif(FLAGS.checkpoint_file_name=="inception_resnet_v2_2016_08_30.ckpt"):
with slim.arg_scope(inception.inception_resnet_v2_arg_scope()):
_, end_points = inception.inception_resnet_v2(
x_input, num_classes=num_classes, is_training=False)
predicted_labels = tf.argmax(end_points['Predictions'], 1)
elif(FLAGS.checkpoint_file_name=="resnet_v2_101.ckpt"):
x_input2 = tf.image.resize_bilinear(x_input,[224,224],align_corners=False);
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
_, end_points = resnet_v2.resnet_v2_101(
x_input2, num_classes=num_classes, is_training=False)
predicted_labels = tf.argmax(end_points['predictions'], 1)
elif(FLAGS.checkpoint_file_name=="resnet_v2_50.ckpt"):
x_input2 = tf.image.resize_bilinear(x_input,[224,224],align_corners=False);
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
_, end_points = resnet_v2.resnet_v2_50(
x_input2, num_classes=num_classes, is_training=False)
predicted_labels = tf.argmax(end_points['predictions'], 1)
elif(FLAGS.checkpoint_file_name=="resnet_v2_152.ckpt"):
x_input2 = tf.image.resize_bilinear(x_input,[224,224],align_corners=False);
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
_, end_points = resnet_v2.resnet_v2_152(
x_input2, num_classes=num_classes, is_training=False)
predicted_labels = tf.argmax(end_points['predictions'], 1)
elif(FLAGS.checkpoint_file_name=="inception_v1.ckpt"):
x_input2 = tf.image.resize_bilinear(x_input,[224,224],align_corners=False);
with slim.arg_scope(inception.inception_v1_arg_scope()):
_, end_points = inception.inception_v1(
x_input2, num_classes=num_classes, is_training=False)
predicted_labels = tf.argmax(end_points['Predictions'], 1)
elif(FLAGS.checkpoint_file_name=="inception_v2.ckpt"):
x_input2 = tf.image.resize_bilinear(x_input,[224,224],align_corners=False);
with slim.arg_scope(inception.inception_v2_arg_scope()):
_, end_points = inception.inception_v2(
x_input2, num_classes=num_classes, is_training=False)
predicted_labels = tf.argmax(end_points['Predictions'], 1)
# Resnet v1 and vgg are not working now
elif(FLAGS.checkpoint_file_name=="vgg_16.ckpt"):
x_input_list=tf.unstack(x_input,FLAGS.batch_size,0);
for i in range(FLAGS.batch_size):
x_input_list[i]=vgg_preprocessing.preprocess_image(x_input_list[i],224,224);
x_input2=tf.stack(x_input_list,0);
with slim.arg_scope(vgg.vgg_arg_scope()):
_, end_points = vgg.vgg_16(
x_input2, num_classes=num_classes-1, is_training=False)
predicted_labels = tf.argmax(end_points['vgg_16/fc8'], 1)+1
elif(FLAGS.checkpoint_file_name=="vgg_19.ckpt"):
x_input_list=tf.unstack(x_input,FLAGS.batch_size,0);
for i in range(FLAGS.batch_size):
x_input_list[i]=vgg_preprocessing.preprocess_image(x_input_list[i],224,224);
x_input2=tf.stack(x_input_list,0);
with slim.arg_scope(vgg.vgg_arg_scope()):
_, end_points = vgg.vgg_19(
x_input2, num_classes=num_classes-1, is_training=False)
predicted_labels = tf.argmax(end_points['vgg_19/fc8'], 1)+1
elif(FLAGS.checkpoint_file_name=="resnet_v1_50.ckpt"):
x_input_list=tf.unstack(x_input,FLAGS.batch_size,0);
for i in range(FLAGS.batch_size):
x_input_list[i]=vgg_preprocessing.preprocess_image(x_input_list[i],224,224);
x_input2=tf.stack(x_input_list,0);
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
_, end_points = resnet_v1.resnet_v1_50(
x_input, num_classes=num_classes-1, is_training=False)
predicted_labels = tf.argmax(end_points['predictions'], 1)+1
elif(FLAGS.checkpoint_file_name=="resnet_v1_101.ckpt"):
x_input_list=tf.unstack(x_input,FLAGS.batch_size,0);
for i in range(FLAGS.batch_size):
x_input_list[i]=vgg_preprocessing.preprocess_image(x_input_list[i],224,224);
x_input2=tf.stack(x_input_list,0);
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
_, end_points = resnet_v1.resnet_v1_101(
x_input2, num_classes=num_classes-1, is_training=False)
predicted_labels = tf.argmax(end_points['predictions'], 1)+1
elif(FLAGS.checkpoint_file_name=="resnet_v1_152.ckpt"):
x_input_list=tf.unstack(x_input,FLAGS.batch_size,0);
for i in range(FLAGS.batch_size):
x_input_list[i]=vgg_preprocessing.preprocess_image(x_input_list[i],224,224);
x_input2=tf.stack(x_input_list,0);
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
_, end_points = resnet_v1.resnet_v1_152(
x_input2, num_classes=num_classes-1, is_training=False)
predicted_labels = tf.argmax(end_points['predictions'], 1)+1
# Run computation
saver = tf.train.Saver(slim.get_model_variables())
session_creator = tf.train.ChiefSessionCreator(
scaffold=tf.train.Scaffold(saver=saver),
checkpoint_filename_with_path=FLAGS.checkpoint_path+FLAGS.checkpoint_file_name,
master=FLAGS.master)
f=open(FLAGS.true_label,"r");
t_label_list=np.array([i[:-1].split(",") for i in f.readlines()]);
score=0;
with tf.train.MonitoredSession(session_creator=session_creator) as sess:
with tf.gfile.Open(FLAGS.output_file, 'w') as out_file:
for filenames, images in load_images(FLAGS.input_dir, batch_shape):
labels = sess.run(predicted_labels, feed_dict={x_input: images})
for filename, label in zip(filenames, labels):
f_name=filename.split(".")[0];
t_label=int(t_label_list[t_label_list[:,0]==f_name,1][0]);
if(t_label!=label):
if(over_epsilon_list[over_epsilon_list[:,0]==f_name,1]!="1"):
score+=1;
#out_file.write('{0},{1}\n'.format(filename, label))
print("Over max epsilon#: "+str(cnt));
print(str(FLAGS.max_epsilon)+" max epsilon Score: "+str(score));
# Open specified url and load image as a string
#image_string = urllib2.urlopen(url).read()
# Decode string into matrix with intensity values
#image = tf.image.decode_jpeg(image_string, channels=3)
X = tf.placeholder(tf.float32,
shape=[None, image_size, image_size, image_channel])
images, processed_images = get_data()
# Create the model, use the default arg scope to configure
# the batch norm parameters. arg_scope is a very conveniet
# feature of slim library -- you can define default
# parameters for layers -- like stride, padding etc.
with slim.arg_scope(inception.inception_v4_arg_scope()):
logits, _ = inception.inception_v4(X,
num_classes=1001,
is_training=False)
# In order to get probabilities we apply softmax on the output.
probabilities = tf.nn.softmax(logits)
# Create a function that reads the network weights
# from the checkpoint file that you downloaded.
# We will run it in session later.
#print slim.get_model_variables()
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'inception_v4.ckpt'),
slim.get_model_variables('InceptionV4'))
names = imagenet.create_readable_names_for_imagenet_labels()
with tf.Session() as sess:
# Load weights
def train():
eps = 2.0 * float(FLAGS.max_epsilon) / 256.0
tf.logging.set_verbosity(tf.logging.INFO)
with tf.Graph().as_default():
# Design architecture
# input
x_data = tf.placeholder(tf.float32,
[None, FLAGS.img_height, FLAGS.img_width, 3],
name="x_data")
y_label = tf.placeholder(tf.float32, [None, FLAGS.num_classes],
name="y_label")
# generator
x_generated, g_params = build_generator(x_data, FLAGS)
x_generated = x_generated * eps
x_generated = x_data + x_generated
# discriminator(inception v3)
with slim.arg_scope(inception.inception_v3_arg_scope()):
_, end_points = inception.inception_v3(
x_generated, num_classes=FLAGS.num_classes, is_training=False)
predicted_labels = tf.argmax(end_points['Predictions'], 1)
predicted_logits = end_points['Logits']
disc_var_list = slim.get_model_variables()
# discriminator(resnet v2 50)
x_generated2 = tf.image.resize_bilinear(x_generated, [224, 224],
align_corners=False)
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
_, end_points2 = resnet_v2.resnet_v2_50(
x_generated2, num_classes=FLAGS.num_classes, is_training=False)
predicted_labels2 = tf.argmax(end_points2['predictions'], 1)
predicted_logits2 = end_points2['predictions']
disc_var_list2 = slim.get_model_variables()[len(disc_var_list):]
# discriminator(resnet v2 152)
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
_, end_points3 = resnet_v2.resnet_v2_152(
x_generated2, num_classes=FLAGS.num_classes, is_training=False)
predicted_labels3 = tf.argmax(end_points3['predictions'], 1)
predicted_logits3 = end_points3['predictions']
disc_var_list3 = slim.get_model_variables()[(len(disc_var_list) +
len(disc_var_list2)):]
# discriminator(resnet v2 101)
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
_, end_points4 = resnet_v2.resnet_v2_101(
x_generated2, num_classes=FLAGS.num_classes, is_training=False)
predicted_labels4 = tf.argmax(end_points4['predictions'], 1)
predicted_logits4 = end_points4['predictions']
disc_var_list4 = slim.get_model_variables()[(len(disc_var_list) +
len(disc_var_list2) +
len(disc_var_list3)):]
# discriminator(inception v4)
with slim.arg_scope(inception.inception_v4_arg_scope()):
_, end_points5 = inception.inception_v4(
x_generated, num_classes=FLAGS.num_classes, is_training=False)
predicted_labels5 = tf.argmax(end_points5['Predictions'], 1)
predicted_logits5 = end_points['Logits']
disc_var_list5 = slim.get_model_variables()[(len(disc_var_list) +
len(disc_var_list2) +
len(disc_var_list3) +
len(disc_var_list4)):]
"""
# discriminator(vgg 19)
with slim.arg_scope(vgg.vgg_arg_scope()):
_, end_points3 = vgg.vgg_19(
x_generated2, num_classes=FLAGS.num_classes, is_training=False)
predicted_labels3 = tf.argmax(end_points3['vgg_19/fc8'], 1);
predicted_logits3 = end_points3['vgg_19/fc8'];
disc_var_list3=slim.get_model_variables()[(len(disc_var_list)+len(disc_var_list2)):];
"""
# loss and optimizer
gen_acc = tf.reduce_mean(
tf.cast(tf.equal(predicted_labels, tf.argmax(y_label, 1)),
tf.float32))
cross_entropy = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(logits=predicted_logits,
labels=y_label))
gen_acc2 = tf.reduce_mean(
tf.cast(tf.equal(predicted_labels2, tf.argmax(y_label, 1)),
tf.float32))
cross_entropy2 = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(logits=predicted_logits2,
labels=y_label))
gen_acc3 = tf.reduce_mean(
tf.cast(tf.equal(predicted_labels3, tf.argmax(y_label, 1)),
tf.float32))
cross_entropy3 = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(logits=predicted_logits3,
labels=y_label))
gen_acc4 = tf.reduce_mean(
tf.cast(tf.equal(predicted_labels4, tf.argmax(y_label, 1)),
tf.float32))
cross_entropy4 = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(logits=predicted_logits4,
labels=y_label))
gen_acc5 = tf.reduce_mean(
tf.cast(tf.equal(predicted_labels5, tf.argmax(y_label, 1)),
tf.float32))
cross_entropy5 = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(logits=predicted_logits5,
labels=y_label))
infi_norm = tf.reduce_mean(
tf.norm(tf.reshape(abs(x_data - x_generated),
[-1, FLAGS.img_size]),
ord=np.inf,
axis=1))
g_loss = -1 * cross_entropy - 1 * cross_entropy2 - 1 * cross_entropy3 - 1 * cross_entropy4 - 1 * cross_entropy5
optimizer = tf.train.AdamOptimizer(0.0001)
g_trainer = optimizer.minimize(g_loss, var_list=g_params)
# get the data and label
img_list = np.sort(glob.glob(FLAGS.input_folder + "*.png"))
total_data = np.zeros(
(len(img_list), FLAGS.img_height, FLAGS.img_width, 3), dtype=float)
for i in range(len(img_list)):
total_data[i] = imread(img_list[i], mode='RGB').astype(
np.float) / 255.0
total_data[i] = total_data[i] * 2.0 - 1.0
# 0~1 -> -1~1
val_data = np.copy(total_data[0])
f = open(FLAGS.label_folder + "true_label", "r")
total_label2 = np.array([i[:-1].split(",")[1] for i in f.readlines()],
dtype=int)
total_label = np.zeros((len(total_data), FLAGS.num_classes), dtype=int)
for i in range(len(total_data)):
total_label[i, total_label2[i]] = 1
val_label = np.copy(total_label[0])
# shuffle
total_idx = range(len(total_data))
np.random.shuffle(total_idx)
total_data = total_data[total_idx]
total_label = total_label[total_idx]
# Run computation
saver = tf.train.Saver(disc_var_list)
saver2 = tf.train.Saver(disc_var_list2)
saver3 = tf.train.Saver(disc_var_list3)
saver_gen = tf.train.Saver(g_params)
# initialization
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
saver.restore(sess,
FLAGS.checkpoint_path + FLAGS.checkpoint_file_name)
saver2.restore(sess,
FLAGS.checkpoint_path + FLAGS.checkpoint_file_name2)
saver3.restore(sess,
FLAGS.checkpoint_path + FLAGS.checkpoint_file_name3)
# training
for i in range(FLAGS.max_epoch):
tr_infi = 0
tr_ce = 0
tr_gen_acc = 0
tr_ce2 = 0
tr_gen_acc2 = 0
tr_ce3 = 0
tr_gen_acc3 = 0
tr_ce4 = 0
tr_gen_acc4 = 0
tr_ce5 = 0
tr_gen_acc5 = 0
for j in range(len(total_data) / FLAGS.batch_size):
batch_data = total_data[j * FLAGS.batch_size:(j + 1) *
FLAGS.batch_size]
batch_label = total_label[j * FLAGS.batch_size:(j + 1) *
FLAGS.batch_size]
acc_p3, ce_p3, acc_p2, ce_p2, acc_p, ce_p, infi_p, _ = sess.run(
[
gen_acc3, cross_entropy3, gen_acc2, cross_entropy2,
gen_acc, cross_entropy, infi_norm, g_trainer
],
feed_dict={
x_data: batch_data,
y_label: batch_label
})
tr_infi += infi_p
tr_ce += ce_p
tr_gen_acc += acc_p
tr_ce2 += ce_p2
tr_gen_acc2 += acc_p2
tr_ce3 += ce_p3
tr_gen_acc3 += acc_p3
print(
str(i + 1) + " Epoch InfiNorm:" + str(tr_infi / (j + 1)) +
",CE: " + str(tr_ce / (j + 1)) + ",Acc: " +
str(tr_gen_acc / (j + 1)) + ",CE2: " + str(tr_ce2 /
(j + 1)) +
",Acc2: " + str(tr_gen_acc2 / (j + 1)) + ",CE3: " +
str(tr_ce3 / (j + 1)) + ",Acc3: " + str(tr_gen_acc3 /
(j + 1)))
total_idx = range(len(total_data))
np.random.shuffle(total_idx)
total_data = total_data[total_idx]
total_label = total_label[total_idx]
saver_gen.save(
sess, "my-models_iv3_rv250_rv2152/my-model_" +
str(FLAGS.max_epsilon) + ".ckpt")
def main(_):
batch_shape = [FLAGS.batch_size, FLAGS.image_height, FLAGS.image_width, 3]
num_classes = 1001
ensemble_type = FLAGS.ensemble_type
tf.logging.set_verbosity(tf.logging.INFO)
checkpoint_path_list = [
FLAGS.checkpoint_path_inception_v1, FLAGS.checkpoint_path_inception_v2,
FLAGS.checkpoint_path_inception_v3, FLAGS.checkpoint_path_inception_v4,
FLAGS.checkpoint_path_inception_resnet_v2,
FLAGS.checkpoint_path_resnet_v1_101,
FLAGS.checkpoint_path_resnet_v1_152,
FLAGS.checkpoint_path_resnet_v2_101,
FLAGS.checkpoint_path_resnet_v2_152, FLAGS.checkpoint_path_vgg_16,
FLAGS.checkpoint_path_vgg_19
]
normalization_method = [
'default', 'default', 'default', 'default', 'global', 'caffe_rgb',
'caffe_rgb', 'default', 'default', 'caffe_rgb', 'caffe_rgb'
]
pred_list = []
for idx, checkpoint_path in enumerate(checkpoint_path_list, 1):
with tf.Graph().as_default():
if int(FLAGS.test_idx) == 20 and idx in [3]:
continue
if int(FLAGS.test_idx) in [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11
] and int(FLAGS.test_idx) != idx:
continue
# Prepare graph
if idx in [1, 2, 6, 7, 10, 11]:
_x_input = tf.placeholder(tf.float32, shape=batch_shape)
x_input = tf.image.resize_images(_x_input, [224, 224])
else:
_x_input = tf.placeholder(tf.float32, shape=batch_shape)
x_input = _x_input
x_input = image_normalize(x_input, normalization_method[idx - 1])
if idx == 1:
with slim.arg_scope(inception.inception_v1_arg_scope()):
_, end_points = inception.inception_v1(
x_input, num_classes=num_classes, is_training=False)
elif idx == 2:
with slim.arg_scope(inception.inception_v2_arg_scope()):
_, end_points = inception.inception_v2(
x_input, num_classes=num_classes, is_training=False)
elif idx == 3:
with slim.arg_scope(inception.inception_v3_arg_scope()):
_, end_points = inception.inception_v3(
x_input, num_classes=num_classes, is_training=False)
elif idx == 4:
with slim.arg_scope(inception.inception_v4_arg_scope()):
_, end_points = inception.inception_v4(
x_input, num_classes=num_classes, is_training=False)
elif idx == 5:
with slim.arg_scope(inception.inception_resnet_v2_arg_scope()):
_, end_points = inception.inception_resnet_v2(
x_input, num_classes=num_classes, is_training=False)
elif idx == 6:
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
_, end_points = resnet_v1.resnet_v1_101(x_input,
num_classes=1000,
is_training=False)
elif idx == 7:
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
_, end_points = resnet_v1.resnet_v1_152(x_input,
num_classes=1000,
is_training=False)
elif idx == 8:
with slim.arg_scope(resnet_v2.resnet_arg_scope()):
_, end_points = resnet_v2.resnet_v2_101(
x_input, num_classes=num_classes, is_training=False)
elif idx == 9:
with slim.arg_scope(resnet_v2.resnet_arg_scope()):
_, end_points = resnet_v2.resnet_v2_152(
x_input, num_classes=num_classes, is_training=False)
elif idx == 10:
with slim.arg_scope(vgg.vgg_arg_scope()):
_, end_points = vgg.vgg_16(x_input,
num_classes=1000,
is_training=False)
end_points['predictions'] = tf.nn.softmax(
end_points['vgg_16/fc8'])
elif idx == 11:
with slim.arg_scope(vgg.vgg_arg_scope()):
_, end_points = vgg.vgg_19(x_input,
num_classes=1000,
is_training=False)
end_points['predictions'] = tf.nn.softmax(
end_points['vgg_19/fc8'])
#end_points = tf.reduce_mean([end_points1['Predictions'], end_points2['Predictions'], end_points3['Predictions'], end_points4['Predictions']], axis=0)
#predicted_labels = tf.argmax(end_points, 1)
# Run computation
saver = tf.train.Saver(slim.get_model_variables())
session_creator = tf.train.ChiefSessionCreator(
scaffold=tf.train.Scaffold(saver=saver),
checkpoint_filename_with_path=checkpoint_path,
master=FLAGS.master)
pred_in = []
filenames_list = []
with tf.train.MonitoredSession(
session_creator=session_creator) as sess:
for filenames, images in load_images(FLAGS.input_dir,
batch_shape):
#if idx in [1,2,6,7,10,11]:
# # 16x299x299x3
# images = zoom(images, (1, 0.7491638795986622, 0.7491638795986622, 1), order=2)
filenames_list.extend(filenames)
end_points_dict = sess.run(end_points,
feed_dict={_x_input: images})
if idx in [6, 7, 10, 11]:
end_points_dict['predictions'] = \
np.concatenate([np.zeros([FLAGS.batch_size, 1]),
np.array(end_points_dict['predictions'].reshape(-1, 1000))],
axis=1)
try:
pred_in.extend(end_points_dict['Predictions'].reshape(
-1, num_classes))
except KeyError:
pred_in.extend(end_points_dict['predictions'].reshape(
-1, num_classes))
pred_list.append(pred_in)
if ensemble_type == 'mean':
pred = np.mean(pred_list, axis=0)
labels = np.argmax(
pred, axis=1
) # model_num X batch X class_num ==(np.mean)==> batch X class_num ==(np.argmax)==> batch
elif ensemble_type == 'vote':
pred = np.argmax(
pred_list, axis=2
) # model_num X batch X class_num ==(np.mean)==> batch X class_num ==(np.argmax)==> batch
labels = np.median(pred, axis=0)
with tf.gfile.Open(FLAGS.output_file, 'w') as out_file:
for filename, label in zip(filenames_list, labels):
out_file.write('{0},{1}\n'.format(filename, label))
with tf.Graph().as_default():
# Create model architecture
from scipy import misc
img = misc.imread('lena_299.png')
print(img.shape)
inputs = np.zeros((1, 299, 299, 3), dtype=np.float32)
inputs[0] = img
inputs = tf.stack(inputs)
with slim.arg_scope(inception.inception_v4_arg_scope()):
logits, _ = inception.inception_v4(inputs,
num_classes=num_classes,
is_training=False)
with tf.Session() as sess:
# Initialize model
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir,
'china-drink-sku_20200214_model.ckpt-200000'),
slim.get_model_variables('InceptionV4'))
init_fn(sess)
# Display model variables
for v in slim.get_model_variables():
print('name = {}, shape = {}'.format(v.name, v.get_shape()))
