def testNoBatchNormScaleByDefault(self):
height, width = 224, 224
num_classes = 1000
inputs = tf.placeholder(tf.float32, (1, height, width, 3))
with slim.arg_scope(inception.inception_v2_arg_scope()):
inception.inception_v2(inputs, num_classes, is_training=False)
self.assertEqual(tf.global_variables('.*/BatchNorm/gamma:0$'), [])
def testRaiseValueErrorWithInvalidDepthMultiplier(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
with self.assertRaises(ValueError):
_ = inception.inception_v2(inputs, num_classes, depth_multiplier=-0.1)
with self.assertRaises(ValueError):
_ = inception.inception_v2(inputs, num_classes, depth_multiplier=0.0)
def testRaiseValueErrorWithInvalidDepthMultiplier(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
with self.assertRaises(ValueError):
_ = inception.inception_v2(inputs, num_classes, depth_multiplier=-0.1)
with self.assertRaises(ValueError):
_ = inception.inception_v2(inputs, num_classes, depth_multiplier=0.0)
def testBatchNormScale(self):
height, width = 224, 224
num_classes = 1000
inputs = tf.placeholder(tf.float32, (1, height, width, 3))
with slim.arg_scope(
inception.inception_v2_arg_scope(batch_norm_scale=True)):
inception.inception_v2(inputs, num_classes, is_training=False)
gamma_names = set(
v.op.name for v in tf.global_variables('.*/BatchNorm/gamma:0$'))
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 testTrainEvalWithReuse(self):
train_batch_size = 5
eval_batch_size = 2
height, width = 150, 150
num_classes = 1000
train_inputs = tf.random_uniform((train_batch_size, height, width, 3))
inception.inception_v2(train_inputs, num_classes)
eval_inputs = tf.random_uniform((eval_batch_size, height, width, 3))
logits, _ = inception.inception_v2(eval_inputs, num_classes, reuse=True)
predictions = tf.argmax(logits, 1)
with self.test_session() as sess:
sess.run(tf.global_variables_initializer())
output = sess.run(predictions)
self.assertEquals(output.shape, (eval_batch_size,))
def create(self, images, num_classes, is_training):
"""See baseclass."""
with slim.arg_scope(inception.inception_v2_arg_scope()):
_, endpoints = inception.inception_v2(inputs=images,
num_classes=num_classes,
is_training=is_training)
return endpoints
def testTrainEvalWithReuse(self):
train_batch_size = 5
eval_batch_size = 2
height, width = 150, 150
num_classes = 1000
train_inputs = tf.random_uniform((train_batch_size, height, width, 3))
inception.inception_v2(train_inputs, num_classes)
eval_inputs = tf.random_uniform((eval_batch_size, height, width, 3))
logits, _ = inception.inception_v2(eval_inputs, num_classes, reuse=True)
predictions = tf.argmax(logits, 1)
with self.test_session() as sess:
sess.run(tf.global_variables_initializer())
output = sess.run(predictions)
self.assertEquals(output.shape, (eval_batch_size,))
def Inception_V2(input_batch):
"""
Reference:
1. Vasili's codes
2. https://github.com/tensorflow/models/issues/429#issuecomment-277885861
"""
slim_dir = "/home/xyang/workspace/models/research/slim"
checkpoints_dir = slim_dir + "/pretrain"
checkpoints_file = checkpoints_dir + '/inception_v2.ckpt'
import sys
sys.path.append(slim_dir)
from nets import inception
slim = tf.contrib.slim
image_size = inception.inception_v2.default_image_size
cropped_images = tf.random_crop(
tf.image.convert_image_dtype(input_batch, dtype=tf.float32),
[tf.shape(input_batch)[0], image_size, image_size, 3])
preprocessed_images = tf.multiply(tf.subtract(cropped_images, 0.5), 2.0)
# Create the model, use the default arg scope to configure
# the batch norm parameters.
with slim.arg_scope(inception.inception_v2_arg_scope()):
logits, endpoints = inception.inception_v2(preprocessed_images,
num_classes=1001,
is_training=True)
pool5 = endpoints['AvgPool_1a']
return tf.reshape(pool5, (-1, 1024))
def testBuildEndPointsWithDepthMultiplierGreaterThanOne(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
_, end_points = inception.inception_v2(inputs, num_classes)
endpoint_keys = [key for key in end_points.keys()
if key.startswith('Mixed') or key.startswith('Conv')]
_, end_points_with_multiplier = inception.inception_v2(
inputs, num_classes, scope='depth_multiplied_net',
depth_multiplier=2.0)
for key in endpoint_keys:
original_depth = end_points[key].get_shape().as_list()[3]
new_depth = end_points_with_multiplier[key].get_shape().as_list()[3]
self.assertEqual(2.0 * original_depth, new_depth)
def testBuildEndPointsWithDepthMultiplierGreaterThanOne(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
_, end_points = inception.inception_v2(inputs, num_classes)
endpoint_keys = [key for key in end_points.keys()
if key.startswith('Mixed') or key.startswith('Conv')]
_, end_points_with_multiplier = inception.inception_v2(
inputs, num_classes, scope='depth_multiplied_net',
depth_multiplier=2.0)
for key in endpoint_keys:
original_depth = end_points[key].get_shape().as_list()[3]
new_depth = end_points_with_multiplier[key].get_shape().as_list()[3]
self.assertEqual(2.0 * original_depth, new_depth)
def testLogitsNotSqueezed(self):
num_classes = 25
images = tf.random_uniform([1, 224, 224, 3])
logits, _ = inception.inception_v2(images,
num_classes=num_classes,
spatial_squeeze=False)
with self.test_session() as sess:
tf.global_variables_initializer().run()
logits_out = sess.run(logits)
self.assertListEqual(list(logits_out.shape), [1, 1, 1, num_classes])
def testBuildPreLogitsNetwork(self):
batch_size = 5
height, width = 224, 224
num_classes = None
inputs = tf.random_uniform((batch_size, height, width, 3))
net, end_points = inception.inception_v2(inputs, num_classes)
self.assertTrue(net.op.name.startswith('InceptionV2/Logits/AvgPool'))
self.assertListEqual(net.get_shape().as_list(), [batch_size, 1, 1, 1024])
self.assertFalse('Logits' in end_points)
self.assertFalse('Predictions' in end_points)
def testLogitsNotSqueezed(self):
num_classes = 25
images = tf.random_uniform([1, 224, 224, 3])
logits, _ = inception.inception_v2(images,
num_classes=num_classes,
spatial_squeeze=False)
with self.test_session() as sess:
tf.global_variables_initializer().run()
logits_out = sess.run(logits)
self.assertListEqual(list(logits_out.shape), [1, 1, 1, num_classes])
def testBuildPreLogitsNetwork(self):
batch_size = 5
height, width = 224, 224
num_classes = None
inputs = tf.random_uniform((batch_size, height, width, 3))
net, end_points = inception.inception_v2(inputs, num_classes)
self.assertTrue(net.op.name.startswith('InceptionV2/Logits/AvgPool'))
self.assertListEqual(net.get_shape().as_list(), [batch_size, 1, 1, 1024])
self.assertFalse('Logits' in end_points)
self.assertFalse('Predictions' in end_points)
def testBuildClassificationNetwork(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, end_points = inception.inception_v2(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV2/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertTrue('Predictions' in end_points)
self.assertListEqual(end_points['Predictions'].get_shape().as_list(),
[batch_size, num_classes])
def testBuildClassificationNetwork(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, end_points = inception.inception_v2(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV2/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertTrue('Predictions' in end_points)
self.assertListEqual(end_points['Predictions'].get_shape().as_list(),
[batch_size, num_classes])
def testHalfSizeImages(self):
batch_size = 5
height, width = 112, 112
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, end_points = inception.inception_v2(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV2/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
pre_pool = end_points['Mixed_5c']
self.assertListEqual(pre_pool.get_shape().as_list(),
[batch_size, 4, 4, 1024])
def testHalfSizeImages(self):
batch_size = 5
height, width = 112, 112
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, end_points = inception.inception_v2(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV2/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
pre_pool = end_points['Mixed_5c']
self.assertListEqual(pre_pool.get_shape().as_list(),
[batch_size, 4, 4, 1024])
def testEvaluation(self):
batch_size = 2
height, width = 224, 224
num_classes = 1000
eval_inputs = tf.random_uniform((batch_size, height, width, 3))
logits, _ = inception.inception_v2(eval_inputs, num_classes,
is_training=False)
predictions = tf.argmax(logits, 1)
with self.test_session() as sess:
sess.run(tf.global_variables_initializer())
output = sess.run(predictions)
self.assertEquals(output.shape, (batch_size,))
def testEvaluation(self):
batch_size = 2
height, width = 224, 224
num_classes = 1000
eval_inputs = tf.random_uniform((batch_size, height, width, 3))
logits, _ = inception.inception_v2(eval_inputs, num_classes,
is_training=False)
predictions = tf.argmax(logits, 1)
with self.test_session() as sess:
sess.run(tf.global_variables_initializer())
output = sess.run(predictions)
self.assertEquals(output.shape, (batch_size,))
def testUnknowBatchSize(self):
batch_size = 1
height, width = 224, 224
num_classes = 1000
inputs = tf.placeholder(tf.float32, (None, height, width, 3))
logits, _ = inception.inception_v2(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV2/Logits'))
self.assertListEqual(logits.get_shape().as_list(), [None, num_classes])
images = tf.random_uniform((batch_size, height, width, 3))
with self.test_session() as sess:
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):
"""Constructs model and return probabilities for given input."""
reuse = True if self.built else None
x_input = image_normalize(x_input, normalization_method[1])
x_input = tf.image.resize_images(x_input, [224, 224])
with slim.arg_scope(inception.inception_v2_arg_scope()):
_, end_points = inception.inception_v2(
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 probs
def testUnknowBatchSize(self):
batch_size = 1
height, width = 224, 224
num_classes = 1000
inputs = tf.placeholder(tf.float32, (None, height, width, 3))
logits, _ = inception.inception_v2(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV2/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[None, num_classes])
images = tf.random_uniform((batch_size, height, width, 3))
with self.test_session() as sess:
sess.run(tf.global_variables_initializer())
output = sess.run(logits, {inputs: images.eval()})
self.assertEquals(output.shape, (batch_size, num_classes))
def testUnknownImageShape(self):
tf.reset_default_graph()
batch_size = 2
height, width = 224, 224
num_classes = 1000
input_np = np.random.uniform(0, 1, (batch_size, height, width, 3))
with self.test_session() as sess:
inputs = tf.placeholder(tf.float32, shape=(batch_size, None, None, 3))
logits, end_points = inception.inception_v2(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV2/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
pre_pool = end_points['Mixed_5c']
feed_dict = {inputs: input_np}
tf.global_variables_initializer().run()
pre_pool_out = sess.run(pre_pool, feed_dict=feed_dict)
self.assertListEqual(list(pre_pool_out.shape), [batch_size, 7, 7, 1024])
def testUnknownImageShape(self):
tf.reset_default_graph()
batch_size = 2
height, width = 224, 224
num_classes = 1000
input_np = np.random.uniform(0, 1, (batch_size, height, width, 3))
with self.test_session() as sess:
inputs = tf.placeholder(tf.float32, shape=(batch_size, None, None, 3))
logits, end_points = inception.inception_v2(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV2/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
pre_pool = end_points['Mixed_5c']
feed_dict = {inputs: input_np}
tf.global_variables_initializer().run()
pre_pool_out = sess.run(pre_pool, feed_dict=feed_dict)
self.assertListEqual(list(pre_pool_out.shape), [batch_size, 7, 7, 1024])
def inception_v2(inputs, is_training, opts):
with slim.arg_scope(inception.inception_v2_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_v2(
inputs,
num_classes=opts.num_classes,
is_training=is_training,
dropout_keep_prob=opts.dropout_keep_prob,
min_depth=opts.min_depth,
depth_multiplier=opts.depth_multiplier,
prediction_fn=slim.softmax,
spatial_squeeze=opts.spatial_squeeze,
reuse=None,
global_pool=opts.global_pool)
def predict(image_file, check_point, label_file):
""" Predict image file with pre-trained model and print top-3 predictions.
Arg:
image_file: Image file to predict.
check_point: Pretrained model path.
label_file: Classes list file with txt format
Returns:
Nothing.
"""
with open(label_file) as f:
classes = f.readlines()
with tf.Graph().as_default():
with open(image_file, "rb") as image_file:
image_string = image_file.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_v2_arg_scope()):
logits, _ = inception.inception_v2(processed_images,
num_classes=len(classes), is_training=False)
probabilities = tf.nn.softmax(logits)
init_fn = slim.assign_from_checkpoint_fn(check_point, slim.get_model_variables('InceptionV2'))
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])]
# Show top 3 predictions
for i in range(5):
index = sorted_inds[i]
print('Probability %0.2f%% => [%s]' % (probabilities[index] * 100, classes[index]))
def __init__(self, num_classes, train_layers=None, weights_path='DEFAULT'):
"""Create the graph of the inceptionv2 model.
"""
# Parse input arguments into class variables
if weights_path == 'DEFAULT':
self.WEIGHTS_PATH = "./pre_trained_models/inception_v2.ckpt"
else:
self.WEIGHTS_PATH = weights_path
self.train_layers = train_layers
with tf.variable_scope("input"):
self.image_size = inception.inception_v2.default_image_size
self.x_input = tf.placeholder(tf.float32, [None, self.image_size, self.image_size, 3], name="x_input")
self.y_input = tf.placeholder(tf.float32, [None, num_classes], name="y_input")
self.learning_rate = tf.placeholder(tf.float32, name="learning_rate")
self.keep_prob = tf.placeholder(tf.float32, name="keep_prob")
# train
with arg_scope(inception.inception_v2_arg_scope()):
self.logits, _ = inception.inception_v2(self.x_input,
num_classes=num_classes,
is_training=True,
reuse=tf.AUTO_REUSE,
dropout_keep_prob=self.keep_prob
)
# validation
with arg_scope(inception.inception_v2_arg_scope()):
self.logits_val, _ = inception.inception_v2(self.x_input,
num_classes=num_classes,
is_training=False,
reuse=tf.AUTO_REUSE,
dropout_keep_prob=self.keep_prob
)
with tf.name_scope("loss"):
self.loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=self.logits, labels=self.y_input))
self.loss_val = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=self.logits_val, labels=self.y_input))
with tf.name_scope("train"):
self.global_step = tf.Variable(0, name="global_step", trainable=False)
update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
var_list = [v for v in tf.trainable_variables() if v.name.split('/')[-2] in train_layers or v.name.split('/')[-3] in train_layers ]
gradients = tf.gradients(self.loss, var_list)
self.grads_and_vars = list(zip(gradients, var_list))
optimizer = tf.train.GradientDescentOptimizer(self.learning_rate)
with tf.control_dependencies(update_ops):
self.train_op = optimizer.apply_gradients(grads_and_vars=self.grads_and_vars, global_step=self.global_step)
with tf.name_scope("probability"):
self.probability = tf.nn.softmax(self.logits_val, name="probability")
with tf.name_scope("prediction"):
self.prediction = tf.argmax(self.logits_val, 1, name="prediction")
with tf.name_scope("accuracy"):
correct_prediction = tf.equal(self.prediction, tf.argmax(self.y_input, 1))
self.accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"), name="accuracy")
def batch_prediction(frame_id_to_path, frame_id_to_image_ids, image_id_to_coordinates, model, image_size, sess, \
debug=_prediction_debug):
print "batch processing: " + str(len(image_id_to_coordinates))
if model == 'inception_v1' or model == 'inception_v2' or model == 'inception_v3' or model == 'inception_v4' or \
model == 'mobilenet_v1_0.25_128' or model == 'mobilenet_v1_0.50_160' or model == 'mobilenet_v1_1.0_224' or \
model == 'inception_resnet_v2' or model == 'nasnet_mobile' or model == 'nasnet_large':
preprocessing_type = 'inception'
elif model == 'vgg_16' or model == 'resnet_v1_50' or model == 'resnet_v1_101' or model == 'resnet_v1_152':
preprocessing_type = 'vgg'
image_id_to_predictions = {}
image_ids = []
count = 0
start_time_1 = time.time()
for frame_id, path in frame_id_to_path.iteritems():
frame_string = open(path, 'rb').read()
frame = tf.image.decode_jpeg(frame_string, channels=3)
#plt.imshow(PIL.Image.open(StringIO.StringIO(sess.run(tf.image.encode_jpeg(frame)))))
#plt.show()
frame_np = cv2.imread(path, cv2.IMREAD_COLOR)
frame_height, frame_width = frame_np.shape[:2]
#print frame_np.shape
if preprocessing_type == 'inception':
processed_frame = preprocess_for_inception(frame,
frame_height,
frame_width,
sess,
central_fraction=1.0,
debug=_prediction_debug)
elif preprocessing_type == 'vgg':
processed_frame = preprocess_for_vgg(frame,
frame_height,
frame_width,
frame_height,
sess,
debug=_prediction_debug)
start_time = time.time()
height, width = processed_frame.shape[:2].as_list()
#print "Size: "+str(width)+", "+str(height)
#plt.imshow(PIL.Image.open(StringIO.StringIO(sess.run(tf.image.encode_jpeg(tf.cast(processed_frame, tf.uint8))))))
#plt.show()
for image_id in frame_id_to_image_ids[frame_id]:
fields = image_id_to_coordinates[image_id].split('\t')
x = int(width * float(fields[0]))
y = int(height * float(fields[1]))
w = int(width * float(fields[2]))
h = int(height * float(fields[3]))
processed_image = tf.image.crop_to_bounding_box(
processed_frame, y, x, h, w)
if debug:
print "object at " + str(fields)
print str(x) + ", " + str(y) + ", " + str(w) + ", " + str(
h) + ", " + str(frame_height - y - h)
if preprocessing_type == 'vgg':
plt.imshow(
PIL.Image.open(
StringIO.StringIO(
sess.run(
tf.image.encode_jpeg(
tf.cast(processed_image, tf.uint8))))))
elif preprocessing_type == 'inception':
plt.imshow(
PIL.Image.open(
StringIO.StringIO(
sess.run(
tf.image.encode_jpeg(
tf.cast(
tf.multiply(processed_image, 255),
tf.uint8))))))
plt.show()
processed_image = tf.image.resize_images(processed_image,
(image_size, image_size))
if debug:
print "resized"
if preprocessing_type == 'vgg':
plt.imshow(
PIL.Image.open(
StringIO.StringIO(
sess.run(
tf.image.encode_jpeg(
tf.cast(processed_image, tf.uint8))))))
elif preprocessing_type == 'inception':
plt.imshow(
PIL.Image.open(
StringIO.StringIO(
sess.run(
tf.image.encode_jpeg(
tf.cast(
tf.multiply(processed_image, 255),
tf.uint8))))))
plt.show()
if count == 0:
processed_images = tf.expand_dims(processed_image, 0)
else:
local_matrix = tf.expand_dims(processed_image, 0)
processed_images = tf.concat([processed_images, local_matrix],
0)
image_ids.append(image_id)
count = count + 1
print "Preparation: " + str(time.time() - start_time_1) + " seconds"
start_time = time.time()
if model == 'inception_v1':
logits, _ = inception.inception_v1(processed_images,
num_classes=1001,
is_training=False)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'inception_v1.ckpt'),
slim.get_model_variables('InceptionV1'))
elif model == 'inception_v2':
logits, _ = inception.inception_v2(processed_images,
num_classes=1001,
is_training=False)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'inception_v2.ckpt'),
slim.get_model_variables('InceptionV2'))
elif model == 'inception_v3':
logits, _ = inception.inception_v3(processed_images,
num_classes=1001,
is_training=False)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'inception_v3.ckpt'),
slim.get_model_variables('InceptionV3'))
elif model == 'inception_v4':
logits, _ = inception.inception_v4(processed_images,
num_classes=1001,
is_training=False)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'inception_v4.ckpt'),
slim.get_model_variables('InceptionV4'))
elif model == 'resnet_v1_50':
logits, _ = resnet_v1.resnet_v1_50(processed_images,
num_classes=1000,
is_training=False)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'resnet_v1_50.ckpt'),
slim.get_model_variables('resnet_v1_50'))
elif model == 'resnet_v1_101':
logits, _ = resnet_v1.resnet_v1_101(processed_images,
num_classes=1000,
is_training=False)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'resnet_v1_101.ckpt'),
slim.get_model_variables('resnet_v1_101'))
elif model == 'resnet_v1_152':
logits, _ = resnet_v1.resnet_v1_152(processed_images,
num_classes=1000,
is_training=False)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'resnet_v1_152.ckpt'),
slim.get_model_variables('resnet_v1_152'))
elif model == 'mobilenet_v1_0.25_128':
logits, _ = mobilenet_v1.mobilenet_v1(processed_images, num_classes=1001, is_training=False, \
depth_multiplier=0.25)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'mobilenet_v1_0.25_128.ckpt'),
slim.get_model_variables('MobilenetV1'))
elif model == 'mobilenet_v1_0.50_160':
logits, _ = mobilenet_v1.mobilenet_v1(processed_images, num_classes=1001, is_training=False, \
depth_multiplier=0.50)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'mobilenet_v1_0.50_160.ckpt'),
slim.get_model_variables('MobilenetV1'))
elif model == 'mobilenet_v1_1.0_224':
logits, _ = mobilenet_v1.mobilenet_v1(processed_images, num_classes=1001, is_training=False, \
depth_multiplier=1.0)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'mobilenet_v1_1.0_224.ckpt'),
slim.get_model_variables('MobilenetV1'))
elif model == 'inception_resnet_v2':
logits, _ = inception_resnet_v2.inception_resnet_v2(processed_images,
num_classes=1001,
is_training=False)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir,
'inception_resnet_v2_2016_08_30.ckpt'),
slim.get_model_variables('InceptionResnetV2'))
elif model == 'nasnet_mobile':
logits, _ = nasnet.build_nasnet_mobile(processed_images,
num_classes=1001,
is_training=False)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'model.ckpt'),
slim.get_model_variables())
elif model == 'nasnet_large':
logits, _ = nasnet.build_nasnet_large(processed_images,
num_classes=1001,
is_training=False)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'model.ckpt'),
slim.get_model_variables())
elif model == 'vgg_16':
logits, _ = vgg.vgg_16(processed_images,
num_classes=1000,
is_training=False)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'vgg_16.ckpt'),
slim.get_model_variables('vgg_16'))
print "Prediction2.1: " + str(time.time() - start_time) + " seconds"
start_time = time.time()
init_fn(sess)
print "Prediction2.2: " + str(time.time() - start_time) + " seconds"
probabilities = tf.nn.softmax(logits)
start_time = time.time()
np_image, probabilities = sess.run([frame, probabilities])
runtime = time.time() - start_time
print "Prediction: " + str(runtime) + " seconds"
for k in range(len(image_ids)):
image_id = image_ids[k]
predictions = []
prob = probabilities[k, 0:]
sorted_inds = [
i[0] for i in sorted(enumerate(-prob), key=lambda x: x[1])
]
for i in range(5):
index = sorted_inds[i]
if model == 'inception_v1' or model == 'inception_v2' or \
model == 'inception_v3' or model == 'inception_v4' or \
model == 'mobilenet_v1_0.25_128' or model == 'mobilenet_v1_0.50_160' or model == 'mobilenet_v1_1.0_224' or \
model == 'inception_resnet_v2' or model == 'nasnet_mobile' or model == 'nasnet_large':
name = names[index]
elif model == 'vgg_16' or model == 'resnet_v1_50' or model == 'resnet_v1_101' or model == 'resnet_v1_152':
name = names[index + 1]
pr = prob[index]
pair = (name, pr)
predictions.append(pair)
image_id_to_predictions[image_id] = predictions
return image_id_to_predictions, runtime, sess
def batch_prediction(image_id_to_path, model, sess):
print "batch processing: " + str(len(image_id_to_path))
image_id_to_predictions = {}
image_ids = []
count = 0
start_time_1 = time.time()
for image_id, path in image_id_to_path.iteritems():
image_string = open(path, 'rb').read()
image = tf.image.decode_jpeg(image_string, channels=3)
if model == 'inception_v1' or model == 'inception_v2' or model == 'inception_v3' or model == 'inception_v4':
processed_image = preprocess_for_inception(image,
image_size,
image_size,
central_fraction=1.0)
elif model == 'vgg_16' or model == 'resnet_v1_50' or model == 'resnet_v1_101' or model == 'resnet_v1_152':
processed_image = vgg_preprocessing.preprocess_image(
image, image_size, image_size, is_training=False)
start_time = time.time()
#print processed_image.shape
#np_val = sess.run(processed_image)
#print np_val.shape
#processed_image = tf.convert_to_tensor(np_val)
#print processed_image.shape
#print "conversion: "+str(time.time()-start_time)+" seconds"
if count == 0:
processed_images = tf.expand_dims(processed_image, 0)
else:
local_matrix = tf.expand_dims(processed_image, 0)
processed_images = tf.concat([processed_images, local_matrix], 0)
image_ids.append(image_id)
count = count + 1
print "Preparation: " + str(time.time() - start_time_1) + " seconds"
start_time = time.time()
if model == 'inception_v1':
logits, _ = inception.inception_v1(processed_images,
num_classes=1001,
is_training=False)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'inception_v1.ckpt'),
slim.get_model_variables('InceptionV1'))
elif model == 'inception_v2':
logits, _ = inception.inception_v2(processed_images,
num_classes=1001,
is_training=False)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'inception_v2.ckpt'),
slim.get_model_variables('InceptionV2'))
elif model == 'inception_v3':
logits, _ = inception.inception_v3(processed_images,
num_classes=1001,
is_training=False)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'inception_v3.ckpt'),
slim.get_model_variables('InceptionV3'))
elif model == 'inception_v4':
logits, _ = inception.inception_v4(processed_images,
num_classes=1001,
is_training=False)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'inception_v4.ckpt'),
slim.get_model_variables('InceptionV4'))
elif model == 'resnet_v1_50':
logits, _ = resnet_v1.resnet_v1_50(processed_images,
num_classes=1000,
is_training=False)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'resnet_v1_50.ckpt'),
slim.get_model_variables('resnet_v1_50'))
elif model == 'resnet_v1_101':
logits, _ = resnet_v1.resnet_v1_101(processed_images,
num_classes=1000,
is_training=False)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'resnet_v1_101.ckpt'),
slim.get_model_variables('resnet_v1_101'))
elif model == 'resnet_v1_152':
logits, _ = resnet_v1.resnet_v1_152(processed_images,
num_classes=1000,
is_training=False)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'resnet_v1_152.ckpt'),
slim.get_model_variables('resnet_v1_152'))
elif model == 'vgg_16':
logits, _ = vgg.vgg_16(processed_images,
num_classes=1000,
is_training=False)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'vgg_16.ckpt'),
slim.get_model_variables('vgg_16'))
print "Prediction2.1: " + str(time.time() - start_time) + " seconds"
start_time = time.time()
init_fn(sess)
print "Prediction2.2: " + str(time.time() - start_time) + " seconds"
probabilities = tf.nn.softmax(logits)
print "Prediction1: " + str(time.time() - start_time) + " seconds"
start_time = time.time()
np_image, probabilities = sess.run([image, probabilities])
runtime = time.time() - start_time
print "Prediction: " + str(runtime) + " seconds"
for k in range(len(image_ids)):
image_id = image_ids[k]
predictions = []
prob = probabilities[k, 0:]
sorted_inds = [
i[0] for i in sorted(enumerate(-prob), key=lambda x: x[1])
]
for i in range(5):
index = sorted_inds[i]
if model == 'inception_v1' or model == 'inception_v2' or model == 'inception_v3' or model == 'inception_v4':
name = names[index]
elif model == 'vgg_16' or model == 'resnet_v1_50' or model == 'resnet_v1_101' or model == 'resnet_v1_152':
name = names[index + 1]
pr = prob[index]
pair = (name, pr)
predictions.append(pair)
image_id_to_predictions[image_id] = predictions
return image_id_to_predictions, runtime, 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));
def create(self, images, num_classes, is_training):
"""See baseclass."""
with slim.arg_scope(inception.inception_v2_arg_scope()):
_, endpoints = inception.inception_v2(
inputs=images, num_classes=num_classes, is_training=is_training)
return endpoints
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))
def eval(params):
# batch_size = params['batch_size']
# num_examples = len(params['test_files'][0])
with tf.Graph().as_default() as g:
url = '/home/coskun/PycharmProjects/data/pose/mv_val/img/S9/Discussion 1.54138969/frame_00010.png'
filename_queue = tf.train.string_input_producer(
[url]) # list of files to read
reader = tf.WholeFileReader()
key, value = reader.read(filename_queue)
# image_raw = tf.image.decode_png(value) # use png or jpg decoder based on your files.
image_raw = tf.image.decode_png(value, channels=3)
processed_image = human36m_preprocessing.preprocess_image(
image_raw, 224, 224, is_training=is_training)
processed_images = tf.expand_dims(processed_image, 0)
# image, label = dut.distorted_inputs(params,is_training=is_training)
with slim.arg_scope(inception.inception_v2_arg_scope()):
logits, end_points = inception.inception_v2(
processed_images,
num_classes=params['n_output'],
is_training=is_training)
init_fn = ut.get_init_fn(slim, params, load_previus_cp=True)
config = tf.ConfigProto()
config.gpu_options.per_process_gpu_memory_fraction = params[
'per_process_gpu_memory_fraction']
# operations = g.get_operations()
# for operation in operations:
# print "Operation:",operation.name
features = g.get_tensor_by_name(
'InceptionV2/InceptionV2/Mixed_3b/concat:0')
# features = g.get_tensor_by_name('InceptionV2/InceptionV2/MaxPool_3a_3x3/MaxPool:0')
with tf.Session(config=config) as sess:
sess.run(tf.initialize_local_variables())
coord = tf.train.Coordinator()
threads = []
for qr in tf.get_collection(tf.GraphKeys.QUEUE_RUNNERS):
threads.extend(
qr.create_threads(sess,
coord=coord,
daemon=True,
start=True))
init_fn(sess)
num_iter = 1
print('%s: Model reading started.' % (datetime.now()))
step = 0
loss_lst = []
# while step < num_iter and not coord.should_stop():
while step < num_iter:
try:
features_values = sess.run(features)
except tf.errors.OutOfRangeError:
print('Testing finished....%d' % step)
break
print features_values.shape
img_arr = np.squeeze(features_values[:, :, :, 1])
print img_arr.shape
img = Image.fromarray(img_arr).convert('RGB')
img.save(
'/home/coskun/PycharmProjects/poseft/files/temp/my.png')
img.show()
# joint_list=['/'.join(p1.split('/')[0:-1]).replace('joints','img').replace('.cdf','')+'/frame_'+(p1.split('/')[-1].replace('.txt','')).zfill(5)+'.png' for p1 in image_names]
# print ('List equality check:')
# print len(label_names) == len(set(label_names))
# print sum(joint_list==label_names)==(len(est))
# print(len(label_names))init_fn=ut.get_init_fn(slim,params,load_previus_cp=True)
step += 1
coord.request_stop()
coord.join(threads)
