def testNoBatchNormScaleByDefault(self):
height, width = 299, 299
num_classes = 1000
inputs = tf.placeholder(tf.float32, (1, height, width, 3))
with slim.arg_scope(inception.inception_v3_arg_scope()):
inception.inception_v3(inputs, num_classes, is_training=False)
self.assertEqual(tf.global_variables('.*/BatchNorm/gamma:0$'), [])
def testRaiseValueErrorWithInvalidDepthMultiplier(self):
batch_size = 5
height, width = 299, 299
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
with self.assertRaises(ValueError):
_ = inception.inception_v3(inputs, num_classes, depth_multiplier=-0.1)
with self.assertRaises(ValueError):
_ = inception.inception_v3(inputs, num_classes, depth_multiplier=0.0)
def testBatchNormScale(self):
height, width = 299, 299
num_classes = 1000
inputs = tf.placeholder(tf.float32, (1, height, width, 3))
with slim.arg_scope(
inception.inception_v3_arg_scope(batch_norm_scale=True)):
inception.inception_v3(inputs, num_classes, is_training=False)
gamma_names = set(
v.op.name for v in tf.global_variables('.*/BatchNorm/gamma:0$'))
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_v3(train_inputs, num_classes)
eval_inputs = tf.random_uniform((eval_batch_size, height, width, 3))
logits, _ = inception.inception_v3(eval_inputs, num_classes,
is_training=False, 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 testBuildEndPointsWithDepthMultiplierLessThanOne(self):
batch_size = 5
height, width = 299, 299
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
_, end_points = inception.inception_v3(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_v3(
inputs, num_classes, scope='depth_multiplied_net',
depth_multiplier=0.5)
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(0.5 * original_depth, new_depth)
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_v3(train_inputs, num_classes)
eval_inputs = tf.random_uniform((eval_batch_size, height, width, 3))
logits, _ = inception.inception_v3(eval_inputs,
num_classes,
is_training=False,
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 testBuildEndPointsWithDepthMultiplierGreaterThanOne(self):
batch_size = 5
height, width = 299, 299
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
_, end_points = inception.inception_v3(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_v3(
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, 299, 299, 3])
logits, _ = inception.inception_v3(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 = 299, 299
num_classes = None
inputs = tf.random_uniform((batch_size, height, width, 3))
net, end_points = inception.inception_v3(inputs, num_classes)
self.assertTrue(net.op.name.startswith('InceptionV3/Logits/AvgPool'))
self.assertListEqual(net.get_shape().as_list(), [batch_size, 1, 1, 2048])
self.assertFalse('Logits' in end_points)
self.assertFalse('Predictions' in end_points)
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 testLogitsNotSqueezed(self):
num_classes = 25
images = tf.random.uniform([1, 299, 299, 3])
logits, _ = inception.inception_v3(images,
num_classes=num_classes,
spatial_squeeze=False)
with self.test_session() as sess:
tf.compat.v1.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 = 299, 299
num_classes = None
inputs = tf.random.uniform((batch_size, height, width, 3))
net, end_points = inception.inception_v3(inputs, num_classes)
self.assertTrue(net.op.name.startswith('InceptionV3/Logits/AvgPool'))
self.assertListEqual(net.get_shape().as_list(), [batch_size, 1, 1, 2048])
self.assertFalse('Logits' in end_points)
self.assertFalse('Predictions' in end_points)
def __call__(self, x_input):
"""Constructs model and return probabilities for given input."""
reuse = True if self.built else None
with slim.arg_scope(inception.inception_v3_arg_scope()):
_, end_points = inception.inception_v3(
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 _buildInception():
g = tf.Graph()
with g.as_default():
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_v3(train_inputs, num_classes)
eval_inputs = tf.random_uniform(
(eval_batch_size, height, width, 3))
logits, _ = inception.inception_v3(eval_inputs,
num_classes,
is_training=False,
reuse=True)
predictions = tf.argmax(logits, 1)
train_op = g.get_collection_ref(tf_ops.GraphKeys.TRAIN_OP)
train_op.append(predictions)
return g
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_v3(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV3/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
pre_pool = end_points['Mixed_7c']
self.assertListEqual(pre_pool.get_shape().as_list(),
[batch_size, 3, 3, 2048])
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_v3(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV3/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
pre_pool = end_points['Mixed_7c']
self.assertListEqual(pre_pool.get_shape().as_list(),
[batch_size, 3, 3, 2048])
def testBuildClassificationNetwork(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_v3(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV3/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 graph_incv3(x, y, i, x_max, x_min, grad, grad_D):
eps = 2.0 * FLAGS.max_epsilon / 255.0
kd = FLAGS.derivative
momentum = FLAGS.momentum
num_iter = FLAGS.num_iter
alpha = eps / FLAGS.num_iter
tf.get_variable_scope().reuse_variables()
x_nes = x + alpha * momentum * grad
x_b = x - alpha * grad_D
with slim.arg_scope(inception.inception_v3_arg_scope()):
logits_1, end_points_1 = inception.inception_v3(
x_b, num_classes=FLAGS.num_classes, is_training=False)
cross_entropy_1 = tf.losses.softmax_cross_entropy(y,
logits_1,
label_smoothing=0.0,
weights=1.0)
noise_1 = tf.gradients(cross_entropy_1, x_b)[0]
noise_1 = noise_1 / tf.reduce_mean(tf.abs(noise_1), [1, 2, 3],
keep_dims=True)
with slim.arg_scope(inception.inception_v3_arg_scope()):
logits, end_points = inception.inception_v3(
x_nes, num_classes=FLAGS.num_classes, is_training=False)
#logits = (end_points['Logits'])
cross_entropy = tf.losses.softmax_cross_entropy(y,
logits,
label_smoothing=0.0,
weights=1.0)
noise = tf.gradients(cross_entropy, x)[0]
noise = noise / tf.reduce_mean(tf.abs(noise), [1, 2, 3], keep_dims=True)
grad_D = grad_D + kd * (noise - noise_1)
noise_all = momentum * grad + noise - grad_D
x = x + alpha * tf.sign(noise_all)
x = tf.clip_by_value(x, x_min, x_max)
i = tf.add(i, 1)
return x, y, i, x_max, x_min, noise_all, grad_D
def testBuildClassificationNetwork(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_v3(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV3/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 test_image_data():
slim = tf.contrib.slim
tf.reset_default_graph()
session = tf.Session()
names = imagenet.create_readable_names_for_imagenet_labels()
processed_images = tf.placeholder(tf.float32, shape=(None, 299, 299, 3))
with slim.arg_scope(inception.inception_v3_arg_scope()):
logits, _ = inception.inception_v3(processed_images,
num_classes=1001,
is_training=False)
probabilities = tf.nn.softmax(logits)
# Please correctly set the model path.
# Download the model at https://github.com/tensorflow/models/tree/master/research/slim
checkpoints_dir = 'model'
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'inception_v3.ckpt'),
slim.get_model_variables('InceptionV3'))
init_fn(session)
def predict_fn(images):
return session.run(probabilities, feed_dict={processed_images: images})
def f(x):
return x / 2 + 0.5
class_names = []
for item in names:
class_names.append(names[item])
images = transform_img_fn(['data/violin.JPEG'])
image = images[0]
explainer = xdeep_image.ImageExplainer(predict_fn, class_names)
explainer.explain('lime', image, top_labels=3)
explainer.show_explanation('lime', deprocess=f, positive_only=False)
explainer.explain('cle', image, top_labels=3)
explainer.show_explanation('cle', deprocess=f, positive_only=False)
explainer.explain('anchor', image)
explainer.show_explanation('anchor')
segments_slic = slic(image, n_segments=50, compactness=30, sigma=3)
explainer.initialize_shap(n_segment=50, segment=segments_slic)
explainer.explain('shap', image, nsamples=400)
explainer.show_explanation('shap', deprocess=f)
def testEvaluation(self):
batch_size = 2
height, width = 299, 299
num_classes = 1000
eval_inputs = tf.random_uniform((batch_size, height, width, 3))
logits, _ = inception.inception_v3(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 = 299, 299
num_classes = 1000
eval_inputs = tf.random.uniform((batch_size, height, width, 3))
logits, _ = inception.inception_v3(eval_inputs, num_classes,
is_training=False)
predictions = tf.argmax(input=logits, axis=1)
with self.test_session() as sess:
sess.run(tf.compat.v1.global_variables_initializer())
output = sess.run(predictions)
self.assertEquals(output.shape, (batch_size,))
def build_network(batch_size, is_training):
# input
tf_raw_image_data = tf.placeholder(tf.string, shape=(batch_size, ))
tf_body_bbox = tf.placeholder(tf.int32, shape=(batch_size, 4))
tf_labels = tf.placeholder(tf.int32, shape=(batch_size, ))
# pre-processing pipeline
crops = []
for i in range(batch_size):
image = tf.image.decode_jpeg(tf_raw_image_data[i], channels=3)
body_crop = tf.image.crop_to_bounding_box(image, tf_body_bbox[i, 1],
tf_body_bbox[i, 0],
tf_body_bbox[i, 3],
tf_body_bbox[i, 2])
processed_crop = inception_preprocessing.preprocess_image(
body_crop, image_size, image_size, is_training=is_training)
crops.append(processed_crop)
processed_images = tf.stack(crops)
# training pipeline
with slim.arg_scope(inception.inception_v3_arg_scope()):
_, endpoints = inception.inception_v3(processed_images,
num_classes=num_identity,
is_training=is_training)
# load model parameters
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, checkpoint_name),
slim.get_model_variables(original_variable_namescope))
net_before_pool = tf.reshape(endpoints['Mixed_7c'], shape=(batch_size, -1))
net_before_pool_frozen = tf.stop_gradient(net_before_pool)
tf_features = slim.fully_connected(net_before_pool_frozen,
feature_length,
activation_fn=None)
tf_features_normalized = tf.nn.l2_normalize(tf_features, dim=1)
tf_loss = coco_loss_layer(tf_features_normalized, tf_labels, batch_size)
# optimizer
tf_lr = tf.placeholder(dtype=tf.float32, shape=(), name='learning_rate')
optimizer = tf.train.AdamOptimizer(learning_rate=0.001)
train = optimizer.minimize(tf_loss)
# summary
tf.summary.scalar('coco_loss', tf_loss)
summary_op = tf.summary.merge_all()
return (tf_raw_image_data, tf_body_bbox,
tf_labels), (init_fn, tf_loss, tf_lr, train,
summary_op), tf_features
def testUnknowBatchSize(self):
batch_size = 1
height, width = 299, 299
num_classes = 1000
inputs = tf.placeholder(tf.float32, (None, height, width, 3))
logits, _ = inception.inception_v3(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV3/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 __init__(self, sess):
# placeholder
self.input_placeholder = tf.placeholder(tf.float32, shape=(None, 299, 299, 3))
# inception features extractor
device = tf.device('device:CPU:0')
if tf.test.is_gpu_available():
device = tf.device('device:GPU:0')
with device:
with tf.contrib.slim.arg_scope(inception_model.inception_v3_arg_scope()):
self.features_extractor, _ = inception_model.inception_v3(self.input_placeholder,
num_classes=0, is_training=False)
# init
init_fn = tf.contrib.slim.assign_from_checkpoint_fn(INCEPTION_MODEL_PATH,
tf.contrib.slim.get_model_variables("InceptionV3"))
init_fn(sess)
def _buildInception():
g = tf.Graph()
train_batch_size = 5
eval_batch_size = 2
height, width = 299, 299
num_classes = 1000
with g.as_default():
train_inputs = tf.random_uniform(
(train_batch_size, height, width, 3))
logits, _ = inception.inception_v3(train_inputs, num_classes)
predictions = tf.argmax(logits, 1)
train_op = g.get_collection_ref(tf_ops.GraphKeys.TRAIN_OP)
train_op.append(predictions)
return g
def load_pretrained_slim_model():
global session, names, probabilities, processed_images, slim_home_dir
names = imagenet.create_readable_names_for_imagenet_labels()
processed_images = tf.placeholder(tf.float32, shape=(None, 299, 299, 3))
with slim.arg_scope(inception.inception_v3_arg_scope()):
logits, _ = inception.inception_v3(processed_images,
num_classes=1001,
is_training=False)
probabilities = tf.nn.softmax(logits)
checkpoints_dir = os.path.join(slim_home_dir, 'pretrained')
session = tf.Session()
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'inception_v3.ckpt'),
slim.get_model_variables('InceptionV3'))
init_fn(session)
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_v3_arg_scope()):
with tf.variable_scope(self.name):
logits, end_points = inception.inception_v3(
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 testUnknownImageShape(self):
tf.compat.v1.reset_default_graph()
batch_size = 2
height, width = 299, 299
num_classes = 1000
input_np = np.random.uniform(0, 1, (batch_size, height, width, 3))
with self.test_session() as sess:
inputs = tf.compat.v1.placeholder(tf.float32, shape=(batch_size, None, None, 3))
logits, end_points = inception.inception_v3(inputs, num_classes)
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
pre_pool = end_points['Mixed_7c']
feed_dict = {inputs: input_np}
tf.compat.v1.global_variables_initializer().run()
pre_pool_out = sess.run(pre_pool, feed_dict=feed_dict)
self.assertListEqual(list(pre_pool_out.shape), [batch_size, 8, 8, 2048])
def testUnknownImageShape(self):
tf.reset_default_graph()
batch_size = 2
height, width = 299, 299
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_v3(inputs, num_classes)
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
pre_pool = end_points['Mixed_7c']
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, 8, 8, 2048])
def testUnknowBatchSize(self):
batch_size = 1
height, width = 299, 299
num_classes = 1000
inputs = tf.placeholder(tf.float32, (None, height, width, 3))
logits, _ = inception.inception_v3(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV3/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 testEvaluation(self):
print('enter testEvaluation(): %s' % datetime.now())
batch_size = 2
height, width = 299, 299
num_classes = 1000
eval_inputs = tf.random_uniform((batch_size, height, width, 3))
logits, _ = inception.inception_v3(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, ))
print('leave testEvaluation(): %s' % datetime.now())
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_v3_arg_scope()):
with tf.variable_scope(self.ckpt):
logits, end_points = inception.inception_v3(
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
#output = end_points['logits']
# Strip off the extra reshape op at the output
#probs = output.op.inputs[0]
return logits
def main():
"""
You can also run these commands manually to generate the pb file
1. git clone https://github.com/tensorflow/models.git
2. export PYTHONPATH=Path_to_your_model_folder
3. python alexnet.py
"""
tf.set_random_seed(1)
height, width = 299, 299
num_classes = 1000
inputs = tf.Variable(tf.random_uniform((1, height, width, 3)), name='input')
inputs = tf.identity(inputs, "input_node")
net, end_points = inception.inception_v3(inputs, num_classes,is_training=False)
print("nodes in the graph")
for n in end_points:
print(n + " => " + str(end_points[n]))
net_outputs = map(lambda x: tf.get_default_graph().get_tensor_by_name(x), argv[2].split(','))
run_model(net_outputs, argv[1], 'InceptionV3', argv[3] == 'True')
def inception_v3(inputs, is_training, opts):
with slim.arg_scope(inception.inception_v3_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_v3(
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,
create_aux_logits=opts.create_aux_logits,
global_pool=opts.global_pool)
def batch_results():
batch_size = 3 # number of samples to show
with tf.Graph().as_default():
tf.logging.set_verbosity(tf.logging.INFO)
images, images_raw, labels = 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_v3_arg_scope()):
logits, _ = inception.inception_v3(images,
num_classes=dataset.num_classes,
is_training=False)
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 xrange(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()
def main():
"""
You can also run these commands manually to generate the pb file
1. git clone https://github.com/tensorflow/models.git
2. export PYTHONPATH=Path_to_your_model_folder
3. python alexnet.py
"""
height, width = 299, 299
num_classes = 1000
inputs = tf.Variable(tf.random_uniform((1, height, width, 3)),
name='input')
net, end_points = inception.inception_v3(inputs,
num_classes,
is_training=False)
print("nodes in the graph")
for n in end_points:
print(n + " => " + str(end_points[n]))
net_outputs = map(lambda x: tf.get_default_graph().get_tensor_by_name(x),
argv[2].split(','))
run_model(net_outputs, argv[1], 'InceptionV3', argv[3] == 'True')
def url_results():
with tf.Graph().as_default():
url = 'http://www.vetprofessionals.com/catprofessional/images/home-cat.jpg'
image_string = urllib2.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_v3_arg_scope()):
logits, _ = inception.inception_v3(processed_images,
num_classes=dataset.num_classes,
is_training=False)
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:
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))
plt.axis('off')
plt.show()
names = dataset.labels_to_names
for i in range(dataset.num_classes):
index = sorted_inds[i]
print('Probability %0.2f%% => [%s]' %
(probabilities[index], names[index + 1]))
def build_graph():
images_ph = tf.placeholder(tf.float32, shape=[None, 299, 299, 3])
labels_ph = tf.placeholder(tf.int32, shape=[
None,
])
with slim.arg_scope(inception.inception_v3_arg_scope()):
l, _ = inception.inception_v3(images_ph,
num_classes=2,
is_training=False,
reuse=False,
scope="crack/InceptionV3")
# Construct the scalar neuron tensor.
logits = tf.get_default_graph().get_tensor_by_name(
'crack/InceptionV3/Logits/SpatialSqueeze:0')
neuron_selector = tf.placeholder(tf.int32)
y = logits[0][neuron_selector]
# Construct tensor for predictions.
prediction = tf.argmax(logits, 1)
probs = tf.nn.softmax(l)
return images_ph, prediction, probs, y, neuron_selector
def testBuildEndPoints(self):
batch_size = 5
height, width = 299, 299
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
_, end_points = inception.inception_v3(inputs, num_classes)
self.assertTrue('Logits' in end_points)
logits = end_points['Logits']
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertTrue('AuxLogits' in end_points)
aux_logits = end_points['AuxLogits']
self.assertListEqual(aux_logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertTrue('Mixed_7c' in end_points)
pre_pool = end_points['Mixed_7c']
self.assertListEqual(pre_pool.get_shape().as_list(),
[batch_size, 8, 8, 2048])
self.assertTrue('PreLogits' in end_points)
pre_logits = end_points['PreLogits']
self.assertListEqual(pre_logits.get_shape().as_list(),
[batch_size, 1, 1, 2048])
def testBuildEndPoints(self):
batch_size = 5
height, width = 299, 299
num_classes = 1000
inputs = tf.random.uniform((batch_size, height, width, 3))
_, end_points = inception.inception_v3(inputs, num_classes)
self.assertTrue('Logits' in end_points)
logits = end_points['Logits']
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertTrue('AuxLogits' in end_points)
aux_logits = end_points['AuxLogits']
self.assertListEqual(aux_logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertTrue('Mixed_7c' in end_points)
pre_pool = end_points['Mixed_7c']
self.assertListEqual(pre_pool.get_shape().as_list(),
[batch_size, 8, 8, 2048])
self.assertTrue('PreLogits' in end_points)
pre_logits = end_points['PreLogits']
self.assertListEqual(pre_logits.get_shape().as_list(),
[batch_size, 1, 1, 2048])
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 create(self, images, num_classes, is_training):
"""See baseclass."""
with slim.arg_scope(inception.inception_v3_arg_scope()):
_, endpoints = inception.inception_v3(
images, num_classes, create_aux_logits=False, is_training=is_training)
return endpoints
print('Start to read images!')
image_list = get_test_images(test_path)
processed_images = tf.placeholder(tf.float32,
shape=(None, image_size, image_size, 3))
if deep_lerning_architecture == "v1" or deep_lerning_architecture == "V1":
with slim.arg_scope(inception.inception_v1_arg_scope()):
logits, _ = inception.inception_v1(processed_images,
num_classes=nb_classes,
is_training=False)
else:
if deep_lerning_architecture == "v3" or deep_lerning_architecture == "V3":
with slim.arg_scope(inception.inception_v3_arg_scope()):
logits, _ = inception.inception_v3(processed_images,
num_classes=nb_classes,
is_training=False)
else:
if deep_lerning_architecture == "resv2" or deep_lerning_architecture == "inception_resnet2":
with slim.arg_scope(inception.inception_resnet_v2_arg_scope()):
logits, _ = inception.inception_resnet_v2(
processed_images,
num_classes=nb_classes,
is_training=False)
def predict_fn(images):
return session.run(probabilities, feed_dict={processed_images: images})
probabilities = tf.nn.softmax(logits)
checkpoint_path = tf.train.latest_checkpoint(train_dir)
init_fn = slim.assign_from_checkpoint_fn(checkpoint_path,
def nestedClassification(img_paths):
checkpoints_path = '/home/mehdi/Desktop/1.Projects/1.Image_Processing/1_.classification/inception_v3/all'
fileName = "../Project_Data/labels.txt"
names = []
crimefile = open(fileName, 'r')
for line in crimefile.readlines():
if line.strip():
names.append(line.strip().split(":")[-1])
BATCH_SIZE=FLAGS.Batch_Size
############################################################################
number_of_inputImage=len(img_paths)
if BATCH_SIZE>=number_of_inputImage:
batch_size=number_of_inputImage
else:
batch_size=BATCH_SIZE
NUM_CLASSES = len(names)
image_size=inception.inception_v3.default_image_size
repeat_count=2
checkpoints_path = tf.train.latest_checkpoint(checkpoints_path)
X = tf.placeholder(tf.float32, [batch_size, image_size, image_size, 3])
with slim.arg_scope(inception.inception_v3_arg_scope()):
model,_ = inception.inception_v3(X, num_classes = NUM_CLASSES, is_training = False)
probabilities = tf.nn.softmax(model)
init = slim.assign_from_checkpoint_fn(checkpoints_path,slim.get_model_variables('InceptionV3'))
def input_parser(img_path):
# # read the img from file
img_file = tf.read_file(img_path)
img_decoded = tf.image.decode_png(img_file,channels=3)
img_decoded=tf.image.convert_image_dtype(img_decoded,dtype=tf.float32)
processed_image = inception_preprocessing.preprocess_image(img_decoded, image_size, image_size,
is_training=False)
return processed_image
data=tf.data.Dataset.from_tensor_slices(img_paths)
print("===imaPath",img_paths)
data = data.map(input_parser, num_parallel_calls=1)
data= data.repeat(repeat_count) # Repeats dataset this # times
data = data.batch(batch_size)
# data= data.repeat(repeat_count) # Repeats dataset this # times
iterator=data.make_initializable_iterator()
next_batch = iterator.get_next()
test_init_op = iterator.make_initializer(data)
with tf.Session() as sess:
init(sess)
sess.run(test_init_op)
#
j = 0
k=0
epoch=int(number_of_inputImage/batch_size)
for i in range(epoch+1):
img_batch=(sess.run(next_batch))
probabilities1 = sess.run(probabilities, feed_dict={X: img_batch})
for prediction in range((probabilities1.shape)[0]): # batch_size
if j<number_of_inputImage:
print(img_paths[j])
j += 1
batchPredResult = probabilities1[prediction, 0:]
sorted_inds = [i[0] for i in sorted(enumerate(-batchPredResult), key=lambda x: x[1])]
for i in range(1):
index = sorted_inds[i]
print('Probability %0.4f => [%s]' % (batchPredResult[index], names[index]))
