def test_network(img_path, label_path):
x = tf.placeholder("float", shape=[None, 224, 224, 3], name='input')
xscale = tf.subtract(tf.multiply(tf.div(x, 255.0), 2), 1.0)
with slim.arg_scope(inception_v1.inception_v1_arg_scope()):
logits, end_points = inception_v1.inception_v1(xscale,
num_classes=1001,
dropout_keep_prob=1.0,
is_training=False)
predictions = tf.nn.softmax(logits, name="output")
saver = tf.train.Saver()
with tf.Session() as sess:
saver.restore(sess, "inception_v1.ckpt")
#ckpt_info("inception_v1.ckpt")
#var_list = tf.global_variables()
#print(var_list)
constant_graph = tf.get_default_graph().as_graph_def()
output_graph_def = graph_util.convert_variables_to_constants(
sess, constant_graph, ['output'])
with tf.gfile.GFile("inception_v1.pb", "wb") as f:
f.write(output_graph_def.SerializeToString())
imgfloat = tf.cast(tf.image.decode_jpeg(tf.read_file(img_path),
channels=3),
dtype=tf.float32)
img = tf.image.resize_images(tf.expand_dims(imgfloat, 0), (224, 224),
method=0)
predictions_val = predictions.eval(feed_dict={x: img.eval()})
predicted_classes = np.argmax(predictions_val, axis=1)
file = open(label_path)
labels = file.readlines()
print(predicted_classes, labels[predicted_classes[0]])
def test_network(img_path, label_path):
x = tf.placeholder("float", shape=[None, 224, 224, 3], name='input')
with slim.arg_scope(inception_v1.inception_v1_arg_scope()):
logits, end_points = inception_v1.inception_v1(x,
num_classes=1001,
dropout_keep_prob=1.0,
is_training=False)
predictions = end_points["Predictions"]
saver = tf.train.Saver()
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
saver.restore(sess, "inception_v1.ckpt")
imgfloat = tf.cast(tf.image.decode_jpeg(tf.read_file(img_path),
channels=3),
dtype=tf.float32)
img = tf.subtract(
tf.multiply(
tf.div(
tf.image.resize_images(tf.expand_dims(imgfloat, 0),
(224, 224),
method=0), 255.0), 2), 1.0)
predictions_val = predictions.eval(feed_dict={x: img.eval()})
predicted_classes = np.argmax(predictions_val, axis=1)
file = open(label_path)
labels = file.readlines()
print(predicted_classes, labels[predicted_classes[0]])
def testModelHasExpectedNumberOfParameters(self):
batch_size = 5
height, width = 224, 224
inputs = random_ops.random_uniform((batch_size, height, width, 3))
with arg_scope(inception_v1.inception_v1_arg_scope()):
inception_v1.inception_v1_base(inputs)
total_params, _ = model_analyzer.analyze_vars(
variables_lib.get_model_variables())
self.assertAlmostEqual(5607184, total_params)
def testModelHasExpectedNumberOfParameters(self):
batch_size = 5
height, width = 224, 224
inputs = random_ops.random_uniform((batch_size, height, width, 3))
with arg_scope(inception_v1.inception_v1_arg_scope()):
inception_v1.inception_v1_base(inputs)
total_params, _ = model_analyzer.analyze_vars(
variables_lib.get_model_variables())
self.assertAlmostEqual(5607184, total_params)
def create_inception(image_input,
is_training,
scope="",
inception_out="Mixed_5c",
resnet_version=50,
cbn=None):
"""
Create a resnet by overidding the classic batchnorm with conditional batchnorm
:param image_input: placeholder with image
:param is_training: are you using the resnet at training_time or test_time
:param scope: tensorflow scope
:param resnet_version: 50/101/152
:param cbn: the cbn factory
:return: the resnet output
"""
# assert False, "\n" \
# "There is a bug with classic batchnorm with slim networks (https://github.com/tensorflow/tensorflow/issues/4887). \n" \
# "Please use the following config -> 'cbn': {'use_cbn':true, 'excluded_scope_names': ['*']}"
# arg_sc = slim_utils.resnet_arg_scope(is_training=is_training)
# print("--- 1")
arg_sc = inception_v1.inception_v1_arg_scope()
# Pick the correct version of the resnet
# if resnet_version == 50:
# current_resnet = resnet_v1.resnet_v1_50
# elif resnet_version == 101:
# current_resnet = resnet_v1.resnet_v1_101
# elif resnet_version == 152:
# current_resnet = resnet_v1.resnet_v1_152
# else:
# raise ValueError("Unsupported resnet version")
# inception_scope = os.path.join('InceptionV1/InceptionV1', inception_out)
# print("--- 2")
inception_scope = inception_out
# print(" resnet_out = {} , resnet_scope = {}".format(resnet_out,resnet_scope))
# print("--- 3")
with slim.arg_scope(arg_sc):
net, end_points = inception_v1.inception_v1(
image_input, 1001) # 1000 is the number of softmax class
print("Net = ", net)
# print("--- 4")
if len(scope) > 0 and not scope.endswith("/"):
scope += "/"
# print("--- 5")
# print(end_points)
print(" Batch ", inception_scope)
out = end_points[scope + inception_scope]
print("-- out Use: {},output = {}".format(inception_scope, out))
return out, end_points
def test_network():
x = tf.placeholder("float", shape=[None, 224, 224, 3], name='input')
with slim.arg_scope(inception_v1.inception_v1_arg_scope()):
logits, end_points = inception_v1.inception_v1(x,
num_classes=2,
dropout_keep_prob=1.0,
is_training=False)
predictions = end_points["Predictions"]
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
saver.restore(sess, "train.ckpt")
path = './picture/'
w = 224
h = 224
c = 3
cate = [path + x for x in os.listdir(path) if os.path.isdir(path + x)]
imgs = []
labels = []
for idx, folder in enumerate(cate):
for im in glob.glob(folder + '/*.jpg'):
print('reading the image: %s' % (im))
img = io.imread(im)
img = transform.resize(img, (w, h, c))
imgs.append(img)
labels.append([1, 0] if idx == 0 else [0, 1])
break
break
data = np.asarray(imgs, np.float32)
label = np.asarray(labels, np.int32)
predictions_val = predictions.eval(feed_dict={x: data})
print(predictions_val)
excluded = True
break
if not excluded:
variables_to_restore.append(var)
return slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'inception_v1.ckpt'),
variables_to_restore)
x = tf.placeholder(tf.float32, shape=[None, 224, 224, 3])
y_ = tf.placeholder(tf.int32, shape=[
None,
], name='y_')
net_in = tl.layers.InputLayer(x, name='input_layer')
with slim.arg_scope(inception_v1_arg_scope()):
network = tl.layers.SlimNetsLayer(
layer=net_in,
slim_layer=inception_v1,
slim_args={
'num_classes': 19,
'is_training': True,
'dropout_keep_prob': 0.5,
'prediction_fn': slim.softmax,
'spatial_squeeze': True,
'reuse': None,
'scope': 'InceptionV1'
},
name='InceptionV1' # <-- the name should be the same with the ckpt model
)
def build_graph(self):
with arg_scope(inception_v1.inception_v1_arg_scope()):
#with variable_scope.variable_scope(None, 'InceptionV1', [self.image, 21], reuse=None) as scope:
with arg_scope([layers_lib.batch_norm, layers_lib.dropout],
is_training=True):
logit, endpoints = inception_v1.inception_v1_base(self.image)
net = endpoints['Mixed_3c']
self.feature_map.append(
conv_layer(net, [3, 3, 480, 4 * (class_num + 4)],
[1, 1, 1, 1], 'FeatureMap_1', 'SSD',
self.is_training, self.reuse))
net = endpoints['Mixed_4f']
net = conv_layer(net, [3, 3, 832, 1024], [1, 1, 1, 1], 'conv6',
'SSD', self.is_training, self.reuse)
net = conv_layer(net, [1, 1, 1024, 1024], [1, 1, 1, 1],
'conv7', 'SSD', self.is_training, self.reuse)
self.feature_map.append(
conv_layer(net, [3, 3, 1024, 6 * (class_num + 4)],
[1, 1, 1, 1], 'FeatureMap_2', 'SSD',
self.is_training, self.reuse))
net = conv_layer(net, [1, 1, 1024, 256], [1, 1, 1, 1],
'conv8_1', 'SSD', self.is_training,
self.reuse)
net = conv_layer(net, [3, 3, 256, 512], [1, 2, 2, 1],
'conv8_2', 'SSD', self.is_training,
self.reuse)
self.feature_map.append(
conv_layer(net, [3, 3, 512, 6 * (class_num + 4)],
[1, 1, 1, 1], 'FeatureMap_3', 'SSD',
self.is_training, self.reuse))
net = conv_layer(net, [1, 1, 512, 128], [1, 1, 1, 1],
'conv9_1', 'SSD', self.is_training,
self.reuse)
net = conv_layer(net, [3, 3, 128, 256], [1, 2, 2, 1],
'conv9_2', 'SSD', self.is_training,
self.reuse)
self.feature_map.append(
conv_layer(net, [3, 3, 256, 6 * (class_num + 4)],
[1, 1, 1, 1], 'FeatureMap_4', 'SSD',
self.is_training, self.reuse))
net = conv_layer(net, [1, 1, 256, 128], [1, 1, 1, 1],
'conv10_1', 'SSD', self.is_training,
self.reuse)
net = conv_layer(net, [3, 3, 128, 256], [1, 1, 1, 1],
'conv10_2',
'SSD',
self.is_training,
self.reuse,
padding='VALID')
self.feature_map.append(
conv_layer(net, [3, 3, 256, 6 * (class_num + 4)],
[1, 1, 1, 1], 'FeatureMap_5', 'SSD',
self.is_training, self.reuse))
net = conv_layer(net, [1, 1, 256, 128], [1, 1, 1, 1],
'conv11_1', 'SSD', self.is_training,
self.reuse)
net = conv_layer(net, [3, 3, 128, 256], [1, 1, 1, 1],
'conv11_2',
'SSD',
self.is_training,
self.reuse,
padding='VALID')
self.feature_map.append(
conv_layer(net, [1, 1, 256, 6 * (class_num + 4)],
[1, 1, 1, 1], 'FeatureMap_6', 'SSD',
self.is_training, self.reuse))
excluded = False
for exclusion in exclusions:
if var.op.name.startswith(exclusion):
excluded = True
break
if not excluded:
variables_to_restore.append(var)
return slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'inception_v1.ckpt'),
variables_to_restore)
x = tf.placeholder(tf.float32, shape=[None, 224, 224, 3])
y_ = tf.placeholder(tf.int32, shape=[None, ], name='y_')
net_in = tl.layers.InputLayer(x, name='input_layer')
with slim.arg_scope(inception_v1_arg_scope()):
network = tl.layers.SlimNetsLayer(layer=net_in, slim_layer=inception_v1,
slim_args= {
'num_classes':19,
'is_training':True,
'dropout_keep_prob':0.5,
'prediction_fn':slim.softmax,
'spatial_squeeze':True,
'reuse':None,
'scope':'InceptionV1'
},
name='InceptionV1' # <-- the name should be the same with the ckpt model
)
y = network.outputs
probs = tf.nn.softmax(y)