def testMobilenetBase(self):
tf.reset_default_graph()
# Verifies that mobilenet_base returns pre-pooling layer.
model = MobilenetV2(depth_multiplier=0.1, min_depth=32)
net, _ = model.forward_base(
tf.placeholder(tf.float32, (10, 224, 224, 16)))
self.assertEqual(net.get_shape().as_list(), [10, 7, 7, 128])
def testDivisibleByWithMultiplier(self):
tf.reset_default_graph()
model = MobilenetV2(depth_multiplier=0.1, min_depth=32)
net, _ = model.forward(tf.placeholder(tf.float32, (10, 224, 224, 16)))
s = [
op.outputs[0].get_shape().as_list()[-1]
for op in find_ops('Conv2D')
]
s = sorted(np.unique(s))
self.assertAllEqual(sorted([32, 192, 128, 1001]), s)
def testDivisibleBy(self):
tf.reset_default_graph()
model = MobilenetV2(divisible_by=16, min_depth=32)
net, _ = model.forward(tf.placeholder(tf.float32, (10, 224, 224, 16)))
s = [
op.outputs[0].get_shape().as_list()[-1]
for op in find_ops('Conv2D')
]
s = sorted(np.unique(s))
self.assertAllEqual(
[32, 64, 96, 160, 192, 320, 384, 576, 960, 1001, 1280], s)
def testImageSizes(self):
model = MobilenetV2()
for input_size, output_size in [(224, 7), (192, 6), (160, 5), (128, 4),
(96, 3)]:
tf.reset_default_graph()
net, endpoints = model.forward(
tf.placeholder(tf.float32, (10, input_size, input_size, 16)))
self.assertEqual(
endpoints['layer_18/output'].get_shape().as_list()[1:3],
[output_size] * 2)
def main(unused_argv):
tf.reset_default_graph()
# For simplicity we just decode jpeg inside tensorflow.
# But one can provide any input obviously.
file_input = tf.placeholder(tf.string, ())
image = tf.image.decode_jpeg(tf.read_file(file_input))
images = tf.expand_dims(image, 0)
images = tf.cast(images, tf.float32) / 128. - 1
images.set_shape((None, None, None, 3))
images = tf.image.resize_images(images, (224, 224))
mobilenet_model = MobilenetV2()
logits, endpoints = mobilenet_model.forward(
images,
is_training=False)
exclude = ['global_step']
variables_to_restore = tf.contrib.slim.get_variables_to_restore(
exclude=exclude)
variables_map = {}
for v in variables_to_restore:
# print(v.name)
old_name = v.name.split(':')[0]
old_name = old_name.replace('conv2d/kernel', 'weights')
old_name = old_name.replace('conv2d/bias', 'biases')
variables_map[old_name] = v
tf.train.init_from_checkpoint(FLAGS.pretrained_model_dir,
variables_map)
# download panda sample image
#filename, _ = urllib.urlretrieve(
# 'https://upload.wikimedia.org/wikipedia/commons/f/fe/Giant_Panda_in_Beijing_Zoo_1.JPG') # noqa
filename = '/home/work/liuqi/datasets/imagenet/validation/ILSVRC2012_val_00000001.JPEG'
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
x = endpoints['Predictions'].eval(
feed_dict={file_input: filename})
if not os.path.exists(FLAGS.output_dir):
os.makedirs(FLAGS.output_dir)
saver.save(sess, FLAGS.output_dir + '/mobilenet-v2-224.ckpt')
# validation
label_map = create_readable_names_for_imagenet_labels()
# output: ('Top 1 prediction: ', 389, 'giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca', 0.83625776) # noqa
print("Top 1 prediction: ", x.argmax(), label_map[x.argmax()], x.max())
def testCreation(self):
model = MobilenetV2()
net, endpoints = model.forward(
tf.placeholder(tf.float32, (10, 224, 224, 16)))
# for t in net.graph.get_operations():
# print(t.name)
spec = model.model_def()
num_convs = len(find_ops('Conv2D'))
# This is mostly a sanity test. No deep reason for these particular
# constants.
#
# All but first 2 and last one have two convolutions, and there is one
# extra conv that is not in the spec. (logits)
self.assertEqual(num_convs, len(spec['spec']) * 2 - 3 + 1)
# Check that depthwise are exposed.
for i in range(2, 17):
self.assertIn('layer_%d/depthwise_output' % i, endpoints)
def encode(self,
input_tensor,
is_training=True):
# extract features
if self.backbone == 'MobilenetV2':
mobilenet_model = MobilenetV2(
self.output_stride,
self.depth_multiplier,
min_depth=8 if self.depth_multiplier == 1.0 else 1,
divisible_by=8 if self.depth_multiplier == 1.0 else 1,
quant_friendly=self.quant_friendly)
else: # MobilenetV3
mobilenet_model = MobilenetV3(
output_stride=self.output_stride,
quant_friendly=self.quant_friendly)
features, endpoints = mobilenet_model.forward_base(
input_tensor,
BACKBONE_INFO[self.backbone]['final_endpoint'],
is_training=is_training)
# add extra losses
self.losses_list.extend(mobilenet_model.losses())
if self.pretrained_backbone_model_dir and is_training:
base_architecture = self.backbone
exclude = [base_architecture + '/Logits', 'global_step']
variables_to_restore = tf.contrib.slim.get_variables_to_restore(
exclude=exclude)
tf.logging.info('init from %s model' % base_architecture)
tf.train.init_from_checkpoint(self.pretrained_backbone_model_dir,
{v.name.split(':')[0]: v for v in
variables_to_restore})
features = self._atrous_spatial_pyramid_pooling(
features, weight_decay=self.weight_decay, is_training=is_training)
return features, endpoints
def testWithOutputStride8(self):
model = MobilenetV2(output_stride=8)
net, _ = model.forward_base(
tf.placeholder(tf.float32, (10, 224, 224, 16)))
self.assertEqual(net.get_shape().as_list()[1:3], [28, 28])
def testCreationNoClasses(self):
model = MobilenetV2()
net, endpoints = model.forward(tf.placeholder(tf.float32,
(10, 224, 224, 16)),
num_classes=None)
self.assertIs(net, endpoints['global_pool'])
def testWithOutputStride16(self):
tf.reset_default_graph()
model = MobilenetV2(output_stride=16)
net, _ = model.forward_base(
tf.placeholder(tf.float32, (10, 224, 224, 16)))
self.assertEqual(net.get_shape().as_list()[1:3], [14, 14])