def testMobilenetV3Small(self, use_groupnorm):
_, endpoints = mobilenet_v3.mobilenet(
tf.placeholder(tf.float32, (1, 224, 224, 3)),
conv_defs=mobilenet_v3.V3_SMALL,
use_groupnorm=use_groupnorm)
self.assertEqual(endpoints['layer_15'].shape, [1, 1, 1, 1024])
self.assertVariablesHaveNormalizerFn(use_groupnorm)
def testMobilenetV3Large(self, use_groupnorm):
logits, endpoints = mobilenet_v3.mobilenet(
tf.placeholder(tf.float32, (1, 224, 224, 3)),
use_groupnorm=use_groupnorm)
self.assertEqual(endpoints['layer_19'].shape, [1, 1, 1, 1280])
self.assertEqual(logits.shape, [1, 1001])
self.assertVariablesHaveNormalizerFn(use_groupnorm)
def testMobilenetV3WithOutReduceMean(self):
_, _ = mobilenet_v3.mobilenet(tf.compat.v1.placeholder(
tf.float32, (1, 224, 224, 3)),
conv_defs=mobilenet_v3.V3_SMALL,
use_reduce_mean_for_pooling=False)
g = tf.get_default_graph()
reduce_mean = [v for v in g.get_operations() if 'ReduceMean' in v.name]
self.assertEmpty(reduce_mean)
def testMobilenetV3BaseOnly(self):
result, endpoints = mobilenet_v3.mobilenet(
tf.compat.v1.placeholder(tf.float32, (1, 224, 224, 3)),
conv_defs=mobilenet_v3.V3_LARGE,
base_only=True,
final_endpoint='layer_17')
# Get the latest layer before average pool.
self.assertEqual(endpoints['layer_17'].shape, [1, 7, 7, 960])
self.assertEqual(result, endpoints['layer_17'])
def testMobilenetV3BaseOnly_VariableInput(self):
result, endpoints = mobilenet_v3.mobilenet(
tf.placeholder(tf.float32, (None, None, None, 3)),
conv_defs=mobilenet_v3.V3_LARGE,
base_only=True,
final_endpoint='layer_17')
# Get the latest layer before average pool.
self.assertEqual(endpoints['layer_17'].shape.as_list(),
[None, None, None, 960])
self.assertEqual(result, endpoints['layer_17'])
def testMobilenetV3WithOutReduceMean(self, use_groupnorm):
_, _ = mobilenet_v3.mobilenet(
tf.placeholder(tf.float32, (1, 224, 224, 3)),
conv_defs=mobilenet_v3.V3_SMALL,
use_groupnorm=use_groupnorm,
use_reduce_mean_for_pooling=False)
g = tf.get_default_graph()
reduce_mean = [v for v in g.get_operations() if 'ReduceMean' in v.name]
self.assertEmpty(reduce_mean)
self.assertVariablesHaveNormalizerFn(use_groupnorm)
def testMobilenetV3BaseOnly(self, use_groupnorm):
result, endpoints = mobilenet_v3.mobilenet(
tf.placeholder(tf.float32, (1, 224, 224, 3)),
conv_defs=mobilenet_v3.V3_LARGE,
use_groupnorm=use_groupnorm,
base_only=True,
final_endpoint='layer_17')
# Get the latest layer before average pool.
self.assertEqual(endpoints['layer_17'].shape, [1, 7, 7, 960])
self.assertEqual(result, endpoints['layer_17'])
self.assertVariablesHaveNormalizerFn(use_groupnorm)
def testMobilenetV3Small(self):
_, endpoints = mobilenet_v3.mobilenet(tf.compat.v1.placeholder(
tf.float32, (1, 224, 224, 3)),
conv_defs=mobilenet_v3.V3_SMALL)
self.assertEqual(endpoints['layer_15'].shape, [1, 1, 1, 1024])
def testMobilenetV3Large(self):
logits, endpoints = mobilenet_v3.mobilenet(
tf.compat.v1.placeholder(tf.float32, (1, 224, 224, 3)))
self.assertEqual(endpoints['layer_19'].shape, [1, 1, 1, 1280])
self.assertEqual(logits.shape, [1, 1001])
def _mobilenet_v3_large_224(*args, **kwargs):
kwargs['depth_multiplier'] = 1.0
kwargs['conv_defs'] = mobilenet_v3.V3_LARGE
return mobilenet_v3.mobilenet(*args, **kwargs)
def _mobilenet_v3_small_224(*args, **kwargs):
kwargs['depth_multiplier'] = 1.0
kwargs['conv_defs'] = mobilenet_v3.V3_SMALL
return mobilenet_v3.mobilenet(*args, **kwargs)
# 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))
# 测试MobileNetV2,MobileNetV3
# Note: arg_scope is optional for inference.
with tf.contrib.slim.arg_scope(mobilenet_v3.training_scope(is_training=False)):
logits, endpoints = mobilenet_v3.mobilenet(images)
# 测试MobileNetV1
#with tf.contrib.slim.arg_scope(mobilenet_v1.mobilenet_v1_arg_scope(is_training=False)):
#logits, endpoints = mobilenet_v1.mobilenet_v1(images)
# Restore using exponential moving average since it produces (1.5-2%) higher
# accuracy
ema = tf.train.ExponentialMovingAverage(0.999)
vars = ema.variables_to_restore()
saver = tf.train.Saver(vars)
from datasets import imagenet
import os
import time
def testMobilenetV3BaseOnly(self):
result, endpoints = mobilenet_v3.mobilenet(
tf.compat.v1.placeholder(tf.float32, (1, 224, 224, 3)),
conv_defs=mobilenet_v3.V3_LARGE,
base_only=True,
final_endpoint='layer_17')
# Get the latest layer before average pool.
self.assertEqual(endpoints['layer_17'].shape, [1, 7, 7, 960])
self.assertEqual(result, endpoints['layer_17'])
def testMobilenetV3BaseOnly_VariableInput(self):
result, endpoints = mobilenet_v3.mobilenet(
tf.placeholder(tf.float32, (None, None, None, 3)),
conv_defs=mobilenet_v3.V3_LARGE,
base_only=True,
final_endpoint='layer_17')
# Get the latest layer before average pool.
self.assertEqual(endpoints['layer_17'].shape.as_list(),
[None, None, None, 960])
self.assertEqual(result, endpoints['layer_17'])
"""
if __name__ == '__main__':
#absltest.main()
logits, endpoints = mobilenet_v3.mobilenet(
tf.compat.v1.placeholder(tf.float32, (1, 800, 800, 3)))
print(logits)
print(endpoints)
#self.assertEqual(endpoints['layer_19'].shape, [1, 1, 1, 1280])
#self.assertEqual(logits.shape, [1, 1001])