def testModelHasExpectedNumberOfParameters(self): batch_size = 5 height, width = 224, 224 inputs = tf.random_uniform((batch_size, height, width, 3)) with slim.arg_scope([slim.conv2d, slim.separable_conv2d], normalizer_fn=slim.batch_norm): mobilenet_v1.mobilenet_v1_base(inputs) total_params, _ = slim.model_analyzer.analyze_vars( slim.get_model_variables()) self.assertAlmostEqual(3217920L, total_params)
def testModelHasExpectedNumberOfParameters(self): batch_size = 5 height, width = 224, 224 inputs = tf.random_uniform((batch_size, height, width, 3)) with slim.arg_scope([slim.conv2d, slim.separable_conv2d], normalizer_fn=slim.batch_norm): mobilenet_v1.mobilenet_v1_base(inputs) total_params, _ = slim.model_analyzer.analyze_vars( slim.get_model_variables()) self.assertAlmostEqual(3217920L, total_params)
def testBuildOnlyUptoFinalEndpoint(self): batch_size = 5 height, width = 224, 224 endpoints = ['Conv2d_0', 'Conv2d_1_depthwise', 'Conv2d_1_pointwise', 'Conv2d_2_depthwise', 'Conv2d_2_pointwise', 'Conv2d_3_depthwise', 'Conv2d_3_pointwise', 'Conv2d_4_depthwise', 'Conv2d_4_pointwise', 'Conv2d_5_depthwise', 'Conv2d_5_pointwise', 'Conv2d_6_depthwise', 'Conv2d_6_pointwise', 'Conv2d_7_depthwise', 'Conv2d_7_pointwise', 'Conv2d_8_depthwise', 'Conv2d_8_pointwise', 'Conv2d_9_depthwise', 'Conv2d_9_pointwise', 'Conv2d_10_depthwise', 'Conv2d_10_pointwise', 'Conv2d_11_depthwise', 'Conv2d_11_pointwise', 'Conv2d_12_depthwise', 'Conv2d_12_pointwise', 'Conv2d_13_depthwise', 'Conv2d_13_pointwise'] for index, endpoint in enumerate(endpoints): with tf.Graph().as_default(): inputs = tf.random_uniform((batch_size, height, width, 3)) out_tensor, end_points = mobilenet_v1.mobilenet_v1_base( inputs, final_endpoint=endpoint) self.assertTrue(out_tensor.op.name.startswith( 'MobilenetV1/' + endpoint)) self.assertItemsEqual(endpoints[:index+1], end_points)
def testBuildAndCheckAllEndPointsApproximateFaceNet(self): batch_size = 5 height, width = 128, 128 inputs = tf.random_uniform((batch_size, height, width, 3)) with slim.arg_scope([slim.conv2d, slim.separable_conv2d], normalizer_fn=slim.batch_norm): _, end_points = mobilenet_v1.mobilenet_v1_base( inputs, final_endpoint='Conv2d_13_pointwise', depth_multiplier=0.75) # For the Conv2d_0 layer FaceNet has depth=16 endpoints_shapes = { 'Conv2d_0': [batch_size, 64, 64, 24], 'Conv2d_1_depthwise': [batch_size, 64, 64, 24], 'Conv2d_1_pointwise': [batch_size, 64, 64, 48], 'Conv2d_2_depthwise': [batch_size, 32, 32, 48], 'Conv2d_2_pointwise': [batch_size, 32, 32, 96], 'Conv2d_3_depthwise': [batch_size, 32, 32, 96], 'Conv2d_3_pointwise': [batch_size, 32, 32, 96], 'Conv2d_4_depthwise': [batch_size, 16, 16, 96], 'Conv2d_4_pointwise': [batch_size, 16, 16, 192], 'Conv2d_5_depthwise': [batch_size, 16, 16, 192], 'Conv2d_5_pointwise': [batch_size, 16, 16, 192], 'Conv2d_6_depthwise': [batch_size, 8, 8, 192], 'Conv2d_6_pointwise': [batch_size, 8, 8, 384], 'Conv2d_7_depthwise': [batch_size, 8, 8, 384], 'Conv2d_7_pointwise': [batch_size, 8, 8, 384], 'Conv2d_8_depthwise': [batch_size, 8, 8, 384], 'Conv2d_8_pointwise': [batch_size, 8, 8, 384], 'Conv2d_9_depthwise': [batch_size, 8, 8, 384], 'Conv2d_9_pointwise': [batch_size, 8, 8, 384], 'Conv2d_10_depthwise': [batch_size, 8, 8, 384], 'Conv2d_10_pointwise': [batch_size, 8, 8, 384], 'Conv2d_11_depthwise': [batch_size, 8, 8, 384], 'Conv2d_11_pointwise': [batch_size, 8, 8, 384], 'Conv2d_12_depthwise': [batch_size, 4, 4, 384], 'Conv2d_12_pointwise': [batch_size, 4, 4, 768], 'Conv2d_13_depthwise': [batch_size, 4, 4, 768], 'Conv2d_13_pointwise': [batch_size, 4, 4, 768] } self.assertItemsEqual(endpoints_shapes.keys(), end_points.keys()) for endpoint_name, expected_shape in endpoints_shapes.iteritems(): self.assertTrue(endpoint_name in end_points) self.assertListEqual( end_points[endpoint_name].get_shape().as_list(), expected_shape)
def testOutputStride8BuildAndCheckAllEndPointsUptoConv2d_13(self): batch_size = 5 height, width = 224, 224 output_stride = 8 inputs = tf.random_uniform((batch_size, height, width, 3)) with slim.arg_scope([slim.conv2d, slim.separable_conv2d], normalizer_fn=slim.batch_norm): _, end_points = mobilenet_v1.mobilenet_v1_base( inputs, output_stride=output_stride, final_endpoint='Conv2d_13_pointwise') endpoints_shapes = { 'Conv2d_0': [batch_size, 112, 112, 32], 'Conv2d_1_depthwise': [batch_size, 112, 112, 32], 'Conv2d_1_pointwise': [batch_size, 112, 112, 64], 'Conv2d_2_depthwise': [batch_size, 56, 56, 64], 'Conv2d_2_pointwise': [batch_size, 56, 56, 128], 'Conv2d_3_depthwise': [batch_size, 56, 56, 128], 'Conv2d_3_pointwise': [batch_size, 56, 56, 128], 'Conv2d_4_depthwise': [batch_size, 28, 28, 128], 'Conv2d_4_pointwise': [batch_size, 28, 28, 256], 'Conv2d_5_depthwise': [batch_size, 28, 28, 256], 'Conv2d_5_pointwise': [batch_size, 28, 28, 256], 'Conv2d_6_depthwise': [batch_size, 28, 28, 256], 'Conv2d_6_pointwise': [batch_size, 28, 28, 512], 'Conv2d_7_depthwise': [batch_size, 28, 28, 512], 'Conv2d_7_pointwise': [batch_size, 28, 28, 512], 'Conv2d_8_depthwise': [batch_size, 28, 28, 512], 'Conv2d_8_pointwise': [batch_size, 28, 28, 512], 'Conv2d_9_depthwise': [batch_size, 28, 28, 512], 'Conv2d_9_pointwise': [batch_size, 28, 28, 512], 'Conv2d_10_depthwise': [batch_size, 28, 28, 512], 'Conv2d_10_pointwise': [batch_size, 28, 28, 512], 'Conv2d_11_depthwise': [batch_size, 28, 28, 512], 'Conv2d_11_pointwise': [batch_size, 28, 28, 512], 'Conv2d_12_depthwise': [batch_size, 28, 28, 512], 'Conv2d_12_pointwise': [batch_size, 28, 28, 1024], 'Conv2d_13_depthwise': [batch_size, 28, 28, 1024], 'Conv2d_13_pointwise': [batch_size, 28, 28, 1024] } self.assertItemsEqual(endpoints_shapes.keys(), end_points.keys()) for endpoint_name, expected_shape in endpoints_shapes.iteritems(): self.assertTrue(endpoint_name in end_points) self.assertListEqual( end_points[endpoint_name].get_shape().as_list(), expected_shape)
def testOutputStride8BuildAndCheckAllEndPointsUptoConv2d_13(self): batch_size = 5 height, width = 224, 224 output_stride = 8 inputs = tf.random_uniform((batch_size, height, width, 3)) with slim.arg_scope([slim.conv2d, slim.separable_conv2d], normalizer_fn=slim.batch_norm): _, end_points = mobilenet_v1.mobilenet_v1_base( inputs, output_stride=output_stride, final_endpoint='Conv2d_13_pointwise') endpoints_shapes = {'Conv2d_0': [batch_size, 112, 112, 32], 'Conv2d_1_depthwise': [batch_size, 112, 112, 32], 'Conv2d_1_pointwise': [batch_size, 112, 112, 64], 'Conv2d_2_depthwise': [batch_size, 56, 56, 64], 'Conv2d_2_pointwise': [batch_size, 56, 56, 128], 'Conv2d_3_depthwise': [batch_size, 56, 56, 128], 'Conv2d_3_pointwise': [batch_size, 56, 56, 128], 'Conv2d_4_depthwise': [batch_size, 28, 28, 128], 'Conv2d_4_pointwise': [batch_size, 28, 28, 256], 'Conv2d_5_depthwise': [batch_size, 28, 28, 256], 'Conv2d_5_pointwise': [batch_size, 28, 28, 256], 'Conv2d_6_depthwise': [batch_size, 28, 28, 256], 'Conv2d_6_pointwise': [batch_size, 28, 28, 512], 'Conv2d_7_depthwise': [batch_size, 28, 28, 512], 'Conv2d_7_pointwise': [batch_size, 28, 28, 512], 'Conv2d_8_depthwise': [batch_size, 28, 28, 512], 'Conv2d_8_pointwise': [batch_size, 28, 28, 512], 'Conv2d_9_depthwise': [batch_size, 28, 28, 512], 'Conv2d_9_pointwise': [batch_size, 28, 28, 512], 'Conv2d_10_depthwise': [batch_size, 28, 28, 512], 'Conv2d_10_pointwise': [batch_size, 28, 28, 512], 'Conv2d_11_depthwise': [batch_size, 28, 28, 512], 'Conv2d_11_pointwise': [batch_size, 28, 28, 512], 'Conv2d_12_depthwise': [batch_size, 28, 28, 512], 'Conv2d_12_pointwise': [batch_size, 28, 28, 1024], 'Conv2d_13_depthwise': [batch_size, 28, 28, 1024], 'Conv2d_13_pointwise': [batch_size, 28, 28, 1024]} self.assertItemsEqual(endpoints_shapes.keys(), end_points.keys()) for endpoint_name, expected_shape in endpoints_shapes.iteritems(): self.assertTrue(endpoint_name in end_points) self.assertListEqual(end_points[endpoint_name].get_shape().as_list(), expected_shape)
def testBuildAndCheckAllEndPointsApproximateFaceNet(self): batch_size = 5 height, width = 128, 128 inputs = tf.random_uniform((batch_size, height, width, 3)) with slim.arg_scope([slim.conv2d, slim.separable_conv2d], normalizer_fn=slim.batch_norm): _, end_points = mobilenet_v1.mobilenet_v1_base( inputs, final_endpoint='Conv2d_13_pointwise', depth_multiplier=0.75) # For the Conv2d_0 layer FaceNet has depth=16 endpoints_shapes = {'Conv2d_0': [batch_size, 64, 64, 24], 'Conv2d_1_depthwise': [batch_size, 64, 64, 24], 'Conv2d_1_pointwise': [batch_size, 64, 64, 48], 'Conv2d_2_depthwise': [batch_size, 32, 32, 48], 'Conv2d_2_pointwise': [batch_size, 32, 32, 96], 'Conv2d_3_depthwise': [batch_size, 32, 32, 96], 'Conv2d_3_pointwise': [batch_size, 32, 32, 96], 'Conv2d_4_depthwise': [batch_size, 16, 16, 96], 'Conv2d_4_pointwise': [batch_size, 16, 16, 192], 'Conv2d_5_depthwise': [batch_size, 16, 16, 192], 'Conv2d_5_pointwise': [batch_size, 16, 16, 192], 'Conv2d_6_depthwise': [batch_size, 8, 8, 192], 'Conv2d_6_pointwise': [batch_size, 8, 8, 384], 'Conv2d_7_depthwise': [batch_size, 8, 8, 384], 'Conv2d_7_pointwise': [batch_size, 8, 8, 384], 'Conv2d_8_depthwise': [batch_size, 8, 8, 384], 'Conv2d_8_pointwise': [batch_size, 8, 8, 384], 'Conv2d_9_depthwise': [batch_size, 8, 8, 384], 'Conv2d_9_pointwise': [batch_size, 8, 8, 384], 'Conv2d_10_depthwise': [batch_size, 8, 8, 384], 'Conv2d_10_pointwise': [batch_size, 8, 8, 384], 'Conv2d_11_depthwise': [batch_size, 8, 8, 384], 'Conv2d_11_pointwise': [batch_size, 8, 8, 384], 'Conv2d_12_depthwise': [batch_size, 4, 4, 384], 'Conv2d_12_pointwise': [batch_size, 4, 4, 768], 'Conv2d_13_depthwise': [batch_size, 4, 4, 768], 'Conv2d_13_pointwise': [batch_size, 4, 4, 768]} self.assertItemsEqual(endpoints_shapes.keys(), end_points.keys()) for endpoint_name, expected_shape in endpoints_shapes.iteritems(): self.assertTrue(endpoint_name in end_points) self.assertListEqual(end_points[endpoint_name].get_shape().as_list(), expected_shape)
def testBuildCustomNetworkUsingConvDefs(self): batch_size = 5 height, width = 224, 224 conv_defs = [ mobilenet_v1.Conv(kernel=[3, 3], stride=2, depth=32), mobilenet_v1.DepthSepConv(kernel=[3, 3], stride=1, depth=64), mobilenet_v1.DepthSepConv(kernel=[3, 3], stride=2, depth=128), mobilenet_v1.DepthSepConv(kernel=[3, 3], stride=1, depth=512) ] inputs = tf.random_uniform((batch_size, height, width, 3)) net, end_points = mobilenet_v1.mobilenet_v1_base( inputs, final_endpoint='Conv2d_3_pointwise', conv_defs=conv_defs) self.assertTrue(net.op.name.startswith('MobilenetV1/Conv2d_3')) self.assertListEqual(net.get_shape().as_list(), [batch_size, 56, 56, 512]) expected_endpoints = ['Conv2d_0', 'Conv2d_1_depthwise', 'Conv2d_1_pointwise', 'Conv2d_2_depthwise', 'Conv2d_2_pointwise', 'Conv2d_3_depthwise', 'Conv2d_3_pointwise'] self.assertItemsEqual(end_points.keys(), expected_endpoints)
def testBuildBaseNetwork(self): batch_size = 5 height, width = 224, 224 inputs = tf.random_uniform((batch_size, height, width, 3)) net, end_points = mobilenet_v1.mobilenet_v1_base(inputs) self.assertTrue(net.op.name.startswith('MobilenetV1/Conv2d_13')) self.assertListEqual(net.get_shape().as_list(), [batch_size, 7, 7, 1024]) expected_endpoints = [ 'Conv2d_0', 'Conv2d_1_depthwise', 'Conv2d_1_pointwise', 'Conv2d_2_depthwise', 'Conv2d_2_pointwise', 'Conv2d_3_depthwise', 'Conv2d_3_pointwise', 'Conv2d_4_depthwise', 'Conv2d_4_pointwise', 'Conv2d_5_depthwise', 'Conv2d_5_pointwise', 'Conv2d_6_depthwise', 'Conv2d_6_pointwise', 'Conv2d_7_depthwise', 'Conv2d_7_pointwise', 'Conv2d_8_depthwise', 'Conv2d_8_pointwise', 'Conv2d_9_depthwise', 'Conv2d_9_pointwise', 'Conv2d_10_depthwise', 'Conv2d_10_pointwise', 'Conv2d_11_depthwise', 'Conv2d_11_pointwise', 'Conv2d_12_depthwise', 'Conv2d_12_pointwise', 'Conv2d_13_depthwise', 'Conv2d_13_pointwise' ] self.assertItemsEqual(end_points.keys(), expected_endpoints)
def testBuildCustomNetworkUsingConvDefs(self): batch_size = 5 height, width = 224, 224 conv_defs = [ mobilenet_v1.Conv(kernel=[3, 3], stride=2, depth=32), mobilenet_v1.DepthSepConv(kernel=[3, 3], stride=1, depth=64), mobilenet_v1.DepthSepConv(kernel=[3, 3], stride=2, depth=128), mobilenet_v1.DepthSepConv(kernel=[3, 3], stride=1, depth=512) ] inputs = tf.random_uniform((batch_size, height, width, 3)) net, end_points = mobilenet_v1.mobilenet_v1_base( inputs, final_endpoint='Conv2d_3_pointwise', conv_defs=conv_defs) self.assertTrue(net.op.name.startswith('MobilenetV1/Conv2d_3')) self.assertListEqual(net.get_shape().as_list(), [batch_size, 56, 56, 512]) expected_endpoints = [ 'Conv2d_0', 'Conv2d_1_depthwise', 'Conv2d_1_pointwise', 'Conv2d_2_depthwise', 'Conv2d_2_pointwise', 'Conv2d_3_depthwise', 'Conv2d_3_pointwise' ] self.assertItemsEqual(end_points.keys(), expected_endpoints)
def testBuildOnlyUptoFinalEndpoint(self): batch_size = 5 height, width = 224, 224 endpoints = [ 'Conv2d_0', 'Conv2d_1_depthwise', 'Conv2d_1_pointwise', 'Conv2d_2_depthwise', 'Conv2d_2_pointwise', 'Conv2d_3_depthwise', 'Conv2d_3_pointwise', 'Conv2d_4_depthwise', 'Conv2d_4_pointwise', 'Conv2d_5_depthwise', 'Conv2d_5_pointwise', 'Conv2d_6_depthwise', 'Conv2d_6_pointwise', 'Conv2d_7_depthwise', 'Conv2d_7_pointwise', 'Conv2d_8_depthwise', 'Conv2d_8_pointwise', 'Conv2d_9_depthwise', 'Conv2d_9_pointwise', 'Conv2d_10_depthwise', 'Conv2d_10_pointwise', 'Conv2d_11_depthwise', 'Conv2d_11_pointwise', 'Conv2d_12_depthwise', 'Conv2d_12_pointwise', 'Conv2d_13_depthwise', 'Conv2d_13_pointwise' ] for index, endpoint in enumerate(endpoints): with tf.Graph().as_default(): inputs = tf.random_uniform((batch_size, height, width, 3)) out_tensor, end_points = mobilenet_v1.mobilenet_v1_base( inputs, final_endpoint=endpoint) self.assertTrue( out_tensor.op.name.startswith('MobilenetV1/' + endpoint)) self.assertItemsEqual(endpoints[:index + 1], end_points)
def testBuildBaseNetwork(self): batch_size = 5 height, width = 224, 224 inputs = tf.random_uniform((batch_size, height, width, 3)) net, end_points = mobilenet_v1.mobilenet_v1_base(inputs) self.assertTrue(net.op.name.startswith('MobilenetV1/Conv2d_13')) self.assertListEqual(net.get_shape().as_list(), [batch_size, 7, 7, 1024]) expected_endpoints = ['Conv2d_0', 'Conv2d_1_depthwise', 'Conv2d_1_pointwise', 'Conv2d_2_depthwise', 'Conv2d_2_pointwise', 'Conv2d_3_depthwise', 'Conv2d_3_pointwise', 'Conv2d_4_depthwise', 'Conv2d_4_pointwise', 'Conv2d_5_depthwise', 'Conv2d_5_pointwise', 'Conv2d_6_depthwise', 'Conv2d_6_pointwise', 'Conv2d_7_depthwise', 'Conv2d_7_pointwise', 'Conv2d_8_depthwise', 'Conv2d_8_pointwise', 'Conv2d_9_depthwise', 'Conv2d_9_pointwise', 'Conv2d_10_depthwise', 'Conv2d_10_pointwise', 'Conv2d_11_depthwise', 'Conv2d_11_pointwise', 'Conv2d_12_depthwise', 'Conv2d_12_pointwise', 'Conv2d_13_depthwise', 'Conv2d_13_pointwise'] self.assertItemsEqual(end_points.keys(), expected_endpoints)