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 testBuildAndCheckAllEndPointsUptoMixed5c(self): batch_size = 5 height, width = 224, 224 inputs = random_ops.random_uniform((batch_size, height, width, 3)) _, end_points = inception_v1.inception_v1_base( inputs, final_endpoint='Mixed_5c') endpoints_shapes = { 'Conv2d_1a_7x7': [5, 112, 112, 64], 'MaxPool_2a_3x3': [5, 56, 56, 64], 'Conv2d_2b_1x1': [5, 56, 56, 64], 'Conv2d_2c_3x3': [5, 56, 56, 192], 'MaxPool_3a_3x3': [5, 28, 28, 192], 'Mixed_3b': [5, 28, 28, 256], 'Mixed_3c': [5, 28, 28, 480], 'MaxPool_4a_3x3': [5, 14, 14, 480], 'Mixed_4b': [5, 14, 14, 512], 'Mixed_4c': [5, 14, 14, 512], 'Mixed_4d': [5, 14, 14, 512], 'Mixed_4e': [5, 14, 14, 528], 'Mixed_4f': [5, 14, 14, 832], 'MaxPool_5a_2x2': [5, 7, 7, 832], 'Mixed_5b': [5, 7, 7, 832], 'Mixed_5c': [5, 7, 7, 1024] } self.assertItemsEqual(endpoints_shapes.keys(), end_points.keys()) for endpoint_name in endpoints_shapes: expected_shape = endpoints_shapes[endpoint_name] self.assertTrue(endpoint_name in end_points) self.assertListEqual(end_points[endpoint_name].get_shape().as_list(), expected_shape)
def testBuildAndCheckAllEndPointsUptoMixed5c(self): batch_size = 5 height, width = 224, 224 inputs = random_ops.random_uniform((batch_size, height, width, 3)) _, end_points = inception_v1.inception_v1_base( inputs, final_endpoint='Mixed_5c') endpoints_shapes = { 'Conv2d_1a_7x7': [5, 112, 112, 64], 'MaxPool_2a_3x3': [5, 56, 56, 64], 'Conv2d_2b_1x1': [5, 56, 56, 64], 'Conv2d_2c_3x3': [5, 56, 56, 192], 'MaxPool_3a_3x3': [5, 28, 28, 192], 'Mixed_3b': [5, 28, 28, 256], 'Mixed_3c': [5, 28, 28, 480], 'MaxPool_4a_3x3': [5, 14, 14, 480], 'Mixed_4b': [5, 14, 14, 512], 'Mixed_4c': [5, 14, 14, 512], 'Mixed_4d': [5, 14, 14, 512], 'Mixed_4e': [5, 14, 14, 528], 'Mixed_4f': [5, 14, 14, 832], 'MaxPool_5a_2x2': [5, 7, 7, 832], 'Mixed_5b': [5, 7, 7, 832], 'Mixed_5c': [5, 7, 7, 1024] } self.assertItemsEqual(endpoints_shapes.keys(), end_points.keys()) for endpoint_name in endpoints_shapes: expected_shape = endpoints_shapes[endpoint_name] self.assertTrue(endpoint_name in end_points) self.assertListEqual( end_points[endpoint_name].get_shape().as_list(), expected_shape)
def testHalfSizeImages(self): batch_size = 5 height, width = 112, 112 inputs = random_ops.random_uniform((batch_size, height, width, 3)) mixed_5c, _ = inception_v1.inception_v1_base(inputs) self.assertTrue(mixed_5c.op.name.startswith('InceptionV1/Mixed_5c')) self.assertListEqual(mixed_5c.get_shape().as_list(), [batch_size, 4, 4, 1024])
def testHalfSizeImages(self): batch_size = 5 height, width = 112, 112 inputs = random_ops.random_uniform((batch_size, height, width, 3)) mixed_5c, _ = inception_v1.inception_v1_base(inputs) self.assertTrue(mixed_5c.op.name.startswith('InceptionV1/Mixed_5c')) self.assertListEqual(mixed_5c.get_shape().as_list(), [batch_size, 4, 4, 1024])
def inception(): image = tf.placeholder(tf.float32, [None, 224, 224, 3], 'image') with slim.arg_scope(inception_arg_scope(is_training=False)): with variable_scope.variable_scope( 'InceptionV1', 'InceptionV1', [image, 1000], reuse=None) as scope: with arg_scope( [layers_lib.batch_norm, layers_lib.dropout], is_training=False): net, end_points = inception_v1_base(image, scope=scope) with variable_scope.variable_scope('Logits'): net_conv = layers_lib.avg_pool2d( net, [7, 7], stride=1, scope='MaxPool_0a_7x7') print(net_conv.shape) return net_conv, image
def testBuildBaseNetwork(self): batch_size = 5 height, width = 224, 224 inputs = random_ops.random_uniform((batch_size, height, width, 3)) mixed_6c, end_points = inception_v1.inception_v1_base(inputs) self.assertTrue(mixed_6c.op.name.startswith('InceptionV1/Mixed_5c')) self.assertListEqual(mixed_6c.get_shape().as_list(), [batch_size, 7, 7, 1024]) expected_endpoints = [ 'Conv2d_1a_7x7', 'MaxPool_2a_3x3', 'Conv2d_2b_1x1', 'Conv2d_2c_3x3', 'MaxPool_3a_3x3', 'Mixed_3b', 'Mixed_3c', 'MaxPool_4a_3x3', 'Mixed_4b', 'Mixed_4c', 'Mixed_4d', 'Mixed_4e', 'Mixed_4f', 'MaxPool_5a_2x2', 'Mixed_5b', 'Mixed_5c' ] self.assertItemsEqual(end_points.keys(), expected_endpoints)
def testBuildBaseNetwork(self): batch_size = 5 height, width = 224, 224 inputs = random_ops.random_uniform((batch_size, height, width, 3)) mixed_6c, end_points = inception_v1.inception_v1_base(inputs) self.assertTrue(mixed_6c.op.name.startswith('InceptionV1/Mixed_5c')) self.assertListEqual(mixed_6c.get_shape().as_list(), [batch_size, 7, 7, 1024]) expected_endpoints = [ 'Conv2d_1a_7x7', 'MaxPool_2a_3x3', 'Conv2d_2b_1x1', 'Conv2d_2c_3x3', 'MaxPool_3a_3x3', 'Mixed_3b', 'Mixed_3c', 'MaxPool_4a_3x3', 'Mixed_4b', 'Mixed_4c', 'Mixed_4d', 'Mixed_4e', 'Mixed_4f', 'MaxPool_5a_2x2', 'Mixed_5b', 'Mixed_5c' ] self.assertItemsEqual(end_points.keys(), expected_endpoints)
def testBuildOnlyUptoFinalEndpoint(self): batch_size = 5 height, width = 224, 224 endpoints = [ 'Conv2d_1a_7x7', 'MaxPool_2a_3x3', 'Conv2d_2b_1x1', 'Conv2d_2c_3x3', 'MaxPool_3a_3x3', 'Mixed_3b', 'Mixed_3c', 'MaxPool_4a_3x3', 'Mixed_4b', 'Mixed_4c', 'Mixed_4d', 'Mixed_4e', 'Mixed_4f', 'MaxPool_5a_2x2', 'Mixed_5b', 'Mixed_5c' ] for index, endpoint in enumerate(endpoints): with ops.Graph().as_default(): inputs = random_ops.random_uniform((batch_size, height, width, 3)) out_tensor, end_points = inception_v1.inception_v1_base( inputs, final_endpoint=endpoint) self.assertTrue( out_tensor.op.name.startswith('InceptionV1/' + endpoint)) self.assertItemsEqual(endpoints[:index + 1], end_points)
def testBuildOnlyUptoFinalEndpoint(self): batch_size = 5 height, width = 224, 224 endpoints = [ 'Conv2d_1a_7x7', 'MaxPool_2a_3x3', 'Conv2d_2b_1x1', 'Conv2d_2c_3x3', 'MaxPool_3a_3x3', 'Mixed_3b', 'Mixed_3c', 'MaxPool_4a_3x3', 'Mixed_4b', 'Mixed_4c', 'Mixed_4d', 'Mixed_4e', 'Mixed_4f', 'MaxPool_5a_2x2', 'Mixed_5b', 'Mixed_5c' ] for index, endpoint in enumerate(endpoints): with ops.Graph().as_default(): inputs = random_ops.random_uniform( (batch_size, height, width, 3)) out_tensor, end_points = inception_v1.inception_v1_base( inputs, final_endpoint=endpoint) self.assertTrue( out_tensor.op.name.startswith('InceptionV1/' + endpoint)) self.assertItemsEqual(endpoints[:index + 1], end_points)
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))