Visualizing and Understanding Convolutional Networks

代码请见:https://github.com/amir-saniyan/ZFNet

 # Input: 224x224x3.
        with tf.name_scope('input'):
            self.X = tf.placeholder(dtype=tf.float32,
                                    shape=[None, self.input_height, self.input_width, self.input_channels], name='X')

        # Labels: 1000.
        with tf.name_scope('labels'):
            self.Y = tf.placeholder(dtype=tf.float32, shape=[None, self.num_classes], name='Y')

        # Dropout keep prob.
        with tf.name_scope('dropout'):
            self.dropout_keep_prob = tf.placeholder(dtype=tf.float32, shape=(), name='dropout_keep_prob')

        # Layer 1.
        # [Input] ==> 224x224x3
        # --> 224x224x3 ==> [Convolution: size=(7x7x3)x96, strides=2, padding=valid] ==> 110x110x96
        # --> 110x110x96 ==> [ReLU] ==> 110x110x96
        # --> 110x110x96 ==> [Max-Pool: size=3x3, strides=2, padding=valid] ==> 55x55x96
        # --> [Output] ==> 55x55x96
        # Note: There were some calculation errors in ZFNet architecture:
        # floor((224-7)/2) + 1 = 109
        # floor((110-3)/2) + 1 = 54
        with tf.name_scope('layer1'):
            layer1_activations = self.__conv(input=self.X, filter_width=7, filter_height=7, filters_count=96,
                                             stride_x=2, stride_y=2, padding='VALID')
            layer1_pool = self.__max_pool(input=layer1_activations, filter_width=3, filter_height=3, stride_x=2,
                                          stride_y=2, padding='VALID')

        # Layer 2.
        # [Input] ==> 55x55x96
        # --> 55x55x96 ==> [Convolution: size=(5x5x96)x256, strides=2, padding=valid] ==> 26x26x256
        # --> 26x26x256 ==> [ReLU] ==> 26x26x256
        # --> 26x26x256 ==> [Max-Pool: size=3x3, strides=2, padding=valid] ==> 13x13x256
        # --> [Output] ==> 13x13x256
        # Note: There were some calculation errors in ZFNet architecture:
        # floor((26-3)/2) + 1 = 12
        with tf.name_scope('layer2'):
            layer2_activations = self.__conv(input=layer1_pool, filter_width=5, filter_height=5, filters_count=256,
                                             stride_x=2, stride_y=2, padding='VALID')
            layer2_pool = self.__max_pool(input=layer2_activations, filter_width=3, filter_height=3, stride_x=2,
                                          stride_y=2, padding='VALID')

        # Layer 3.
        # [Input] ==> 13x13x256
        # --> 13x13x256 ==> [Convolution: size=(3x3x256)x384, strides=1, padding=same] ==> 13x13x384
        # --> 13x13x384 ==> [ReLU] ==> 13x13x384
        # --> [Output] ==> 13x13x384
        with tf.name_scope('layer3'):
            layer3_activations = self.__conv(input=layer2_pool, filter_width=3, filter_height=3, filters_count=384,
                                             stride_x=1, stride_y=1, padding='SAME')

        # Layer 4.
        # [Input] ==> 13x13x384
        # --> 13x13x384 ==> [Convolution: size=(3x3x384)x384, strides=1, padding=same] ==> 13x13x384
        # --> 13x13x384 ==> [ReLU] ==> 13x13x384
        # --> [Output] ==> 13x13x384
        with tf.name_scope('layer4'):
            layer4_activations = self.__conv(input=layer3_activations, filter_width=3, filter_height=3,
                                             filters_count=384, stride_x=1, stride_y=1, padding='SAME')

        # Layer 5.
        # [Input] ==> 13x13x384
        # --> 13x13x384 ==> [Convolution: size=(3x3x384)x256, strides=1, padding=same] ==> 13x13x256
        # --> 13x13x256 ==> [ReLU] ==> 13x13x256
        # --> 13x13x256 ==> [Max-Pool: size=3x3, strides=2, padding=valid] ==> 6x6x256
        # --> [Output] ==> 6x6x256
        with tf.name_scope('layer5'):
            layer5_activations = self.__conv(input=layer4_activations, filter_width=3, filter_height=3,
                                             filters_count=256, stride_x=1, stride_y=1, padding='SAME')
            layer5_pool = self.__max_pool(input=layer5_activations, filter_width=3, filter_height=3, stride_x=2,
                                          stride_y=2, padding='VALID')

        # Layer 6.
        # [Input] ==> 6x6x256=9216
        # --> 9216 ==> [Fully Connected: neurons=4096] ==> 4096
        # --> 4096 ==> [ReLU] ==> 4096
        # --> 4096 ==> [Dropout] ==> 4096
        # --> [Output] ==> 4096
        with tf.name_scope('layer6'):
            pool5_shape = layer5_pool.get_shape().as_list()
            flattened_input_size = pool5_shape[1] * pool5_shape[2] * pool5_shape[3]
            layer6_fc = self.__fully_connected(input=tf.reshape(layer5_pool, shape=[-1, flattened_input_size]),
                                               inputs_count=flattened_input_size, outputs_count=4096, relu=True)
            layer6_dropout = self.__dropout(input=layer6_fc)

        # Layer 7.
        # [Input] ==> 4096
        # --> 4096 ==> [Fully Connected: neurons=4096] ==> 4096
        # --> 4096 ==> [ReLU] ==> 4096
        # --> 4096 ==> [Dropout] ==> 4096
        # --> [Output] ==> 4096
        with tf.name_scope('layer7'):
            layer7_fc = self.__fully_connected(input=layer6_dropout, inputs_count=4096, outputs_count=4096, relu=True)
            layer7_dropout = self.__dropout(input=layer7_fc)

        # Layer 8.
        # [Input] ==> 4096
        # --> 4096 ==> [Logits: neurons=1000] ==> 1000
        # --> [Output] ==> 1000
        with tf.name_scope('layer8'):
            layer8_logits = self.__fully_connected(input=layer7_dropout, inputs_count=4096,
                                                   outputs_count=self.num_classes, relu=False, name='logits')