architecture.py 文件源码

def build_graph(input_tensor, train_flag, start_filter_size, n_anchors, n_classes):
    # preprocessing
    mean = tf.constant(np.load('rgb_mean.npy'), dtype=tf.float32)
    x = (input_tensor - mean) / 255

    with tf.name_scope('Block_1'):
        x = get_block(x, start_filter_size, train_flag, maxpool=True)

    with tf.name_scope('Block_2'):
        x = get_block(x, start_filter_size * 2 ** 1, train_flag, maxpool=True)

    with tf.name_scope('bigBlock_1'):
        x = get_block(x, start_filter_size * 2 ** 2, train_flag)
        x = get_block(x, start_filter_size * 2 ** 1, train_flag, kernel=(1, 1))
        x = get_block(x, start_filter_size * 2 ** 2, train_flag, maxpool=True)

    with tf.name_scope('bigBlock_2'):
        x = get_block(x, start_filter_size * 2 ** 3, train_flag)
        x = get_block(x, start_filter_size * 2 ** 2, train_flag, kernel=(1, 1))
        x = get_block(x, start_filter_size * 2 ** 3, train_flag, maxpool=True)

    with tf.name_scope('doubleBigBlock_1'):
        x = get_block(x, start_filter_size * 2 ** 4, train_flag)
        x = get_block(x, start_filter_size * 2 ** 3, train_flag, kernel=(1, 1))
        x = get_block(x, start_filter_size * 2 ** 4, train_flag)
        x = get_block(x, start_filter_size * 2 ** 3, train_flag, kernel=(1, 1))
        x = get_block(x, start_filter_size * 2 ** 4, train_flag)

    with tf.name_scope('passThrough'):
        y = get_block(x, start_filter_size * 2 ** 1, train_flag)
        y = tf.space_to_depth(y, 2)

    with tf.name_scope('doubleBigBlock_2'):
        x = tf.layers.max_pooling2d(x, (2, 2), (2, 2), padding='same')
        x = get_block(x, start_filter_size * 2 ** 5, train_flag)
        x = get_block(x, start_filter_size * 2 ** 4, train_flag, kernel=(1, 1))
        x = get_block(x, start_filter_size * 2 ** 5, train_flag)
        x = get_block(x, start_filter_size * 2 ** 4, train_flag, kernel=(1, 1))
        x = get_block(x, start_filter_size * 2 ** 5, train_flag)

    with tf.name_scope('Block_3'):
        x = get_block(x, start_filter_size * 2 ** 5, train_flag)

    with tf.name_scope('Block_4'):
        x = get_block(x, start_filter_size * 2 ** 5, train_flag)

    x = tf.concat([x, y], axis=3)

    with tf.name_scope('Block_6'):
        x = get_block(x, start_filter_size * 2 ** 5, train_flag)

    with tf.name_scope('Prediction'):
        x = get_block(x, n_anchors * (n_classes + 5), train_flag, kernel=(1, 1))

    return x