# 《TensorFlow实战》06 TensorFlow实现经典卷积神经网络
# win10 Tensorflow1.0.1 python3.5.3
# CUDA v8.0 cudnn-8.0-windows10-x64-v5.1
# filename:sz06.02.py # TensorFlow实现VGGNet

# 参考 https://github.com/machrisaa/tensorflow-vgg

from datetime import datetime
import math
import time
import tensorflow as tf

def conv_op(input_op, name, kh, kw, n_out, dh, dw, p):
    n_in = input_op.get_shape()[-1].value

    with tf.name_scope(name) as scope:
        kernel = tf.get_variable(scope + "w",
                                 shape = [kh, kw, n_in, n_out], dtype=tf.float32,
                                 initializer = tf.contrib.layers.xavier_initializer_conv2d())
        conv = tf.nn.conv2d(input_op, kernel, (1, dh, dw, 1), padding='SAME')
        bias_init_val = tf.constant(0.0, shape=[n_out], dtype=tf.float32)
        biases = tf.Variable(bias_init_val, trainable=True, name='b')
        z = tf.nn.bias_add(conv, biases)
        activation = tf.nn.relu(z, name=scope)
        p += [kernel, biases]
        return activation

def fc_op(input_op, name, n_out, p):
    n_in = input_op.get_shape()[-1].value

    with tf.name_scope(name) as scope:
        kernel = tf.get_variable(scope + "w",
                                 shape=[n_in, n_out], dtype=tf.float32,
                                 initializer=tf.contrib.layers.xavier_initializer())
        biases = tf.Variable(tf.constant(0.1, shape=[n_out], dtype=tf.float32), name='b')
        activation = tf.nn.relu_layer(input_op, kernel, biases, name=scope)
        p += [kernel, biases]
        return activation

def mpool_op(input_op, name, kh, kw, dh, dw):
    return tf.nn.max_pool(input_op,
                          ksize=[1, kh, kw, 1],
                          strides=[1, dh, dw, 1],
                          padding='SAME',
                          name=name)

def inference_op(input_op, keep_prob):
    p = []
    conv1_1 = conv_op(input_op, name="conv1_1", kh=3, kw=3, n_out=64, dh=1, dw=1, p=p)
    conv1_2 = conv_op(conv1_1, name="conv1_2", kh=3, kw=3, n_out=64, dh=1, dw=1, p=p)
    pool1 = mpool_op(conv1_2, name="pool1", kh=2, kw=2, dh=2, dw=2)

    conv2_1 = conv_op(pool1, name="conv2_1", kh=3, kw=3, n_out=128, dh=1, dw=1, p=p)
    conv2_2 = conv_op(conv2_1, name="conv2_2", kh=3, kw=3, n_out=128, dh=1, dw=1, p=p)
    pool2 = mpool_op(conv2_2, name="pool2", kh=2, kw=2, dh=2, dw=2)

    conv3_1 = conv_op(pool2, name="conv3_1", kh=3, kw=3, n_out=256, dh=1, dw=1, p=p)
    conv3_2 = conv_op(conv3_1, name="conv3_2", kh=3, kw=3, n_out=256, dh=1, dw=1, p=p)
    conv3_3 = conv_op(conv3_2, name="conv3_3", kh=3, kw=3, n_out=256, dh=1,dw=1, p=p)
    pool3 = mpool_op(conv3_3, name="pool3", kh=2, kw=2, dh=2, dw=2)

    conv4_1 = conv_op(pool3, name="conv4_1", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
    conv4_2 = conv_op(conv4_1, name="conv4_2", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
    conv4_3 = conv_op(conv4_2, name="conv4_3", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
    pool4 = mpool_op(conv4_3, name="pool4", kh=2, kw=2, dh=2, dw=2)

    conv5_1 = conv_op(pool4, name="conv5_1", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
    conv5_2 = conv_op(conv5_1, name="conv5_2", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
    conv5_3 = conv_op(conv5_2, name="conv5_3", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
    pool5 = mpool_op(conv5_3, name="pool5", kh=2, kw=2, dh=2, dw=2)

    shp = pool5.get_shape()
    flattened_shape = shp[1].value * shp[2].value * shp[3].value
    resh1 = tf.reshape(pool5, [-1, flattened_shape], name="resh1")

    fc6 = fc_op(resh1, name="fc6", n_out=4096, p=p)
    fc6_drop = tf.nn.dropout(fc6, keep_prob, name="fc6_drop")
    fc7 = fc_op(fc6_drop, name="fc7", n_out=4096, p=p)
    fc7_drop = tf.nn.dropout(fc7, keep_prob, name="fc7_drop")
    fc8 = fc_op(fc7_drop, name="fc8", n_out=1000, p=p)
    softmax = tf.nn.softmax(fc8)
    predictions = tf.argmax(softmax, 1)
    return predictions, softmax, fc8, p

def time_tensorflow_run(session, target, feed, info_string):
    num_steps_burn_in = 10
    total_duration = 0.0
    total_duration_squared = 0.0
    for i in range(num_batches + num_steps_burn_in):
        start_time = time.time()
        _ = session.run(target, feed_dict=feed)
        duration = time.time() - start_time
        if i >= num_steps_burn_in:
            if not i % 10:
                print('%s: step %d, duration = %.3f' %(datetime.now(), i - num_steps_burn_in, duration))
            total_duration += duration
            total_duration_squared += duration* duration
    mn = total_duration / num_batches
    vr = total_duration_squared / num_batches - mn * mn
    sd = math.sqrt(vr)
    print('%s: %s across %d steps, %.3f +/- %.3f sec / batch' %
          (datetime.now(), info_string, num_batches, mn, sd))

def run_benchmark():
    with tf.Graph().as_default():
        images_size = 224
        images = tf.Variable(tf.random_normal([batch_size, images_size, images_size, 3],
            dtype = tf.float32,
            stddev = 1e-1))
        keep_prob = tf.placeholder(tf.float32)
        predictions, softmax, fc8, p = inference_op(images, keep_prob)
        init = tf.global_variables_initializer()
        sess = tf.Session()
        sess.run(init)
        time_tensorflow_run(sess, predictions, {keep_prob: 1.0}, "Forward")
        objective = tf.nn.l2_loss(fc8)
        grad = tf.gradients(objective, p)
        time_tensorflow_run(sess, grad, {keep_prob: 0.5}, "Forward-backward")

batch_size = 32
num_batches = 100
run_benchmark()
'''
2017-04-13 20:46:38.301421: step 0, duration = 0.876
2017-04-13 20:46:47.062714: step 10, duration = 0.876
2017-04-13 20:46:55.825010: step 20, duration = 0.876
2017-04-13 20:47:04.586824: step 30, duration = 0.876
2017-04-13 20:47:13.350110: step 40, duration = 0.876
2017-04-13 20:47:22.112488: step 50, duration = 0.876
2017-04-13 20:47:30.879796: step 60, duration = 0.876
2017-04-13 20:47:39.645100: step 70, duration = 0.877
2017-04-13 20:47:48.409402: step 80, duration = 0.876
2017-04-13 20:47:57.172700: step 90, duration = 0.876
2017-04-13 20:48:05.061676: Forward across 100 steps, 0.876 +/- 0.000 sec / batch
2017-04-13 20:48:48.393882: step 0, duration = 3.434
2017-04-13 20:49:22.706495: step 10, duration = 3.412
2017-04-13 20:49:57.018747: step 20, duration = 3.432
2017-04-13 20:50:31.359640: step 30, duration = 3.427
2017-04-13 20:51:05.571630: step 40, duration = 3.419
2017-04-13 20:51:39.908891: step 50, duration = 3.459
2017-04-13 20:52:14.316013: step 60, duration = 3.423
2017-04-13 20:52:48.706655: step 70, duration = 3.428
2017-04-13 20:53:23.171285: step 80, duration = 3.455
2017-04-13 20:53:57.729194: step 90, duration = 3.460
2017-04-13 20:54:28.629420: Forward-backward across 100 steps, 3.437 +/- 0.020 sec / batch
'''