[深度学习] TensorFlow上FCN模型验证

版权声明：博客地址：https://blog.csdn.net/weixin_41028208，未经博主允许不得转载。QQ：335848046。微博：小黑_songrn。 https://blog.csdn.net/weixin_41028208/article/details/83545941

针对 https://blog.csdn.net/weixin_41028208/article/details/81568310 中好多留言，不知道如何用自己的数据验证模型结果，我特意从原程序中摘出来了一个程序，用来验证data_dir中的图片

一个简单的办法，把图片放到valid_images里，然后改成visualize模式

from __future__ import print_function
import tensorflow as tf
import numpy as np
import os
import TensorflowUtils as utils
import read_MITSceneParsingData as scene_parsing
import datetime
import BatchDatsetReader as dataset
from six.moves import xrange
import matplotlib.pyplot as plt
import scipy.misc as misc
import cv2

FLAGS = tf.flags.FLAGS
tf.flags.DEFINE_integer("batch_size", "5", "batch size for training")
tf.flags.DEFINE_string("logs_dir", "logs/", "path to logs directory")
tf.flags.DEFINE_string("data_dir", "data/", "path to dataset")
tf.flags.DEFINE_string("output_dir", "output/", "path to output dir")
tf.flags.DEFINE_float("learning_rate", "1e-4", "Learning rate for Adam Optimizer")
tf.flags.DEFINE_string("model_dir", "model/", "Path to vgg model mat")
tf.flags.DEFINE_bool('debug', "False", "Debug mode: True/ False")

gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=1)

os.environ["CUDA_VISIBLE_DEVICES"] = '1' #use GPU with ID=1  

MODEL_URL = 'http://www.vlfeat.org/matconvnet/models/beta16/imagenet-vgg-verydeep-19.mat'

# 迭代的最大次数
MAX_ITERATION = int(1e5 + 1)
# 分类的个数
NUM_OF_CLASSESS = 151
# 图片尺寸
IMAGE_SIZE = 1000

# vgg_net：根据权重构建VGG网络
def vgg_net(weights, image):
    layers = (
        'conv1_1', 'relu1_1', 'conv1_2', 'relu1_2', 'pool1',
        'conv2_1', 'relu2_1', 'conv2_2', 'relu2_2', 'pool2',
        'conv3_1', 'relu3_1', 'conv3_2', 'relu3_2', 'conv3_3',
        'relu3_3', 'conv3_4', 'relu3_4', 'pool3',
        'conv4_1', 'relu4_1', 'conv4_2', 'relu4_2', 'conv4_3',
        'relu4_3', 'conv4_4', 'relu4_4', 'pool4',
        'conv5_1', 'relu5_1', 'conv5_2', 'relu5_2', 'conv5_3',
        'relu5_3', 'conv5_4', 'relu5_4'
    )

    net = {}
    current = image
    for i, name in enumerate(layers):
        kind = name[:4]
        if kind == 'conv':
            kernels, bias = weights[i][0][0][0][0]
            # matconvnet: weights are [width, height, in_channels, out_channels]
            # tensorflow: weights are [height, width, in_channels, out_channels]
            kernels = utils.get_variable(np.transpose(kernels, (1, 0, 2, 3)), name=name + "_w")
            bias = utils.get_variable(bias.reshape(-1), name=name + "_b")
            current = utils.conv2d_basic(current, kernels, bias)
        elif kind == 'relu':
            current = tf.nn.relu(current, name=name)
            if FLAGS.debug:
                utils.add_activation_summary(current)
        elif kind == 'pool':
            current = utils.avg_pool_2x2(current)
        net[name] = current

    return net

def train(loss_val, var_list):
    optimizer = tf.train.AdamOptimizer(FLAGS.learning_rate)
    grads = optimizer.compute_gradients(loss_val, var_list=var_list)
    if FLAGS.debug:
        # print(len(var_list))
        for grad, var in grads:
            utils.add_gradient_summary(grad, var)
    return optimizer.apply_gradients(grads)

# 定义Semantic segmentation network，使用VGG结构
def inference(image, keep_prob):
    """
    Semantic segmentation network definition
    :param image: input image. Should have values in range 0-255
    :param keep_prob:
    :return:
    """
    print("setting up vgg initialized conv layers ...")
    # download Model，建议提前下好，这样不会重新下载
    model_data = utils.get_model_data(FLAGS.model_dir, MODEL_URL)

    # batch normalization
    mean = model_data['normalization'][0][0][0]
    mean_pixel = np.mean(mean, axis=(0, 1))

    # layers字段，所有的权重都存在这里面
    weights = np.squeeze(model_data['layers'])

    # image - mean_pixel：每一channel的均值
    processed_image = utils.process_image(image, mean_pixel)

    # 以inference为名的命名空间
    with tf.variable_scope("inference"):
        # 构建VGG网络
        image_net = vgg_net(weights, processed_image)
        # 最后一层
        conv_final_layer = image_net["conv5_3"]
        # 最后添加一层2*2的max pool
        pool5 = utils.max_pool_2x2(conv_final_layer)

        # 再加conv6，conv7，conv8三个卷基层，都用的ReLU
        W6 = utils.weight_variable([7, 7, 512, 4096], name="W6")
        b6 = utils.bias_variable([4096], name="b6")
        conv6 = utils.conv2d_basic(pool5, W6, b6)
        relu6 = tf.nn.relu(conv6, name="relu6")
        if FLAGS.debug:
            utils.add_activation_summary(relu6)
        relu_dropout6 = tf.nn.dropout(relu6, keep_prob=keep_prob)

        W7 = utils.weight_variable([1, 1, 4096, 4096], name="W7")
        b7 = utils.bias_variable([4096], name="b7")
        conv7 = utils.conv2d_basic(relu_dropout6, W7, b7)
        relu7 = tf.nn.relu(conv7, name="relu7")
        if FLAGS.debug:
            utils.add_activation_summary(relu7)
        relu_dropout7 = tf.nn.dropout(relu7, keep_prob=keep_prob)

        W8 = utils.weight_variable([1, 1, 4096, NUM_OF_CLASSESS], name="W8")
        b8 = utils.bias_variable([NUM_OF_CLASSESS], name="b8")
        conv8 = utils.conv2d_basic(relu_dropout7, W8, b8)
        # annotation_pred1 = tf.argmax(conv8, dimension=3, name="prediction1")

        # now to upscale to actual image size
        # 进行deconv操作，依次获取前面卷积前的图片大小
        deconv_shape1 = image_net["pool4"].get_shape()
        W_t1 = utils.weight_variable([4, 4, deconv_shape1[3].value, NUM_OF_CLASSESS], name="W_t1")
        b_t1 = utils.bias_variable([deconv_shape1[3].value], name="b_t1")
        conv_t1 = utils.conv2d_transpose_strided(conv8, W_t1, b_t1, output_shape=tf.shape(image_net["pool4"]))
        fuse_1 = tf.add(conv_t1, image_net["pool4"], name="fuse_1")

        deconv_shape2 = image_net["pool3"].get_shape()
        W_t2 = utils.weight_variable([4, 4, deconv_shape2[3].value, deconv_shape1[3].value], name="W_t2")
        b_t2 = utils.bias_variable([deconv_shape2[3].value], name="b_t2")
        conv_t2 = utils.conv2d_transpose_strided(fuse_1, W_t2, b_t2, output_shape=tf.shape(image_net["pool3"]))
        fuse_2 = tf.add(conv_t2, image_net["pool3"], name="fuse_2")

        shape = tf.shape(image)
        deconv_shape3 = tf.stack([shape[0], shape[1], shape[2], NUM_OF_CLASSESS])
        W_t3 = utils.weight_variable([16, 16, NUM_OF_CLASSESS, deconv_shape2[3].value], name="W_t3")
        b_t3 = utils.bias_variable([NUM_OF_CLASSESS], name="b_t3")
        conv_t3 = utils.conv2d_transpose_strided(fuse_2, W_t3, b_t3, output_shape=deconv_shape3, stride=8)

        annotation_pred = tf.argmax(conv_t3, dimension=3, name="prediction")

    return tf.expand_dims(annotation_pred, dim=3), conv_t3

# 主函数
def main(argv=None):
    # placeholder 定义输入，keep_probability隐含层节点保持工作的概率，这是个什么概念？
    keep_probability = tf.placeholder(tf.float32, name="keep_probabilty")
    # 输入图像，3是指channel？
    image = tf.placeholder(tf.float32, shape=[None, IMAGE_SIZE, IMAGE_SIZE, 3], name="input_image")
    # 标注图像，只有1个channel
    annotation = tf.placeholder(tf.int32, shape=[None, IMAGE_SIZE, IMAGE_SIZE, 1], name="annotation")
    # 构建训练模型
    pred_annotation, logits = inference(image, keep_probability)
    tf.summary.image("input_image", image, max_outputs=2)
    tf.summary.image("ground_truth", tf.cast(annotation, tf.uint8), max_outputs=2)
    tf.summary.image("pred_annotation", tf.cast(pred_annotation, tf.uint8), max_outputs=2)
    # loss函数，
    loss = tf.reduce_mean((tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logits, labels=tf.squeeze(annotation, squeeze_dims=[3]),name="entropy")))
    loss_summary = tf.summary.scalar("entropy", loss)
    # 优化器
    trainable_var = tf.trainable_variables()
    train_op = train(loss, trainable_var)

    print("Setting up summary op...")
    summary_op = tf.summary.merge_all()

    # 会下载Train和Valid数据
    print("Setting up image reader...")
    train_records = scene_parsing.read_test_dataset(FLAGS.data_dir)
    print("Train Set Size: " + str(len(train_records)))
#     print("Valid Set Size: " + str(len(valid_records)))

    print("Setting up dataset reader")
    image_options = {'resize': True, 'resize_size': IMAGE_SIZE}

    validation_dataset_reader = dataset.BatchDatset(train_records, image_options)

    sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))

    print("Setting up Saver...")
    saver = tf.train.Saver()

    # create two summary writers to show training loss and validation loss in the same graph
    # need to create two folders 'train' and 'validation' inside FLAGS.logs_dir
#     train_writer = tf.summary.FileWriter(FLAGS.logs_dir + '/train', sess.graph)
    validation_writer = tf.summary.FileWriter(FLAGS.logs_dir + '/validation')

    sess.run(tf.global_variables_initializer())
    ckpt = tf.train.get_checkpoint_state(FLAGS.logs_dir)
    if ckpt and ckpt.model_checkpoint_path:
        saver.restore(sess, ckpt.model_checkpoint_path)
        print("Model restored...")

        
    valid_images, valid_annotations = validation_dataset_reader.get_random_batch(FLAGS.batch_size)
    pred = sess.run(pred_annotation, feed_dict={image: valid_images,
                                                keep_probability: 1.0})
    valid_annotations = np.squeeze(valid_annotations, axis=3)
    pred = np.squeeze(pred, axis=3)

    for itr in range(FLAGS.batch_size):
        utils.save_image(valid_images[itr].astype(np.uint8), FLAGS.output_dir, name="inp_" + str(5+itr))
        utils.save_image(valid_annotations[itr].astype(np.uint8), FLAGS.output_dir, name="gt_" + str(5+itr))
        utils.save_image(pred[itr].astype(np.uint8), FLAGS.output_dir, name="pred_" + str(5+itr))
        print("Saved image: %d" % itr)

tf.app.run()

setting up vgg initialized conv layers ...
Setting up summary op...
Setting up image reader...
Found pickle file!
Train Set Size: 5
Setting up dataset reader
Initializing Batch Dataset Reader...
{'resize': True, 'resize_size': 1000}
(5, 1000, 1000, 3)
(5, 1000, 1000, 1)
Setting up Saver...
INFO:tensorflow:Restoring parameters from logs/model.ckpt-10000
Model restored...

image = misc.imread("output/inp_6.png")
plt.imshow(image)

image = misc.imread("output/gt_6.png")
plt.imshow(image)

image = misc.imread("output/pred_6.png")
plt.imshow(image)