深度原理与框架-图像超分辨重构-tensorlayer

图像超分辨重构的原理，输入一张像素点少，像素较低的图像， 输出一张像素点多，像素较高的图像

而在作者的文章中，作者使用downsample_up, 使用imresize(img, []) 将图像的像素从原理的384，384降低到96， 96, 从而构造出高水平的图像和低水平的图像

作者使用了三个部分构成网络，

第一部分是生成网络，用于进行图片的生成，使用了16层的残差网络，最后的输出结果为tf.nn.tanh(),即为-1, 1, 因为图像进行了-1,1的预处理

第二部分是判别网络， 用于进行图片的判别操作，对于判别网络而言，是希望将生成的图片判别为假，将真的图片判别为真

第三部分是VGG19来提取生成图片和真实图片的conv5层卷积层的输出结果，用于生成局部部位的损失值mse

损失值说明：

d_loss:

d_loss_1: tl.cost.sigmoid_cross_entropy(logits_real, tf.ones_like(logits_real))  # 真实图像的判别结果的损失值

d_loss_2: tl.cost.sigmoid_cross_entrpopy(logits_fake, tf.zeros_like(logits_real)) # 生成图像的判别结果的损失值

g_loss:

g_gan_loss: 1e-3 * tl.cost.sigmoid_cross_entropy(logits_fake, tf.ones_like(logits_real))  # 损失值表示为 -log(D(g(lr))) # 即生成的图像被判别为真的损失值

mse_loss: tl.cost.mean_squared_error(net_g.outputs, t_target_image)  # 计算真实值与生成值之间的像素差

vgg_loss: tl.cost.mean_squared_error(vgg_predict_emb.outputs, vgg_target_emb.outputs) # 用于计算生成图片和真实图片经过vgg19的卷积层后，特征图之间的差异，用来获得特征细节的差异性

训练说明：

首先进行100次迭代，用来优化生成网络，使用tf.train.AdamOptimer(lr_v, beta1=beta1).minimize(mse_loss, var_list=g_var)

等生成网络迭代好以后，开始迭代生成网络和判别网络，以及VGG19的损失值缩小

生成网络：使用了16个残差模块，在残差模块的输入与下一层的输出之间又进行一次残差直连

判别网络：使用的是feature_map递增的卷积层构造成的判别网路

代码说明：

第一步：将参数从config中导入到main.py

第二步：使用tl.file.exists_or_mkdir() 构造用于储存图片的文件夹，同时定义checkpoint的文件夹

第三步：使用sorted(tl.files.load_file_list) 生成图片的列表， 使用tl.vis.read_images() 进行图片的读入

第四步：构建模型的构架Model

第一步：定义输入参数t_image = tf.placeholder('float32', [batch_size, 96, 96, 3]), t_target_image = tf.placeholder('float32', [batch_size, 384, 384, 3])

第二步： 使用SGRAN_g 用来生成最终的生成网络，net_g, 输入参数为t_image, is_training, reuse

第三步： 使用SGRAN_d 用来生成判别网络，输出结果为net_d网络架构，logits_real, 输入参数为t_target_image, is_training, reuse, 同理输入t_image, 获得logits_fake

第四步： 使用net_g.print_params(False) 和 net_g.print_layers() 不打印参数，打印每一层

第五步：将net_g.outputs即生成的结果和t_target_image即目标图像的结果输入到Vgg_19_simple_api, 获得vgg_net, 以及conv第五层的输出结果

第一步：tf.image.resize_images()进行图片的维度变换，为了可以使得其能输入到VGG_19中

第二步：将变化了维度的t_target_image 输入到Vgg_19_simple_api, 获得net_vgg, 和 vgg_target_emb即第五层卷积的输出结果

第三步：将变化了维度的net_g.outputs 输入到Vgg_19_simple_api, 获得 vgg_pred_emb即第五层卷积的输出结果

第六步： 构造net_g_test = SGRAN_g(t_image, False, True) 用于进行训练中的测试图片

第五步：构造模型loss，还有trian_ops操作

第一步： loss的构造， d_loss 和 g_loss的构造

第一步： d_loss的构造， d_loss_1 + d_loss_2

第一步： d_loss_1: 构造真实图片的判别损失值，即tl.cost.softmax_cross_entropy(logits_real, tf.ones_like(logits_real))

第二步： d_loss_2: 构造生成图片的判别损失值， 即tl.cost.softmax_cross_entropy(logits_fake, tf.ones_like(logits_fake))

第二步： g_loss的构造，g_gan_loss, mse_loss, vgg_loss

第一步： g_gan_loss, 生成网络被判别网络判别为真的概率，使用tl.cost.softmax_cross_entropy(logits_fake, tf.ones_like(logits_fake))

第二步：mse_loss 生成图像与目标图像之间的像素点差值，使用tl.cost.mean_squared_error(t_target_image, net_g.outputs)

第三步：vgg_loss  将vgg_target_emb.outputs与vgg_pred_emb.outputs获得第五层卷积层输出的mse_loss

第二步：构造train_op，包括 g_optim_init用预训练, 构造g_optim, d_optim

第一步：g_var = tl.layers.get_variables_with_name(‘SGRAN_g') 生成网络的参数获得

第二步： d_var = tl.layers.get_variable_with_name('SGRAN_d') 判别网络的参数获得

第三步： 使用with tf.variable_scope('learning_rate'): 使用lr_v = tf.Variable(lr_init)

第四步：定义train_op, g_optim_init, g_optim, d_optim

第一步：构造g_optim_init 使用tf.train.Adaoptimer(lr_v, beta1=betal).minimize(mse_loss, var_list=g_var)

第二步：构造g_optim 使用tf.train.Adaoptimer(lr_v, beta1=betal).minimize(g_loss, var_list=g_var)

第三步：构造d_optim 使用tf.train.Adaoptimer(lr_v, beta1=betal).minimize(d_loss, var_list=d_var)

第六步：使用tl.files.load_and_assign_npz() 载入训练好的sess参数

第一步： 使用tf.Session(config=tf.ConfigProto(allow_soft_placement=True, log_device_placement=False))

第二步： tl.layers.initialize_global_variables(sess)

第三步： 使用tf.file.load_and_assign_npz 进行g_net的参数下载， 否者就下载g_{}_init的参数下载

第四步：使用tf.file.load_and_assgin_npz进行d_net的参数下载

第七步：下载VGG网络，将其运用到net_vgg

第一步：使用np.load(path, encoding='latin1').item() 下载参数

第二步：循环sorted(npz.items()) 进行参数循环，将其添加到params

第三步：使用tl.files.assign_params(sess, params, net_vgg) 将参数运用到net_vgg

第八步：进行参数的训练操作

第一步：从图片中跳出一个batch_size的数据构成测试集

第一步： 使用tl.prepro.threading_data fn = crop_sub_imgs_fn， 使用crop进行裁剪操作

第二步： 使用tl.prepro.threading_data fn = downsample 使用imresize进行图片的维度压缩

第二步：进行预训练操作

第一步：循环迭代， 获得一个batch的数据，使用crop_sub_imgs_fn 和 downsample构造低水平的数据和高水平的数据

第二步：使用sess.run， g_optim_init进行图片的预训练

第三步：进行训练操作

第一步：循环迭代，获得一个batch的数据，使用crop_sub_imgs_fn 和 downsample构造低水平的数据和高水平的数据

第二步：使用sess.run, g_optim 和 d_optim 进行图片的训练操作

第九步：进行evaluate图片的测试阶段

第一步： 构造图片展示的文件夹，使用tf.files.exits_files_mkdir

第二步: 使用tl.files.load_file_list 和 tl.vis.read_images读入图片

第三步：根据索引选择一张图片，/127.5 - 1 进行归一化处理

第四步：使用tf.placeholder('float32', [1, None, None, 3]) 构造输入的t_image

第五步： 使用SGRAN_g(t_image, False, False) 构造net_g

第六步：使用tf.Session() 构造sess，使用tl.files.load_and_assign_npz下载训练好的sess， network=net_g

第七步：使用sess.run([net_g.outputs], feed_dict={t_image:[valid_lr_img]}) 获得图片

第八步：使用tl.vis.save_images(outputs[0])保存图片

第九步：使用scipy.misc.imresize() 将低像素的图片扩大为原来的四倍，与重构的图像作对比

代码： main.py  主函数

import tensorlayer as tl
import tensorflow as tf
import numpy as np
from config import config
from model import *
import os
import time
import scipy
 
## 添加参数
batch_size = config.TRAIN.batch_size
lr_init = config.TRAIN.lr_init
betal = config.TRAIN.betal
 
### initialze G
n_epoch_init = config.TRAIN.n_epoch_init
### adversarial learning
n_epoch = config.TRAIN.n_epoch
lr_decay = config.TRAIN.lr_decay
decay_every = config.TRAIN.decay_every
 
ni = int(np.sqrt(batch_size))
 
def train():
 
   # 创建用于进行图片储存的文件
   save_dir_ginit = 'sample/{}_ginit'.format(tl.global_flag['mode'])
   save_dir_gan = 'sample/{}_gan'.format(tl.global_flag['mode'])
   tl.files.exists_or_mkdir(save_dir_ginit)
   tl.files.exists_or_mkdir(save_dir_gan)
   checkpoint = 'checkpoint'
   tl.files.exists_or_mkdir(checkpoint)
 
   train_hr_img_list = sorted(tl.files.load_file_list(path=config.TRAIN.hr_img_path, regx='.*.png', printable=False))
   train_lr_img_list = sorted(tl.files.load_file_list(path=config.TRAIN.lr_img_path, regx='.*.png', printable=False))
 
   train_hr_img = tl.vis.read_images(train_hr_img_list, path=config.TRAIN.hr_img_path, n_threads=8)
   train_lr_img = tl.vis.read_images(train_lr_img_list, path=config.TRAIN.lr_img_path, n_threads=8)
 
   # 构造输入
   t_image = tf.placeholder('float32', [batch_size, 96, 96, 3])
   t_target_image = tf.placeholder('float32', [batch_size, 384, 384, 3])
   # 构造生成的model，获得生成model的输出net_g
   net_g = SRGAN_g(t_image, True, False)
   # 构造判别网络，判别net_g.output, t_target_image, net_d表示整个网络
   net_d, logist_real = SRGAN_d(t_target_image, True, False)
   _, logist_fake = SRGAN_d(net_g.outputs, True, True)
   # 构造VGG网络
 
   net_g.print_params(False)
   net_g.print_layers()
   net_d.print_params(False)
   net_d.print_layers()
 
   # 进行输入数据的维度变换，将其转换为224和224
   target_image_224 = tf.image.resize_images(t_target_image, [224, 224], method=0, align_corners=False)
   pred_image_224 = tf.image.resize_images(net_g.outputs, [224, 224], method=0, align_corners=False)
 
   net_vgg, vgg_target_emb = Vgg_19_simple_api((target_image_224 + 1) / 2, reuse=False)
   _, vgg_pred_emb = Vgg_19_simple_api((net_g + 1) / 2, reuse=True)
   # 进行训练阶段的测试
   net_g_test = SRGAN_g(t_image, False, True)
 
   #### ========== DEFINE_TRAIN_OP =================###
   d_loss_1 = tl.cost.sigmoid_cross_entropy(logist_real, tf.ones_like(logist_real))
   d_loss_2 = tl.cost.sigmoid_cross_entropy(logist_fake, tf.zeros_like(logist_fake))
   d_loss = d_loss_1 + d_loss_2
 
   g_gan_loss = 1e-3 * tl.cost.sigmoid_cross_entropy(logist_fake, tf.ones_like(logist_fake))
   mse_loss = tl.cost.mean_squared_error(net_g.outputs, t_target_image, is_mean=True)
   vgg_loss = 2e-6 * tl.cost.mean_squared_error(vgg_target_emb.outputs, vgg_pred_emb.outputs, is_mean=True)
   g_loss = g_gan_loss + mse_loss + vgg_loss
 
   g_var = tl.layers.get_variables_with_name('SRGAN_g', True, True)
   d_var = tl.layers.get_variables_with_name('SRGAN_d', True, True)
 
   with tf.variable_scope('learning_rate'):
       lr_v = tf.Variable(lr_init, trainable=False)
 
   g_optim_init = tf.train.AdamOptimizer(lr_v, beta1=betal).minimize(mse_loss, var_list=g_var)
   g_optim = tf.train.AdamOptimizer(lr_v, beta1=betal).minimize(g_loss, var_list=g_var)
   d_optim = tf.train.AdamOptimizer(lr_v, beta1=betal).minimize(d_loss, var_list=d_var)
 
   ###======================RESTORE_MODEL_SESS ==================###
   sess = tf.Session(config=tf.ConfigProto(allow_soft_placement=True, log_device_placement=False))
   tl.layers.initialize_global_variables(sess)
   if tl.files.load_and_assign_npz(sess, checkpoint + '/g_{}.npz'.format(tl.global_flag['mode'], network=net_g)) is False:
       tl.files.load_and_assign_npz(sess, checkpoint + '/g_init_{}.npz'.format(tl.global_flag['mode'], network=net_g))
   tl.files.load_and_assign_npz(sess, checkpoint + '/d_{}.npz'.format(tl.global_flag['mode'], network=net_d))
 
   ### ================== load vgg params =================== ###
   vgg_npy_path = 'vgg19.npy'
   if not os.path.isfile(vgg_npy_path):
       print('Please download vgg19.npz from : https://github.com/machrisaa/tensorflow-vgg')
       exit()
 
   npz = np.load(vgg_npy_path, encoding='latin1').item()
   params = []
   for var in sorted(npz.items()):
       W = np.asarray(var[1][0])
       b = np.asarray(var[1][1])
       params.extend([W, b])
 
   tl.files.assign_params(sess, params, net_vgg)
 
   print('ok')
 
   ###======================== TRAIN =======================###
   sample_imgs = train_hr_img[0:batch_size]
   # 进行随机裁剪，保证其维度为384
   sample_imgs_384 = tl.prepro.threading_data(sample_imgs, fn=crop_sub_imgs_fn, is_random=False)
   # 进行像素的降低
   sample_imgs_96 = tl.prepro.threading_data(sample_imgs_384, fn=downsample_fn)
   # 进行图片的保存
   tl.vis.save_images(sample_imgs_96, [ni, ni], save_dir_ginit + '/_train_sample_96.png')
   tl.vis.save_images(sample_imgs_384, [ni, ni], save_dir_ginit + '/_train_sample_384.png')
   tl.vis.save_images(sample_imgs_96, [ni, ni], save_dir_gan + '/_train_sample_96.png')
   tl.vis.save_images(sample_imgs_384, [ni, ni], save_dir_gan + '/_train_sample_384.png')
 
   ###======================== initial train G =====================###
 
   for epoch in range(n_epoch_init):
 
       n_iter = 0
       init_loss_total = 0
 
       for idx in range(0, len(train_hr_img), batch_size):
 
           b_img_384 = tl.prepro.threading_data(train_hr_img[idx:idx+batch_size], fn=crop_sub_imgs_fn, is_random=False)
           b_img_96 = tl.prepro.threading_data(b_img_384, fn=downsample_fn)
 
           _, MSE_LOSS = sess.run([g_optim_init, mse_loss], feed_dict={t_image:b_img_96, t_target_image:b_img_384})
 
           init_loss_total += MSE_LOSS
 
       if (epoch != 0) and (epoch % 10 == 0):
           out = sess.run(net_g_test.outputs, feed_dict={t_image:sample_imgs_96})
           print('[*] save image')
           tl.vis.save_images(out, [ni, ni], save_dir_ginit + '/train_%d.png' % epoch)
 
       if (epoch != 0) and (epoch % 10 ==0):
 
           tl.files.save_npz(net_g.all_params, name=checkpoint + '/g_init_{}.npz'.format(tl.global_flag['mode']))
 
   ### ======================== train GAN ================== ###
 
   for epoch in range(0, n_epoch+1):
 
       if epoch != 0 and epoch % decay_every == 0:
           new_lr = lr_decay ** (epoch // decay_every)
           sess.run(tf.assign(lr_v, new_lr * lr_v))
           log = '** new learning rate: %f(for GAN)' % (lr_init * new_lr)
           print(log)
 
       elif epoch == 0:
           sess.run(tf.assign(lr_v, lr_init))
           log = '** init lr: %f decay_every_init: %d, lr_decay: %f(for GAN)'%(lr_init, decay_every, lr_decay)
           print(log)
 
       epoch_time = time.time()
       total_d_loss, total_g_loss, n_iter = 0, 0, 0
 
       for idx in range(0, len(train_hr_img), batch_size):
 
           b_img_384 = tl.prepro.threading_data(train_hr_img[idx:idx+batch_size], fn=crop_sub_imgs_fn, is_random=False)
           b_img_96 = tl.prepro.threading_data(b_img_384, fn=downsample_fn)
 
           _, errD = sess.run([d_optim, d_loss], feed_dict={t_image:b_img_96, t_target_image:b_img_384})
           _, errG, errM, errV, errA = sess.run([g_optim, g_loss, mse_loss, vgg_loss, g_gan_loss], feed_dict={t_image:b_img_96, t_target_image:b_img_384})
 
           total_d_loss += errD
           total_g_loss += errG
 
       if epoch != 0 and epoch % 10 == 0:
           out = sess.run(net_g_test.outputs, feed_dict={t_image:sample_imgs_96})
           print('[*] save image')
           tl.vis.save_images(out, [ni, ni], save_dir_gan + '/train_%d' % epoch)
 
       if epoch != 0 and epoch % 10 == 0:
 
           tl.files.save_npz(net_g.all_params, name = checkpoint + '/g_{}.npz'.format(tl.global_flag['mode']))
           tl.files.save_npz(net_d.all_params, name= checkpoint + '/d_{}.npz'.format(tl.global_flag['mode']))
 
def evaluate():
 
    save_dir = 'sample/{}'.format(tl.global_flag['mode'])
    tl.files.exists_or_mkdir(save_dir)
    checkpoints = 'checkpoints'
 
    evaluate_hr_img_list = sorted(tl.files.load_file_list(config.VALID.hr_img_path, regx='.*.png', printable=False))
    evaluate_lr_img_list = sorted(tl.files.load_file_list(config.VALID.lr_img_path, regx='.*.png', printable=False))
 
    valid_lr_imgs = tl.vis.read_images(evaluate_lr_img_list, path=config.VALID.lr_img_path, n_threads=8)
    valid_hr_imgs = tl.vis.read_images(evaluate_hr_img_list, path=config.VALID.hr_img_path, n_threads=8)
 
    ### ==================== DEFINE MODEL =================###
    imid = 64
    valid_lr_img = valid_lr_imgs[imid]
    valid_hr_img = valid_hr_imgs[imid]
 
    valid_lr_img = (valid_lr_img / 127.5) - 1
 
    t_image = tf.placeholder('float32', [1, None, None, 3])
    net_g = SGRAN_g(t_image, False, False)
 
    sess = tf.Session()
    tl.files.load_and_assign_npz(sess, checkpoints + '/g_{}.npz'.format(tl.global_flag['mode']), network=net_g)
 
    output = sess.run([net_g.outputs], feed_dict={t_image:[valid_lr_img]})
 
    tl.vis.save_images(output[0], [ni, ni], save_dir + '/valid_gen.png')
    tl.vis.save_images(valid_lr_img, [ni, ni], save_dir + '/valid_lr.png')
    tl.vis.save_images(valid_hr_img, [ni, ni], save_dir + '/valid_hr.png')
 
    size = valid_hr_img.shape
    out_bicu = scipy.misc.imresize(valid_lr_img, [size[0]*4, size[1]*4], interp='bicubic', mode=None)
    tl.vis.save_images(out_bicu, [ni, ni], save_dir + '/valid_out_bicu.png')
 
if __name__ == '__main__':
    import argparse
    parse = argparse.ArgumentParser()
    parse.add_argument('--mode', type=str, default='srgan', help='srgan evaluate')
    args = parse.parse_args()
 
    tl.global_flag['mode'] = args.mode
    if tl.global_flag['mode'] == 'srgan':
        train()
 
    elif tl.global_flag['mode'] == 'evaluate':
        evaluate()

model.py 构建模型

import tensorflow as tf
import tensorlayer as tl
from tensorlayer.layers import *
import time
 
def SRGAN_g(input_image, is_train, reuse):
 
    w_init = tf.random_normal_initializer(stddev=0.2)
    b_init = None
    g_init = tf.random_normal_initializer(1, 0.02)
 
    with tf.variable_scope('SRGAN_g', reuse=reuse):
        n = InputLayer(input_image, name='in')
        n = Conv2d(n, 64, (3, 3), (1, 1), act=tf.nn.relu, padding='SAME', W_init=w_init, name='n64s1/c')
        temp = n
        for i in range(16):
            nn = Conv2d(n, 64, (3, 3), (1, 1), act=None, padding='SAME', W_init=w_init, name='n64s1/c1/%d' % i)
            nn = BatchNormLayer(nn, act=tf.nn.relu, is_train=is_train, gamma_init=g_init, name='n64s1/b1/%d' % i)
            nn = Conv2d(nn, 64, (3, 3), (1, 1), act=None, padding='SAME', W_init=w_init, name='n64s1/c2/%d' % i)
            nn = BatchNormLayer(nn, act=None, is_train=is_train, gamma_init=g_init, name='n64s1/b2/%d'%i)
            nn = ElementwiseLayer([n, nn], tf.add, name='b_residual_add_%d' % i)
            n = nn
 
        n = Conv2d(n, 64, (3, 3), (1, 1), act=None, padding='SAME', W_init=w_init, name='n64s1/c3')
        n = BatchNormLayer(n, act=None, is_train=is_train, gamma_init=g_init, name='n64s1/b3')
        n = ElementwiseLayer([temp, n], tf.add, name='add3')
 
        # 进行反卷积操作
        n = Conv2d(n, 256, (3, 3), (1, 1), act=None, padding='SAME', W_init=w_init, name='n64s1/c4')
        n = SubpixelConv2d(n, scale=2, n_out_channel=None, act=tf.nn.relu, name='pixelshuffler2/1')
 
        n = Conv2d(n, 256, (3, 3), (1, 1), act=None, padding='SAME', W_init=w_init, name='n64s1/c5')
        n = SubpixelConv2d(n, scale=2, n_out_channel=None, act=tf.nn.relu, name='pixelshuffle2/2')
 
        n = Conv2d(n, 3, (1, 1), (1, 1), act=tf.nn.tanh, padding='SAME', W_init=w_init, name='out')
 
        return n
 
def SRGAN_d(input_image, is_training=True, reuse=False):
 
    w_init = tf.random_normal_initializer(stddev=0.2)
    b_init = None
    g_init = tf.random_normal_initializer(1.0, stddev=0.02)
    lrelu = lambda x: tl.act.lrelu(x, 0.2)
    df_dim = 64
    with tf.variable_scope('SRGAN_d', reuse=reuse):
        tl.layers.set_name_reuse(reuse)
        net_in = InputLayer(input_image, name='input/image')
        net_h0 = Conv2d(net_in, df_dim, (4, 4), (2, 2), act=lrelu, padding='SAME', W_init=w_init, name='h0/c')
 
        net_h1 = Conv2d(net_h0, df_dim*2, (4, 4), (2, 2), act=None, padding='SAME', W_init=w_init, name='h1/c')
        net_h1 = BatchNormLayer(net_h1, act=lrelu, is_train=is_training, gamma_init=g_init, name='h1/bn')
        net_h2 = Conv2d(net_h1, df_dim*4, (4, 4), (2, 2), act=None, padding='SAME', W_init=w_init, name='h2/c')
        net_h2 = BatchNormLayer(net_h2, act=lrelu, is_train=is_training, gamma_init=g_init, name='h2/bn')
        net_h3 = Conv2d(net_h2, df_dim*8, (4, 4), (2, 2), act=None, padding='SAME', W_init=w_init, name='h3/c')
        net_h3 = BatchNormLayer(net_h3, act=lrelu, is_train=is_training, gamma_init=g_init, name='h3/bn')
        net_h4 = Conv2d(net_h3, df_dim*16, (4, 4), (2, 2), act=None, padding='SAME', W_init=w_init, name='h4/c')
        net_h4 = BatchNormLayer(net_h4, act=lrelu, is_train=is_training, gamma_init=g_init, name='h4/bn')
        net_h5 = Conv2d(net_h4, df_dim*32, (4, 4), (2, 2), act=None, padding='SAME', W_init=w_init, name='h5/c')
        net_h5 = BatchNormLayer(net_h5, act=lrelu, is_train=is_training, gamma_init=g_init, name='h5/bn')
        net_h6 = Conv2d(net_h5, df_dim*16, (1, 1), (1, 1), act=None, padding='SAME', W_init=w_init, name='h6/c')
        net_h6 = BatchNormLayer(net_h6, act=lrelu, is_train=is_training, gamma_init=g_init, name='h6/bn')
        net_h7 = Conv2d(net_h6, df_dim*8, (1, 1), (1, 1), act=None, padding='SAME', W_init=w_init, name='h7/c')
        net_h7 = BatchNormLayer(net_h7, act=lrelu, is_train=is_training, gamma_init=g_init, name='h7/bn')
 
        net = Conv2d(net_h7, df_dim*2, (1, 1), (1, 1), act=None, padding='SAME', W_init=w_init, name='reg/c')
        net = BatchNormLayer(net, act=lrelu, is_train=is_training, gamma_init=g_init, name='reg/bn')
        net = Conv2d(net, df_dim*2, (3, 3), (1, 1), act=None, padding='SAME', W_init=w_init, name='reg/c2')
        net = BatchNormLayer(net, act=lrelu, is_train=is_training, gamma_init=g_init, name='reg/bn2')
        net = Conv2d(net, df_dim*8, (3, 3), (1, 1), act=None, padding='SAME', W_init=w_init, name='reg/c3')
        net = BatchNormLayer(net, act=lrelu, is_train=is_training, gamma_init=g_init, name='reg/bn3')
 
        net_h8 = ElementwiseLayer([net_h7, net], tf.add, name='red/add')
        net_h8.outputs = tl.act.lrelu(net_h8.outputs, 0.2)
 
        net_ho = FlattenLayer(net_h8, name='ho/flatten')
        net_ho = DenseLayer(net_ho, n_units=1, act=tf.identity, W_init=w_init, name='ho/dense')
        logits = net_ho.outputs
        net_ho.outputs = tf.nn.sigmoid(net_ho.outputs)
 
        return net_ho, logits
 
def Vgg_19_simple_api(input_image, reuse):
 
    VGG_MEAN = [103.939, 116.779, 123.68]
    # 将输入的rgb图像转换为bgr
    with tf.variable_scope('VGG19', reuse=reuse) as vs:
        start_time = time.time()
        print('build the model')
        input_image = input_image * 255
        red, green, blue = tf.split(input_image, 3, 3)
        assert red.get_shape().as_list()[1:] == [224, 224, 1]
        assert green.get_shape().as_list()[1:] == [224, 224, 1]
        assert blue.get_shape().as_list()[1:] == [224, 224, 1]
 
        bgr = tf.concat([blue-VGG_MEAN[0], green-VGG_MEAN[1], red-VGG_MEAN[2]], axis=3)
        assert input_image.get_shape().as_list()[1:] == [224, 224, 3]
 
        net_in = InputLayer(bgr, name='input')
        # 构建网络
        """conv1"""
        network = Conv2d(net_in, 64, (3, 3), (1, 1), act=tf.nn.relu, padding='SAME', name='conv1_1')
        network = Conv2d(network, 64, (3, 3), (1, 1), act=tf.nn.relu, padding='SAME', name='conv1_2')
        network = MaxPool2d(network, (2, 2), (2, 2), padding='SAME', name='pool1')
        '''conv2'''
        network = Conv2d(network, 128, (3, 3), (1, 1), act=tf.nn.relu, padding='SAME', name='conv2_1')
        network = Conv2d(network, 128, (3, 3), (1, 1), act=tf.nn.relu, padding='SAME', name='conv2_2')
        network = MaxPool2d(network, (2, 2), (2, 2), padding='SAME', name='pool2')
        '''conv3'''
        network = Conv2d(network, 256, (3, 3), (1, 1), act=tf.nn.relu, padding='SAME', name='conv3_1')
        network = Conv2d(network, 256, (3, 3), (1, 1), act=tf.nn.relu, padding='SAME', name='conv3_2')
        network = Conv2d(network, 256, (3, 3), (1, 1), act=tf.nn.relu, padding='SAME', name='conv3_3')
        network = Conv2d(network, 256, (3, 3), (1, 1), act=tf.nn.relu, padding='SAME', name='conv3_4')
        network = MaxPool2d(network, (2, 2), (2, 2), padding='SAME', name='pool3')
        '''conv4'''
        network = Conv2d(network, 512, (3, 3), (1, 1), act=tf.nn.relu, padding='SAME', name='conv4_1')
        network = Conv2d(network, 512, (3, 3), (1, 1), act=tf.nn.relu, padding='SAME', name='conv4_2')
        network = Conv2d(network, 512, (3, 3), (1, 1), act=tf.nn.relu, padding='SAME', name='conv4_3')
        network = Conv2d(network, 512, (3, 3), (1, 1), act=tf.nn.relu, padding='SAME', name='conv4_4')
        network = MaxPool2d(network, (2, 2), (2, 2), padding='SAME', name='pool4')
        '''conv5'''
        network = Conv2d(network, 512, (3, 3), (1, 1), act=tf.nn.relu, padding='SAME', name='conv5_1')
        network = Conv2d(network, 512, (3, 3), (1, 1), act=tf.nn.relu, padding='SAME', name='conv5_2')
        network = Conv2d(network, 512, (3, 3), (1, 1), act=tf.nn.relu, padding='SAME', name='conv5_3')
        network = Conv2d(network, 512, (3, 3), (1, 1), act=tf.nn.relu, padding='SAME', name='conv5_4')
        network = MaxPool2d(network, (2, 2), (2, 2), padding='SAME', name='pool5')
        conv = network
        """fc6-8"""
        network = FlattenLayer(network, name='flatten')
        network = DenseLayer(network, n_units=4096, act=tf.nn.relu, name='fc6')
        network = DenseLayer(network, n_units=4096, act=tf.nn.relu, name='fc7')
        network = DenseLayer(network, n_units=1000, act=tf.identity, name='fc8')
        print('finish the bulid %fs' % (time.time() - start_time))
        return network, conv

config.py  参数文件

from easydict import EasyDict as edict
import json
 
config = edict()
 
config.TRAIN = edict()
 
# Adam
config.TRAIN.batch_size = 1
config.TRAIN.lr_init = 1e-4
config.TRAIN.betal = 0.9
 
### initialize G
config.TRAIN.n_epoch_init = 100
 
### adversarial_leaning
config.TRAIN.n_epoch = 2000
config.TRAIN.lr_decay = 0.1
config.TRAIN.decay_every = int(config.TRAIN.n_epoch / 2)
 
## train set location
config.TRAIN.hr_img_path = r'C:\Users\qq302\Desktop\srdata\DIV2K_train_HR'
config.TRAIN.lr_img_path = r'C:\Users\qq302\Desktop\srdata\DIV2K_train_LR_bicubic\X4'
 
# valid set location
 
config.VALID = edict()
 
config.VALID.hr_img_path = r'C:\Users\qq302\Desktop\srdata\DIV2K_valid_HR'
config.VALID.lr_img_path = r'C:\Users\qq302\Desktop\srdata\DIV2K_valid_LR_bicubic/X4'

utils.py  操作文件

from tensorlayer.prepro import *
 
def crop_sub_imgs_fn(img, is_random=True):
 
    x = crop(img, wrg=384, hrg=384, is_random=is_random)
    # 进行 -1 - 1 的归一化
    x = x / 127.5 - 1
    return x
 
def downsample_fn(img):
 
    x = imresize(img, [96, 96], interp='bicubic', mode=None)
    # 存在一定的问题
    x = x / 127.5 - 1
    return x