网站制作app免费软件,做微信投票的网站,网络推广方法大全,无聊的网站GAN 这个领域发展太快#xff0c;日新月异#xff0c;各种 GAN 层出不穷#xff0c;前几天看到一篇关于 Wasserstein GAN 的文章#xff0c;讲的很好#xff0c;在此把它分享出来一起学习#xff1a;https://zhuanlan.zhihu.com/p/25071913。相比 Wasserstein GAN #…GAN 这个领域发展太快日新月异各种 GAN 层出不穷前几天看到一篇关于 Wasserstein GAN 的文章讲的很好在此把它分享出来一起学习https://zhuanlan.zhihu.com/p/25071913。相比 Wasserstein GAN 我们的 DCGAN 好像低了一个档次但是我们伟大的教育家鲁迅先生说过“合抱之木生于毫末九层之台起于累土千里之行始于足下”依稀记得那大概是我 7 - 8 岁的时候鲁迅先生依偎在我身旁带着和蔼可亲切的口吻对我说的这句话他当时还加了一句话小伙子你要记住如果一句名言你不知道是谁说的那就是鲁迅说的。所以我们的基础还是要打好的 DCGAN 是我们的基础有了 DCGAN 的代码经验相信写起 Wasserstein GAN 就顺手很多所以我们接下来继续来研究我们的无约束条件 DCGAN。 在上一篇文章中我们用 MNIST 手写字符训练 GAN生成网络 G 生成了相对比较好的手写字符这一次我们换个数据集用 CelebA 人脸数据集来训练我们的 GAN相比于手写字符人脸数据集的分布更加复杂多样长头发短头发黄种人黑种人戴眼镜不戴眼镜男人女人等等看看我们的生成网络 G 能否成功的检验出人脸数据集的分布。 首先准备数据从官网分享的百度云盘连接 https://pan.baidu.com/s/1eSNpdRG#list/path%2FCelebA%2FImg 下载 img_align_celeba.zip在 /home/your_name/TensorFlow/DCGAN/data 文件夹下解压得到 img_align_celeba 文件夹里面有 20600 张人脸图片在 /home/your_name/TensorFlow/DCGAN/data 文件夹下新建 img_align_celeba_tfrecords 文件夹用来存放 tfrecords 文件然后在 /home/your_name/TensorFlow/DCGAN/ 下新建 convert_data.py编写如下的代码把人脸图片转化成 tfrecords 形式 import os
import time
from PIL import Imageimport tensorflow as tf# 将图片裁剪为 128 x 128
OUTPUT_SIZE 128
# 图片通道数3 表示彩色
DEPTH 3def _int64_feature(value):return tf.train.Feature(int64_list tf.train.Int64List(value [value]))
def _bytes_feature(value):return tf.train.Feature(bytes_list tf.train.BytesList(value [value]))def convert_to(data_path, name):Converts s dataset to tfrecordsrows 64cols 64depth DEPTH# 循环 12 次产生 12 个 .tfrecords 文件for ii in range(12):writer tf.python_io.TFRecordWriter(name str(ii) .tfrecords)# 每个 tfrecord 文件有 16384 个图片for img_name in os.listdir(data_path)[ii*16384 : (ii1)*16384]:# 打开图片img_path data_path img_nameimg Image.open(img_path)# 设置裁剪参数h, w img.size[:2]j, k (h - OUTPUT_SIZE) / 2, (w - OUTPUT_SIZE) / 2box (j, k, j OUTPUT_SIZE, k OUTPUT_SIZE)# 裁剪图片img img.crop(box box)# image resizeimg img.resize((rows,cols))# 转化为字节img_raw img.tobytes()# 写入到 Example example tf.train.Example(features tf.train.Features(feature {height: _int64_feature(rows),width: _int64_feature(cols),depth: _int64_feature(depth),image_raw: _bytes_feature(img_raw)}))writer.write(example.SerializeToString())writer.close()if __name__ __main__:current_dir os.getcwd() data_path current_dir /data/img_align_celeba/name current_dir /data/img_align_celeba_tfrecords/trainstart_time time.time() print(Convert start) print(\n * 2)convert_to(data_path, name)print(\n * 2)print(Convert done, take %.2f seconds % (time.time() - start_time)) 运行之后在 /home/your_name/TensorFlow/DCGAN/data/img_align_celeba_tfrecords/ 下会产生 12 个 .tfrecords 文件这就是我们要的数据格式。 数据准备好之后根据前面的经验我们来写无约束条件的 DCGAN 代码在 /home/your_name/TensorFlow/DCGAN/ 新建 none_cond_DCGAN.py 文件敲写代码为了简便起见代码中没有加注释并且把所有的代码总结到一个代码中从代码中可以看到我们自己写了一个 batch_norm 层解决了 evaluation 函数中 is_train False 的问题并且可以断点续训练(只需要将开头的 LOAD_MODEL 设置为 True)此外该程序在开头采用很多的宏定义可以方便的改为 tf.app.flags 定义的命令行参数进而在命令行终端进行训练还可以进行类的拓展例如 class DCGAN(object):def __init__(self):self.BATCH_SIZE 64...def bias(self):...... 关于类的拓展这里不做过多说明。 在 none_cond_DCGAN.py 文件中敲写如下代码 import os
import numpy as np
import scipy.misc
import tensorflow as tfBATCH_SIZE 64
OUTPUT_SIZE 64
GF 64 # Dimension of G filters in first conv layer. default [64]
DF 64 # Dimension of D filters in first conv layer. default [64]
Z_DIM 100
IMAGE_CHANNEL 3
LR 0.0002 # Learning rate
EPOCH 5
LOAD_MODEL False # Whether or not continue train from saved model。
TRAIN True
CURRENT_DIR os.getcwd()def bias(name, shape, bias_start 0.0, trainable True):dtype tf.float32var tf.get_variable(name, shape, tf.float32, trainable trainable, initializer tf.constant_initializer(bias_start, dtype dtype))return vardef weight(name, shape, stddev 0.02, trainable True):dtype tf.float32var tf.get_variable(name, shape, tf.float32, trainable trainable, initializer tf.random_normal_initializer(stddev stddev, dtype dtype))return vardef fully_connected(value, output_shape, name fully_connected, with_w False):shape value.get_shape().as_list()with tf.variable_scope(name):weights weight(weights, [shape[1], output_shape], 0.02)biases bias(biases, [output_shape], 0.0)if with_w:return tf.matmul(value, weights) biases, weights, biaseselse:return tf.matmul(value, weights) biasesdef lrelu(x, leak0.2, name lrelu):with tf.variable_scope(name):return tf.maximum(x, leak*x, name name)def relu(value, name relu):with tf.variable_scope(name):return tf.nn.relu(value)def deconv2d(value, output_shape, k_h 5, k_w 5, strides [1, 2, 2, 1], name deconv2d, with_w False):with tf.variable_scope(name):weights weight(weights, [k_h, k_w, output_shape[-1], value.get_shape()[-1]])deconv tf.nn.conv2d_transpose(value, weights, output_shape, strides strides)biases bias(biases, [output_shape[-1]])deconv tf.reshape(tf.nn.bias_add(deconv, biases), deconv.get_shape())if with_w:return deconv, weights, biaseselse:return deconvdef conv2d(value, output_dim, k_h 5, k_w 5, strides [1, 2, 2, 1], name conv2d):with tf.variable_scope(name):weights weight(weights, [k_h, k_w, value.get_shape()[-1], output_dim])conv tf.nn.conv2d(value, weights, strides strides, padding SAME)biases bias(biases, [output_dim])conv tf.reshape(tf.nn.bias_add(conv, biases), conv.get_shape())return convdef conv_cond_concat(value, cond, name concat):Concatenate conditioning vector on feature map axis.value_shapes value.get_shape().as_list()cond_shapes cond.get_shape().as_list()with tf.variable_scope(name): return tf.concat(3,[value, cond * tf.ones(value_shapes[0:3] cond_shapes[3:])])def batch_norm(value, is_train True, name batch_norm, epsilon 1e-5, momentum 0.9):with tf.variable_scope(name):ema tf.train.ExponentialMovingAverage(decay momentum)shape value.get_shape().as_list()[-1]beta bias(beta, [shape], bias_start 0.0)gamma bias(gamma, [shape], bias_start 1.0)if is_train:batch_mean, batch_variance tf.nn.moments(value, [0, 1, 2], name moments)moving_mean bias(moving_mean, [shape], 0.0, False)moving_variance bias(moving_variance, [shape], 1.0, False)ema_apply_op ema.apply([batch_mean, batch_variance])assign_mean moving_mean.assign(ema.average(batch_mean))assign_variance \moving_variance.assign(ema.average(batch_variance))with tf.control_dependencies([ema_apply_op]):mean, variance \tf.identity(batch_mean), tf.identity(batch_variance)with tf.control_dependencies([assign_mean, assign_variance]):return tf.nn.batch_normalization(value, mean, variance, beta, gamma, 1e-5)else:mean bias(moving_mean, [shape], 0.0, False)variance bias(moving_variance, [shape], 1.0, False)return tf.nn.batch_normalization(value, mean, variance, beta, gamma, epsilon)def generator(z, is_train True, name generator):with tf.name_scope(name):s2, s4, s8, s16 \OUTPUT_SIZE/2, OUTPUT_SIZE/4, OUTPUT_SIZE/8, OUTPUT_SIZE/16h1 tf.reshape(fully_connected(z, GF*8*s16*s16, g_fc1), [-1, s16, s16, GF*8], name reshap)h1 relu(batch_norm(h1, name g_bn1, is_train is_train))h2 deconv2d(h1, [BATCH_SIZE, s8, s8, GF*4], name g_deconv2d1)h2 relu(batch_norm(h2, name g_bn2, is_train is_train))h3 deconv2d(h2, [BATCH_SIZE, s4, s4, GF*2], name g_deconv2d2)h3 relu(batch_norm(h3, name g_bn3, is_train is_train))h4 deconv2d(h3, [BATCH_SIZE, s2, s2, GF*1], name g_deconv2d3)h4 relu(batch_norm(h4, name g_bn4, is_train is_train))h5 deconv2d(h4, [BATCH_SIZE, OUTPUT_SIZE, OUTPUT_SIZE, 3], name g_deconv2d4) return tf.nn.tanh(h5)def discriminator(image, reuse False, name discriminator):with tf.name_scope(name): if reuse:tf.get_variable_scope().reuse_variables()h0 lrelu(conv2d(image, DF, named_h0_conv), name d_h0_lrelu)h1 lrelu(batch_norm(conv2d(h0, DF*2, named_h1_conv),name d_h1_bn), name d_h1_lrelu)h2 lrelu(batch_norm(conv2d(h1, DF*4, named_h2_conv),name d_h2_bn), name d_h2_lrelu)h3 lrelu(batch_norm(conv2d(h2, DF*8, named_h3_conv),name d_h3_bn), name d_h3_lrelu)h4 fully_connected(tf.reshape(h3, [BATCH_SIZE, -1]), 1, d_h4_fc)return tf.nn.sigmoid(h4), h4def sampler(z, is_train False, name sampler):with tf.name_scope(name):tf.get_variable_scope().reuse_variables()return generator(z, is_train is_train)def read_and_decode(filename_queue):read and decode tfrecordsreader tf.TFRecordReader()_, serialized_example reader.read(filename_queue)features tf.parse_single_example(serialized_example,features {image_raw:tf.FixedLenFeature([], tf.string)})image tf.decode_raw(features[image_raw], tf.uint8)image tf.reshape(image, [OUTPUT_SIZE, OUTPUT_SIZE, 3])image tf.cast(image, tf.float32)image image / 255.0return imagedef inputs(data_dir, batch_size, name input):Reads input data num_epochs times.with tf.name_scope(name):filenames [os.path.join(data_dir,train%d.tfrecords % ii) for ii in range(12)]filename_queue tf.train.string_input_producer(filenames)image read_and_decode(filename_queue)images tf.train.shuffle_batch([image], batch_size batch_size, num_threads 4, capacity 20000 3 * batch_size, min_after_dequeue 20000)return imagesdef save_images(images, size, path):Save the samples imagesThe best size number isint(max(sqrt(image.shape[1]),sqrt(image.shape[1]))) 1img (images 1.0) / 2.0h, w img.shape[1], img.shape[2]merge_img np.zeros((h * size[0], w * size[1], 3))for idx, image in enumerate(images):i idx % size[1]j idx // size[1]merge_img[j*h:j*hh, i*w:i*ww, :] imagereturn scipy.misc.imsave(path, merge_img) def train():global_step tf.Variable(0, name global_step, trainable False)train_dir CURRENT_DIR /logs_without_condition/data_dir CURRENT_DIR /data/img_align_celeba_tfrecords/images inputs(data_dir, BATCH_SIZE)z tf.placeholder(tf.float32, [None, Z_DIM], namez)G generator(z)D, D_logits discriminator(images)samples sampler(z)D_, D_logits_ discriminator(G, reuse True)d_loss_real tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(D_logits, tf.ones_like(D)))d_loss_fake tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(D_logits_, tf.zeros_like(D_)))d_loss d_loss_real d_loss_fakeg_loss tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(D_logits_, tf.ones_like(D_)))z_sum tf.histogram_summary(z, z)d_sum tf.histogram_summary(d, D)d__sum tf.histogram_summary(d_, D_)G_sum tf.image_summary(G, G)d_loss_real_sum tf.scalar_summary(d_loss_real, d_loss_real)d_loss_fake_sum tf.scalar_summary(d_loss_fake, d_loss_fake)d_loss_sum tf.scalar_summary(d_loss, d_loss) g_loss_sum tf.scalar_summary(g_loss, g_loss)g_sum tf.merge_summary([z_sum, d__sum, G_sum, d_loss_fake_sum, g_loss_sum])d_sum tf.merge_summary([z_sum, d_sum, d_loss_real_sum, d_loss_sum])t_vars tf.trainable_variables()d_vars [var for var in t_vars if d_ in var.name]g_vars [var for var in t_vars if g_ in var.name]saver tf.train.Saver()d_optim tf.train.AdamOptimizer(LR, beta1 0.5) \.minimize(d_loss, var_list d_vars, global_step global_step)g_optim tf.train.AdamOptimizer(LR, beta1 0.5) \.minimize(g_loss, var_list g_vars, global_step global_step)os.environ[CUDA_VISIBLE_DEVICES] str(0)config tf.ConfigProto()config.gpu_options.per_process_gpu_memory_fraction 0.2sess tf.InteractiveSession(configconfig)writer tf.train.SummaryWriter(train_dir, sess.graph) sample_z np.random.uniform(-1, 1, size (BATCH_SIZE, Z_DIM))coord tf.train.Coordinator()threads tf.train.start_queue_runners(sess sess, coord coord)init tf.initialize_all_variables() sess.run(init)start 0if LOAD_MODEL: print( [*] Reading checkpoints...)ckpt tf.train.get_checkpoint_state(train_dir) if ckpt and ckpt.model_checkpoint_path:ckpt_name os.path.basename(ckpt.model_checkpoint_path)saver.restore(sess, os.path.join(train_dir, ckpt_name))global_step ckpt.model_checkpoint_path.split(/)[-1]\.split(-)[-1]print(Loading success, global_step is %s % global_step)start int(global_step)for epoch in range(EPOCH):batch_idxs 3072if epoch:start 0for idx in range(start, batch_idxs):batch_z np.random.uniform(-1, 1, size (BATCH_SIZE, Z_DIM))_, summary_str sess.run([d_optim, d_sum], feed_dict {z: batch_z})writer.add_summary(summary_str, idx1)# Update G network_, summary_str sess.run([g_optim, g_sum], feed_dict {z: batch_z})writer.add_summary(summary_str, idx1)# Run g_optim twice to make sure that d_loss does not go to zero_, summary_str sess.run([g_optim, g_sum], feed_dict {z: batch_z})writer.add_summary(summary_str, idx1)errD_fake d_loss_fake.eval({z: batch_z})errD_real d_loss_real.eval()errG g_loss.eval({z: batch_z})if idx % 20 0:print([%4d/%4d] d_loss: %.8f, g_loss: %.8f \% (idx, batch_idxs, errD_fakeerrD_real, errG))if idx % 100 0:sample sess.run(samples, feed_dict {z: sample_z})samples_path CURRENT_DIR /samples_without_condition/save_images(sample, [8, 8], samples_path \sample_%d_epoch_%d.png % (epoch, idx))print \n*2print( %d_epoch_%d.png save down %(epoch, idx))print \n*2if (idx % 512 0) or (idx 1 batch_idxs):checkpoint_path os.path.join(train_dir, my_dcgan_tfrecords.ckpt)saver.save(sess, checkpoint_path, global_step idx1)print ********* model saved *********print ******* start with %d ******* % startcoord.request_stop() coord.join(threads)sess.close()def evaluate():eval_dir CURRENT_DIR /eval/checkpoint_dir CURRENT_DIR /logs_without_condition/z tf.placeholder(tf.float32, [None, Z_DIM], namez)G generator(z, is_train False)sample_z1 np.random.uniform(-1, 1, size(BATCH_SIZE, Z_DIM))sample_z2 np.random.uniform(-1, 1, size(BATCH_SIZE, Z_DIM))sample_z3 (sample_z1 sample_z2) / 2sample_z4 (sample_z1 sample_z3) / 2sample_z5 (sample_z2 sample_z3) / 2 print(Reading checkpoints...)ckpt tf.train.get_checkpoint_state(checkpoint_dir)saver tf.train.Saver(tf.all_variables())os.environ[CUDA_VISIBLE_DEVICES] str(0)config tf.ConfigProto()config.gpu_options.per_process_gpu_memory_fraction 0.2sess tf.InteractiveSession(configconfig)if ckpt and ckpt.model_checkpoint_path:ckpt_name os.path.basename(ckpt.model_checkpoint_path)global_step ckpt.model_checkpoint_path.split(/)[-1].split(-)[-1] saver.restore(sess, os.path.join(checkpoint_dir, ckpt_name))print(Loading success, global_step is %s % global_step)eval_sess1 sess.run(G, feed_dict {z: sample_z1})eval_sess2 sess.run(G, feed_dict {z: sample_z4})eval_sess3 sess.run(G, feed_dict {z: sample_z3})eval_sess4 sess.run(G, feed_dict {z: sample_z5})eval_sess5 sess.run(G, feed_dict {z: sample_z2})print(eval_sess3.shape)save_images(eval_sess1, [8, 8], eval_dir eval_%d.png % 1)save_images(eval_sess2, [8, 8], eval_dir eval_%d.png % 2)save_images(eval_sess3, [8, 8], eval_dir eval_%d.png % 3)save_images(eval_sess4, [8, 8], eval_dir eval_%d.png % 4)save_images(eval_sess5, [8, 8], eval_dir eval_%d.png % 5)sess.close()if __name__ __main__:if TRAIN:train()else:evaluate() View Code 完成后运行代码网络开始训练大致需要 1~2 个小时训练就可以完成在训练的过程中可以看出 sampler 采样的生成结果越来越好最后得到了一个如下图所示的结果由于人脸的数据分布比手写数据分布复杂多样所以生成器不能完全抓住人脸的特征下图所示的第 6 行第 7 列就是一个很糟糕的生成图像。 训练完成后我们用 tensorboard 打开网络的 graph看看经过我们的精心设计网络结构变成了什么样子 可以看出来这次的结构图比之前的顺眼多了简直是处女座的福音啊有木有。 至此我们完成了 DCGAN 的代码下一篇文章我们来说说 Caffe 那点事。 参考文献 1. https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/how_tos/reading_data/convert_to_records.py 2. https://github.com/carpedm20/DCGAN-tensorflow 转载于:https://www.cnblogs.com/Charles-Wan/p/6386148.html
