DCGAN简单实现

1、预处理

有关生成式网络图片预处理的探讨实验见博客:
『TensorFlow』生成式网络中的图片预处理
数据在预处理时采用了原像素数据除以127.5减去1的操作，使得输出值保持在-1~1之间，这样配合sigmoid激活函数可以很好的模拟学习。

2、目录介绍

TFR_process.py：TFRecode数据生成以及处理脚本
ops.py：层封装脚本
DCGAN_class.py：使用类的方式实现DC_GAN，因为是重点所以代码中给出了详尽的注释
DCGAN_function.py：使用函数的方式实现DC_GAN，因为上面版本受开源项目影响较大，代码繁杂，这里进行了改写，采取了更为清晰的写法
utils.py：格式化绘图、保存图片函数，开源项目直接找来的
DCGAN_reload.py：利用已经训练好的模型生成一组头像
Data_Set/cartoon_faces：此处目录下放置头像图片

3、实验步骤

先运行TFR_process.py产生TFRecord数据：

python TFR_process.py

本部分涉及参量如下（位于TFR_process.py的起始位置）：

# 定义每个TFR文件中放入多少条数据
INSTANCES_PER_SHARD = 10000
# 图片文件存放路径
IMAGE_PATH = './Data_Set/cartoon_faces'
# 图片文件和标签清单保存文件
IMAGE_LABEL_LIST = 'images_&_labels.txt'
# TFR文件保存路径
TFR_PATH = './TFRecord_Output'

然后再运行DC_GAN.py使用前面的数据训练DC_GAN，

python DCGAN_class.py

或者

python DCGAN_function.py

当时为了方便，这些参量的设置也放在了TFR_process.py中，

# TFR保存图像尺寸
IMAGE_HEIGHT = 48
IMAGE_WIDTH = IMAGE_HEIGHT
IMAGE_DEPTH = 3
# 训练batch尺寸
BATCH_SIZE = 64

这是因为我的数据读取函数batch_from_tfr位于此文件中，该函数可以设置传入网络的图片大小。

已经训练好模型了的话如下操作，

python DCGAN_reload.py

即可直接生成一组图像。

4、网络示意

5、结果展示

请教报错

本地使用docker，拿到的是TensorFlow 最新版本（直接拿的docker），python2.7

报错信息如下：
Traceback (most recent call last):
File "DCGAN_reload.py", line 48, in
reload_dcgan()
File "DCGAN_reload.py", line 43, in reload_dcgan
samples = sess.run(end_points['sample_output'], feed_dict={end_points['initial_z']: sample_z})
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 929, in run
run_metadata_ptr)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1152, in _run
feed_dict_tensor, options, run_metadata)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1328, in _do_run
run_metadata)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1348, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.FailedPreconditionError: Attempting to use uninitialized value generator/g_h2/w
[[node generator/g_h2/w/read (defined at /notebooks/myBun/DCGAN_TensorFlow/ops.py:159) = IdentityT=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

Caused by op u'generator/g_h2/w/read', defined at:
File "DCGAN_reload.py", line 48, in
reload_dcgan()
File "DCGAN_reload.py", line 33, in reload_dcgan
end_points = dcgan()
File "/notebooks/myBun/DCGAN_TensorFlow/DCGAN_function.py", line 90, in dcgan
g = generator(z)
File "/notebooks/myBun/DCGAN_TensorFlow/DCGAN_function.py", line 78, in generator
h2 = deconv2d(h1, [batch_size, s_h4, s_w4, gf_dim * 2], scope='g_h2')
File "/notebooks/myBun/DCGAN_TensorFlow/ops.py", line 159, in deconv2d
w = tf.get_variable('w', [k_h, k_w, output_shape[-1], input_.get_shape()[-1]],initializer=tf.random_normal_initializer(stddev=0.02))
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 1487, in get_variable
aggregation=aggregation)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 1237, in get_variable
aggregation=aggregation)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 540, in get_variable
aggregation=aggregation)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 492, in _true_getter
aggregation=aggregation)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 922, in _get_single_variable
aggregation=aggregation)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variables.py", line 183, in call
return cls._variable_v1_call(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variables.py", line 146, in _variable_v1_call
aggregation=aggregation)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variables.py", line 125, in
previous_getter = lambda **kwargs: default_variable_creator(None, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 2444, in default_variable_creator
expected_shape=expected_shape, import_scope=import_scope)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variables.py", line 187, in call
return super(VariableMetaclass, cls).call(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variables.py", line 1329, in init
constraint=constraint)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variables.py", line 1491, in _init_from_args
self._snapshot = array_ops.identity(self._variable, name="read")
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/array_ops.py", line 81, in identity
return gen_array_ops.identity(input, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 3454, in identity
"Identity", input=input, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/util/deprecation.py", line 488, in new_func
return func(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 3274, in create_op
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1770, in init
self._traceback = tf_stack.extract_stack()

FailedPreconditionError (see above for traceback): Attempting to use uninitialized value generator/g_h2/w
[[node generator/g_h2/w/read (defined at /notebooks/myBun/DCGAN_TensorFlow/ops.py:159) = IdentityT=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

请问我这是哪出了问题？多谢！其他基本都OK，只有一些警告信息！

hellcatzm / dcgan_tensorflow Goto Github PK

dcgan_tensorflow's Introduction

DCGAN简单实现

相关资源

1、预处理

2、目录介绍

3、实验步骤

4、网络示意

5、结果展示

dcgan_tensorflow's People

Contributors

Stargazers

Watchers

Forkers

dcgan_tensorflow's Issues

Recommend Projects

Recommend Topics

Recommend Org

Jobs