无奈啊，按照书上的源码，怎么都调试不出来，无奈只好找过的源码：
在这个博客中发现一个卡通用的数据集，比较小，心想用小数据集试下吧，反正也就没指望能跑出来~~~~~~https://blog.csdn.net/heyc861221/article/details/80127914，数据集是卡通的头像，才两百多M。
源码我换成这个：
https://github.com/carpedm20/DCGAN-tensorflow
一共五个文件，多了个ops.py，但是download.py用的还是google盘，所以还是不能用，utils.py 文件增添了些内容，main.py把flags弄得更全点，ops.py是把卷积和反卷积等操作单独设成函数存在这里，其它的方面没什么区别，反正核心是model.py这里没改动就行。
这里要在data文件夹下再新建个叫anime的文件夹， 用来存卡通头像，data文件夹与源码是在同一个文件夹下的，data文件夹里应该还有之前下载过mnist和celebA。
windows的cmd是可以运行py文件的。这并不是MAC或Linux的专利。输入python加空格后，把要运行的py文件拖到cmd框上，这样就不用去输这么夸张的路径的， 然后再空格，用--参数项 参数 的形式定义好参数，再回车运行就可以的
我这样运行是报错的，说是准备checkpoint存取的文件夹找不到，后来我加上 --checkpoint_dir anime_64_48_48就可以了。如果不想在cmd上运行，需要改下main.py的开头几个flags代码的参数如下：
flags = tf.app.flags
# flags.DEFINE_integer("epoch", 25, "Epoch to train [25]")
flags.DEFINE_integer("epoch", 2, "Epoch to train [25]")
flags.DEFINE_float("learning_rate", 0.0002, "Learning rate of for adam [0.0002]")
flags.DEFINE_float("beta1", 0.5, "Momentum term of adam [0.5]")
flags.DEFINE_float("train_size", np.inf, "The size of train images [np.inf]")
flags.DEFINE_integer("batch_size", 64, "The size of batch images [64]")
# flags.DEFINE_integer("input_height", 108, "The size of image to use (will be center cropped). [108]")
flags.DEFINE_integer("input_height", 96, "The size of image to use (will be center cropped). [108]")
flags.DEFINE_integer("input_width", None, "The size of image to use (will be center cropped). If None, same value as input_height [None]")
# flags.DEFINE_integer("output_height", 64, "The size of the output images to produce [64]")
flags.DEFINE_integer("output_height", 48, "The size of the output images to produce [64]")
flags.DEFINE_integer("output_width", None, "The size of the output images to produce. If None, same value as output_height [None]")
# flags.DEFINE_string("dataset", "celebA", "The name of dataset [celebA, mnist, lsun]")
flags.DEFINE_string("dataset", "anime", "The name of dataset [celebA, mnist, lsun]")
flags.DEFINE_string("input_fname_pattern", "*.jpg", "Glob pattern of filename of input images [*]")
# flags.DEFINE_string("checkpoint_dir", "checkpoint", "Directory name to save the checkpoints [checkpoint]")
flags.DEFINE_string("checkpoint_dir", "anime_64_48_48", "Directory name to save the checkpoints [checkpoint]")
flags.DEFINE_string("data_dir", "./data", "Root directory of dataset [data]")
flags.DEFINE_string("sample_dir", "samples", "Directory name to save the image samples [samples]")
# flags.DEFINE_boolean("train", False, "True for training, False for testing [False]")
flags.DEFINE_boolean("train", True, "True for training, False for testing [False]")
# flags.DEFINE_boolean("crop", False, "True for training, False for testing [False]")
flags.DEFINE_boolean("crop", True, "True for training, False for testing [False]")
flags.DEFINE_boolean("visualize", False, "True for visualizing, False for nothing [False]")
flags.DEFINE_integer("generate_test_images", 100, "Number of images to generate during test. [100]")
FLAGS = flags.FLAGS
因为是正方形，所以只要输入input_height和output_height的参数就可以的。这里的卡通头像大小都是96像素的正方形，所以参数是96，输出是48像素正方形，而checkpoint的anime_64_48_48指的是anime数据集的三层处理大小分别是64，48，48所以这么取名的，我是根据报错信息取的。
然后运行如下：
{'batch_size': <absl.flags._flag.Flag object at 0x000000000958C5F8>,
'beta1': <absl.flags._flag.Flag object at 0x000000000957DCF8>,
'checkpoint_dir': <absl.flags._flag.Flag object at 0x000000000C3BFA90>,
'crop': <absl.flags._flag.BooleanFlag object at 0x000000000C3BFC50>,
'data_dir': <absl.flags._flag.Flag object at 0x000000000C3BFB00>,
'dataset': <absl.flags._flag.Flag object at 0x000000000C3BF940>,
'epoch': <absl.flags._flag.Flag object at 0x000000000126F0F0>,
'generate_test_images': <absl.flags._flag.Flag object at 0x000000000C3BFD68>,
'h': <tensorflow.python.platform.app._HelpFlag object at 0x000000000C3BFDA0>,
'help': <tensorflow.python.platform.app._HelpFlag object at 0x000000000C3BFDA0>,
'helpfull': <tensorflow.python.platform.app._HelpfullFlag object at 0x000000000C3BFE48>,
'helpshort': <tensorflow.python.platform.app._HelpshortFlag object at 0x000000000C3BFEB8>,
'input_fname_pattern': <absl.flags._flag.Flag object at 0x000000000C3BF9E8>,
'input_height': <absl.flags._flag.Flag object at 0x000000000958C6D8>,
'input_width': <absl.flags._flag.Flag object at 0x000000000C3BF7B8>,
'learning_rate': <absl.flags._flag.Flag object at 0x0000000004388FD0>,
'output_height': <absl.flags._flag.Flag object at 0x000000000C3BF828>,
'output_width': <absl.flags._flag.Flag object at 0x000000000C3BF8D0>,
'sample_dir': <absl.flags._flag.Flag object at 0x000000000C3BFB70>,
'train': <absl.flags._flag.BooleanFlag object at 0x000000000C3BFBA8>,
'train_size': <absl.flags._flag.Flag object at 0x000000000958C208>,
'visualize': <absl.flags._flag.BooleanFlag object at 0x000000000C3BFCC0>}
---------
Variables: name (type shape) [size]
---------
generator/g_h0_lin/Matrix:0 (float32_ref 100x4608) [460800, bytes: 1843200]
generator/g_h0_lin/bias:0 (float32_ref 4608) [4608, bytes: 18432]
generator/g_bn0/beta:0 (float32_ref 512) [512, bytes: 2048]
generator/g_bn0/gamma:0 (float32_ref 512) [512, bytes: 2048]
generator/g_h1/w:0 (float32_ref 5x5x256x512) [3276800, bytes: 13107200]
generator/g_h1/biases:0 (float32_ref 256) [256, bytes: 1024]
generator/g_bn1/beta:0 (float32_ref 256) [256, bytes: 1024]
generator/g_bn1/gamma:0 (float32_ref 256) [256, bytes: 1024]
generator/g_h2/w:0 (float32_ref 5x5x128x256) [819200, bytes: 3276800]
generator/g_h2/biases:0 (float32_ref 128) [128, bytes: 512]
generator/g_bn2/beta:0 (float32_ref 128) [128, bytes: 512]
generator/g_bn2/gamma:0 (float32_ref 128) [128, bytes: 512]
generator/g_h3/w:0 (float32_ref 5x5x64x128) [204800, bytes: 819200]
generator/g_h3/biases:0 (float32_ref 64) [64, bytes: 256]
generator/g_bn3/beta:0 (float32_ref 64) [64, bytes: 256]
generator/g_bn3/gamma:0 (float32_ref 64) [64, bytes: 256]
generator/g_h4/w:0 (float32_ref 5x5x3x64) [4800, bytes: 19200]
generator/g_h4/biases:0 (float32_ref 3) [3, bytes: 12]
discriminator/d_h0_conv/w:0 (float32_ref 5x5x3x64) [4800, bytes: 19200]
discriminator/d_h0_conv/biases:0 (float32_ref 64) [64, bytes: 256]
discriminator/d_h1_conv/w:0 (float32_ref 5x5x64x128) [204800, bytes: 819200]
discriminator/d_h1_conv/biases:0 (float32_ref 128) [128, bytes: 512]
discriminator/d_bn1/beta:0 (float32_ref 128) [128, bytes: 512]
discriminator/d_bn1/gamma:0 (float32_ref 128) [128, bytes: 512]
discriminator/d_h2_conv/w:0 (float32_ref 5x5x128x256) [819200, bytes: 3276800]
discriminator/d_h2_conv/biases:0 (float32_ref 256) [256, bytes: 1024]
discriminator/d_bn2/beta:0 (float32_ref 256) [256, bytes: 1024]
discriminator/d_bn2/gamma:0 (float32_ref 256) [256, bytes: 1024]
discriminator/d_h3_conv/w:0 (float32_ref 5x5x256x512) [3276800, bytes: 13107200]
discriminator/d_h3_conv/biases:0 (float32_ref 512) [512, bytes: 2048]
discriminator/d_bn3/beta:0 (float32_ref 512) [512, bytes: 2048]
discriminator/d_bn3/gamma:0 (float32_ref 512) [512, bytes: 2048]
discriminator/d_h4_lin/Matrix:0 (float32_ref 4608x1) [4608, bytes: 18432]
discriminator/d_h4_lin/bias:0 (float32_ref 1) [1, bytes: 4]
Total size of variables: 9086340
Total bytes of variables: 36345360
[*] Reading checkpoints...
[*] Success to read DCGAN.model-2
[*] Load SUCCESS
Epoch: [ 0/ 2] [ 0/ 800] time: 38.8909, d_loss: 4.83695269, g_loss: 0.01604199
Epoch: [ 0/ 2] [ 1/ 800] time: 75.9409, d_loss: 4.21985102, g_loss: 0.03411261
Epoch: [ 0/ 2] [ 2/ 800] time: 112.8350, d_loss: 4.44241142, g_loss: 0.02101352
Epoch: [ 0/ 2] [ 3/ 800] time: 149.5263, d_loss: 3.07594109, g_loss: 0.11336002
Epoch: [ 0/ 2] [ 4/ 800] time: 186.3891, d_loss: 2.70502377, g_loss: 0.14985262
Epoch: [ 0/ 2] [ 5/ 800] time: 223.3300, d_loss: 3.69357109, g_loss: 0.04717619
Epoch: [ 0/ 2] [ 6/ 800] time: 260.0525, d_loss: 2.17558765, g_loss: 0.68981493
Epoch: [ 0/ 2] [ 7/ 800] time: 297.1181, d_loss: 5.51236010, g_loss: 0.00628419
Epoch: [ 0/ 2] [ 8/ 800] time: 333.8094, d_loss: 2.00994205, g_loss: 0.82554901
Epoch: [ 0/ 2] [ 9/ 800] time: 370.4227, d_loss: 5.24547815, g_loss: 0.01088684
Epoch: [ 0/ 2] [ 10/ 800] time: 407.0671, d_loss: 2.80249119, g_loss: 1.36248946
Epoch: [ 0/ 2] [ 11/ 800] time: 443.8676, d_loss: 5.26725864, g_loss: 0.01024086
Epoch: [ 0/ 2] [ 12/ 800] time: 480.6368, d_loss: 1.86196470, g_loss: 1.17058265
Epoch: [ 0/ 2] [ 13/ 800] time: 517.5933, d_loss: 4.18832588, g_loss: 0.02691788
Epoch: [ 0/ 2] [ 14/ 800] time: 554.1754, d_loss: 2.07127762, g_loss: 2.26849294
Epoch: [ 0/ 2] [ 15/ 800] time: 590.8510, d_loss: 4.49704552, g_loss: 0.01644055
Epoch: [ 0/ 2] [ 16/ 800] time: 627.6671, d_loss: 1.76221132, g_loss: 2.19296288
Epoch: [ 0/ 2] [ 17/ 800] time: 664.5924, d_loss: 3.17999744, g_loss: 0.08178606
Epoch: [ 0/ 2] [ 18/ 800] time: 701.6112, d_loss: 1.68936574, g_loss: 3.26065779
Epoch: [ 0/ 2] [ 19/ 800] time: 738.1621, d_loss: 3.68083525, g_loss: 0.05507284
Epoch: [ 0/ 2] [ 20/ 800] time: 774.7442, d_loss: 1.62791634, g_loss: 1.72477102
Epoch: [ 0/ 2] [ 21/ 800] time: 811.2326, d_loss: 4.06185627, g_loss: 0.03332135
Epoch: [ 0/ 2] [ 22/ 800] time: 848.3139, d_loss: 0.83045113, g_loss: 3.93568897
Epoch: [ 0/ 2] [ 23/ 800] time: 884.9740, d_loss: 3.16240478, g_loss: 0.05494529
Epoch: [ 0/ 2] [ 24/ 800] time: 921.7744, d_loss: 1.69060552, g_loss: 1.86502504
Epoch: [ 0/ 2] [ 25/ 800] time: 958.3253, d_loss: 4.17921877, g_loss: 0.03710852
[Cancelled]
我算了一下，就算跑一个epoch也要38个小时，用的是家里的电脑，所以果断放弃了，这个还真只能等有好机器时才能试了，用cpu来跑是不可能的了，必须要有GPU才行啊！~~希望有土豪机路过可以来试下。但别忘了把结果告我下喔