bishe

疑问：data[‘label’]是怎么存的，怎么会是(1,3,512,512)
adam优化器

make_source对应test：test_img，test_label_ori，test_head_ori，pose_source.npy
make_target对应train：train_img，train_label，head_img，pose.npy
normalization:
source_img = cv2.imread(‘./data/source/test_label_ori/00001.png’)[:,:,0]
source_img_rgb = cv2.imread(‘./data/source/test_img/00001.png’)
target_img = cv2.imread(‘./data/target/train/train_label/00001.png’)[:,:,0]
target_img_rgb = cv2.imread(‘./data/target/train/train_img/00001.png’)

save_dir = Path(‘./data/source/’)

prepare.py里
①Prepare test_real
这里很坑，写图片的时候多了空格，少了"/“，以至于全存在文件夹外
img: 将./data/target/train/train_img/xxx.png存在
./data/face/test_real/xxx.png
和./data/target/test_img/xxx.png
label: 将./data/target/train/train_label/xxx.png存在
./data/target/test_label/xxx.png
②Prepare test_sync
由’…/data/target/test_label/xxx.png’生成新图片
将生成的图片存在./face_enhancer/prepare/target/test_latest/images/
③Copy the synthesized images…
这里读图片多了个空格，写图片也少了”/"
将②中生成的图片存在./data/face/test_sync/xxx.png

用到vgg网络时self.vgg_features = vgg.make_layers(vgg.cfgs[‘D’])的cfg少了s我真的会谢

main.py里
取’…/data/face/test_real’里图片存入数据库
取’…/data/target/pose.npy’脸
进行模型训练

enhance.py里
取’…/data/face/test_real’里图片存入数据库（但注释里写的是test_sync）
取’…/data/source/pose_source_norm.npy’脸
把fake_head头拿出来放进generator生成残差后，加上fake_head
然后在fake_full中加入头的部分

loss:
label, inst, (real)image, feat
loss_G_GAN：
loss_G_GAN_Feat：
loss_G_VGG：
loss_D_real：
loss_D_fake：

模型打印：
#training images = 1069
self.use_features is [False]
self.gen_features is [False]
GlobalGenerator(
(model): Sequential(
(0): ReflectionPad2d((3, 3, 3, 3))
(1): Conv2d(18, 64, kernel_size=(7, 7), stride=(1, 1))
(2): InstanceNorm2d(64, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(3): ReLU(inplace=True)
(4): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(5): InstanceNorm2d(128, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(6): ReLU(inplace=True)
(7): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(8): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(9): ReLU(inplace=True)
(10): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(11): InstanceNorm2d(512, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(12): ReLU(inplace=True)
(13): Conv2d(512, 1024, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(14): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(15): ReLU(inplace=True)
(16): ResnetBlock(
(conv_block): Sequential(
(0): ReflectionPad2d((1, 1, 1, 1))
(1): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
(2): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(3): ReLU(inplace=True)
(4): ReflectionPad2d((1, 1, 1, 1))
(5): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
(6): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
)
)
(17): ResnetBlock(
(conv_block): Sequential(
(0): ReflectionPad2d((1, 1, 1, 1))
(1): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
(2): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(3): ReLU(inplace=True)
(4): ReflectionPad2d((1, 1, 1, 1))
(5): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
(6): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
)
)
(18): ResnetBlock(
(conv_block): Sequential(
(0): ReflectionPad2d((1, 1, 1, 1))
(1): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
(2): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(3): ReLU(inplace=True)
(4): ReflectionPad2d((1, 1, 1, 1))
(5): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
(6): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
)
)
(19): ResnetBlock(
(conv_block): Sequential(
(0): ReflectionPad2d((1, 1, 1, 1))
(1): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
(2): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(3): ReLU(inplace=True)
(4): ReflectionPad2d((1, 1, 1, 1))
(5): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
(6): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
)
)
(20): ResnetBlock(
(conv_block): Sequential(
(0): ReflectionPad2d((1, 1, 1, 1))
(1): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
(2): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(3): ReLU(inplace=True)
(4): ReflectionPad2d((1, 1, 1, 1))
(5): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
(6): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
)
)
(21): ResnetBlock(
(conv_block): Sequential(
(0): ReflectionPad2d((1, 1, 1, 1))
(1): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
(2): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(3): ReLU(inplace=True)
(4): ReflectionPad2d((1, 1, 1, 1))
(5): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
(6): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
)
)
(22): ResnetBlock(
(conv_block): Sequential(
(0): ReflectionPad2d((1, 1, 1, 1))
(1): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
(2): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(3): ReLU(inplace=True)
(4): ReflectionPad2d((1, 1, 1, 1))
(5): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
(6): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
)
)
(23): ResnetBlock(
(conv_block): Sequential(
(0): ReflectionPad2d((1, 1, 1, 1))
(1): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
(2): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(3): ReLU(inplace=True)
(4): ReflectionPad2d((1, 1, 1, 1))
(5): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
(6): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
)
)
(24): ResnetBlock(
(conv_block): Sequential(
(0): ReflectionPad2d((1, 1, 1, 1))
(1): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
(2): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(3): ReLU(inplace=True)
(4): ReflectionPad2d((1, 1, 1, 1))
(5): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
(6): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
)
)
(25): ConvTranspose2d(1024, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), output_padding=(1, 1))
(26): InstanceNorm2d(512, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(27): ReLU(inplace=True)
(28): ConvTranspose2d(512, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), output_padding=(1, 1))
(29): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(30): ReLU(inplace=True)
(31): ConvTranspose2d(256, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), output_padding=(1, 1))
(32): InstanceNorm2d(128, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(33): ReLU(inplace=True)
(34): ConvTranspose2d(128, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), output_padding=(1, 1))
(35): InstanceNorm2d(64, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(36): ReLU(inplace=True)
(37): ReflectionPad2d((3, 3, 3, 3))
(38): Conv2d(64, 3, kernel_size=(7, 7), stride=(1, 1))
(39): Tanh()
)
)
MultiscaleDiscriminator(
(scale0_layer0): Sequential(
(0): Conv2d(21, 64, kernel_size=(4, 4), stride=(2, 2), padding=(2, 2))
(1): LeakyReLU(negative_slope=0.2, inplace=True)
)
(scale0_layer1): Sequential(
(0): Conv2d(64, 128, kernel_size=(4, 4), stride=(2, 2), padding=(2, 2))
(1): InstanceNorm2d(128, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(2): LeakyReLU(negative_slope=0.2, inplace=True)
)
(scale0_layer2): Sequential(
(0): Conv2d(128, 256, kernel_size=(4, 4), stride=(2, 2), padding=(2, 2))
(1): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(2): LeakyReLU(negative_slope=0.2, inplace=True)
)
(scale0_layer3): Sequential(
(0): Conv2d(256, 512, kernel_size=(4, 4), stride=(1, 1), padding=(2, 2))
(1): InstanceNorm2d(512, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(2): LeakyReLU(negative_slope=0.2, inplace=True)
)
(scale0_layer4): Sequential(
(0): Conv2d(512, 1, kernel_size=(4, 4), stride=(1, 1), padding=(2, 2))
)
(scale1_layer0): Sequential(
(0): Conv2d(21, 64, kernel_size=(4, 4), stride=(2, 2), padding=(2, 2))
(1): LeakyReLU(negative_slope=0.2, inplace=True)
)
(scale1_layer1): Sequential(
(0): Conv2d(64, 128, kernel_size=(4, 4), stride=(2, 2), padding=(2, 2))
(1): InstanceNorm2d(128, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(2): LeakyReLU(negative_slope=0.2, inplace=True)
)
(scale1_layer2): Sequential(
(0): Conv2d(128, 256, kernel_size=(4, 4), stride=(2, 2), padding=(2, 2))
(1): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(2): LeakyReLU(negative_slope=0.2, inplace=True)
)
(scale1_layer3): Sequential(
(0): Conv2d(256, 512, kernel_size=(4, 4), stride=(1, 1), padding=(2, 2))
(1): InstanceNorm2d(512, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(2): LeakyReLU(negative_slope=0.2, inplace=True)
)
(scale1_layer4): Sequential(
(0): Conv2d(512, 1, kernel_size=(4, 4), stride=(1, 1), padding=(2, 2))
)
(downsample): AvgPool2d(kernel_size=3, stride=2, padding=[1, 1])
)

脸部：
GlobalGenerator(
(model): Sequential(
(0): ReflectionPad2d((3, 3, 3, 3))
(1): Conv2d(3, 64, kernel_size=(7, 7), stride=(1, 1))
(2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(3): ReLU(inplace=True)
(4): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(5): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(6): ReLU(inplace=True)
(7): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(8): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(9): ReLU(inplace=True)
(10): ResnetBlock(
(conv_block): Sequential(
(0): ReflectionPad2d((1, 1, 1, 1))
(1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(3): ReLU(inplace=True)
(4): ReflectionPad2d((1, 1, 1, 1))
(5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(6): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(11): ResnetBlock(
(conv_block): Sequential(
(0): ReflectionPad2d((1, 1, 1, 1))
(1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(3): ReLU(inplace=True)
(4): ReflectionPad2d((1, 1, 1, 1))
(5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(6): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(12): ResnetBlock(
(conv_block): Sequential(
(0): ReflectionPad2d((1, 1, 1, 1))
(1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(3): ReLU(inplace=True)
(4): ReflectionPad2d((1, 1, 1, 1))
(5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(6): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(13): ResnetBlock(
(conv_block): Sequential(
(0): ReflectionPad2d((1, 1, 1, 1))
(1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(3): ReLU(inplace=True)
(4): ReflectionPad2d((1, 1, 1, 1))
(5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(6): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(14): ResnetBlock(
(conv_block): Sequential(
(0): ReflectionPad2d((1, 1, 1, 1))
(1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(3): ReLU(inplace=True)
(4): ReflectionPad2d((1, 1, 1, 1))
(5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(6): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(15): ResnetBlock(
(conv_block): Sequential(
(0): ReflectionPad2d((1, 1, 1, 1))
(1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(3): ReLU(inplace=True)
(4): ReflectionPad2d((1, 1, 1, 1))
(5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(6): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(16): ConvTranspose2d(256, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), output_padding=(1, 1))
(17): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(18): ReLU(inplace=True)
(19): ConvTranspose2d(128, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), output_padding=(1, 1))
(20): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(21): ReLU(inplace=True)
(22): ReflectionPad2d((3, 3, 3, 3))
(23): Conv2d(64, 3, kernel_size=(7, 7), stride=(1, 1))
(24): Tanh()
)
)

NLayerDiscriminator(
(model): Sequential(
(0): Conv2d(3, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
(1): LeakyReLU(negative_slope=0.2, inplace=True)
(2): Conv2d(64, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), bias=False)
(3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(4): LeakyReLU(negative_slope=0.2, inplace=True)
(5): Conv2d(128, 256, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), bias=False)
(6): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(7): LeakyReLU(negative_slope=0.2, inplace=True)
)
(predictor): Sequential(
(0): Conv2d(256, 512, kernel_size=(4, 4), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.2, inplace=True)
(3): Conv2d(512, 1, kernel_size=(3, 3), stride=(1, 1))
(4): Sigmoid()
)
)