update reader and spade (#3400)

PaddleCV/PaddleGAN/README.md

@@ -24,6 +24,7 @@
 3. CGAN和DCGAN两个模型训练使用的数据集为MNIST数据集；StarGAN，AttGAN和STGAN的数据集为CelebA数据集。Pix2Pix和CycleGAN支持的数据集可以参考download.py中的cycle_pix_dataset。
 4. PaddlePaddle1.5.1及之前的版本不支持在AttGAN和STGAN模型里的判别器加上的instance norm。如果要在判别器中加上instance norm，请源码编译develop分支并安装。
 5. 中间效果图保存在${output_dir}/test文件夹中。对于Pix2Pix来说，inputA 和inputB 代表输入的两种风格的图片，fakeB表示生成图片；对于CycleGAN来说，inputA表示输入图片，fakeB表示inputA根据生成的图片，cycA表示fakeB经过生成器重构出来的对应于inputA的重构图片；对于StarGAN，AttGAN和STGAN来说，第一行表示原图，之后的每一行都代表一种属性变换。
+6. infer过程使用的test_list文件和训练过程中使用的train_list具有相同格式，第一行为样本数量，第二行为属性，之后的行中第一个表示图片名称，之后的-1和1表示该图片是否拥有该属性(1为有该属性，-1为没有该属性)。
 
 图像生成模型库库的目录结构如下：
 ```
@@ -139,6 +140,7 @@ StarGAN, AttGAN和STGAN所需要的[Celeba](http://mmlab.ie.cuhk.edu.hk/projects
     python infer.py \
       --model_net=$(StarGAN_or_AttGAN_or_STGAN) \
       --init_model=$(path_to_init_model)\
+      --test_list=$(path_to_test_list)\
       --dataset_dir=$(path_to_data)
 
 Pix2Pix和CycleGAN的效果如图所示：

PaddleCV/PaddleGAN/data_reader.py

@@ -237,8 +237,8 @@ class triplex_reader_creator(reader_creator):
             batch_size=batch_size,
             mode=mode)
 
-    self.name2id = {}
-    self.id2name = {}
+        self.name2id = {}
+        self.id2name = {}
 
     def make_reader(self, args, return_name=False):
         print(self.image_dir, self.list_filename)
@@ -376,13 +376,18 @@ class celeba_reader_creator(reader_creator):
             self.batch_size = args.batch_size
             self.shuffle = args.shuffle
             lines = lines[2:train_end]
-        else:
+        elif self.mode == 'TEST':
             self.batch_size = args.n_samples
             self.shuffle = False
-            if self.mode == "TEST":
-                lines = lines[train_end:test_end]
-            else:
-                lines = lines[test_end:]
+            lines = lines[train_end:test_end]
+        elif self.mode == 'VAL':
+            self.batch_size = args.n_samples
+            self.shuffle = False
+            lines = lines[2:]
+        else:
+            raise NotImplementedError(
+                "Wrong Reader MODE: {}, mode must in [TRAIN|TEST|VAL]".format(
+                    self.mode))
 
         self.images = []
         attr_names = args.selected_attrs.split(',')

PaddleCV/PaddleGAN/network/SPADE_network.py

@@ -20,6 +20,7 @@ from .base_network import conv2d, deconv2d, norm_layer, conv2d_spectral_norm
 import paddle.fluid as fluid
 import numpy as np
 
+
 class SPADE_model(object):
     def __init__(self):
         pass
@@ -30,80 +31,175 @@ class SPADE_model(object):
         sw = cfg.crop_width // (2**num_up_layers)
         sh = cfg.crop_height // (2**num_up_layers)
         seg = input
-        x = fluid.layers.resize_nearest(seg, out_shape=(sh, sw), align_corners=False)
-        x = conv2d(x, 16*nf,3,padding=1,name=name + "_fc",use_bias=True, is_test=is_test)
-        x = self.SPADEResnetBlock(x, seg, 16 * nf, 16 * nf, cfg, name=name+"_head_0", is_test=is_test)
-        x = fluid.layers.resize_nearest(x, scale=2, align_corners=False)
-        x = self.SPADEResnetBlock(x, seg, 16 * nf, 16 * nf, cfg, name=name+"_G_middle_0", is_test=is_test)
-        x = self.SPADEResnetBlock(x, seg, 16 * nf, 16 * nf, cfg, name=name+"_G_middle_1", is_test=is_test)
-        x = fluid.layers.resize_nearest(x, scale=2, align_corners=False)
-
-        x = self.SPADEResnetBlock(x, seg, 16 * nf, 8 * nf, cfg, name=name+"_up_0", is_test=is_test)
-        x = fluid.layers.resize_nearest(x, scale=2, align_corners=False)
-        x = self.SPADEResnetBlock(x, seg, 8 * nf, 4 * nf, cfg, name=name+"_up_1", is_test=is_test)
-        x = fluid.layers.resize_nearest(x, scale=2, align_corners=False)
-        x = self.SPADEResnetBlock(x, seg, 4 * nf, 2 * nf, cfg, name=name+"_up_2", is_test=is_test)
-        x = fluid.layers.resize_nearest(x, scale=2, align_corners=False)
-        x = self.SPADEResnetBlock(x, seg, 2 * nf, 1 * nf, cfg, name=name+"_up_3", is_test=is_test)
+        x = fluid.layers.resize_nearest(
+            seg, out_shape=(sh, sw), align_corners=False)
+        x = conv2d(
+            x,
+            16 * nf,
+            3,
+            padding=1,
+            name=name + "_fc",
+            use_bias=True,
+            is_test=is_test)
+        x = self.SPADEResnetBlock(
+            x,
+            seg,
+            16 * nf,
+            16 * nf,
+            cfg,
+            name=name + "_head_0",
+            is_test=is_test)
+        x = fluid.layers.resize_nearest(x, scale=2.0, align_corners=False)
+        x = self.SPADEResnetBlock(
+            x,
+            seg,
+            16 * nf,
+            16 * nf,
+            cfg,
+            name=name + "_G_middle_0",
+            is_test=is_test)
+        x = self.SPADEResnetBlock(
+            x,
+            seg,
+            16 * nf,
+            16 * nf,
+            cfg,
+            name=name + "_G_middle_1",
+            is_test=is_test)
+        x = fluid.layers.resize_nearest(x, scale=2.0, align_corners=False)
+
+        x = self.SPADEResnetBlock(
+            x, seg, 16 * nf, 8 * nf, cfg, name=name + "_up_0", is_test=is_test)
+        x = fluid.layers.resize_nearest(x, scale=2.0, align_corners=False)
+        x = self.SPADEResnetBlock(
+            x, seg, 8 * nf, 4 * nf, cfg, name=name + "_up_1", is_test=is_test)
+        x = fluid.layers.resize_nearest(x, scale=2.0, align_corners=False)
+        x = self.SPADEResnetBlock(
+            x, seg, 4 * nf, 2 * nf, cfg, name=name + "_up_2", is_test=is_test)
+        x = fluid.layers.resize_nearest(x, scale=2.0, align_corners=False)
+        x = self.SPADEResnetBlock(
+            x, seg, 2 * nf, 1 * nf, cfg, name=name + "_up_3", is_test=is_test)
         x = fluid.layers.leaky_relu(
             x, alpha=0.2, name=name + '_conv_img_leaky_relu')
-        x = conv2d(x, 3,3,padding=1,name=name + "_conv_img",use_bias=True, is_test=is_test)
+        x = conv2d(
+            x,
+            3,
+            3,
+            padding=1,
+            name=name + "_conv_img",
+            use_bias=True,
+            is_test=is_test)
         x = fluid.layers.tanh(x)
 
         return x
+
     def SPADEResnetBlock(self, x, seg, fin, fout, opt, name, is_test=False):
         learn_shortcut = (fin != fout)
         fmiddle = min(fin, fout)
         semantic_nc = opt.label_nc + (0 if opt.no_instance else 1)
         if learn_shortcut:
-            x_s = self.SPADE(x, seg, fin, name=name+".norm_s", is_test=is_test)
-            x_s = conv2d_spectral_norm(x_s, fout,1,use_bias=False, name=name + ".conv_s", is_test=is_test)
+            x_s = self.SPADE(
+                x, seg, fin, name=name + ".norm_s", is_test=is_test)
+            x_s = conv2d_spectral_norm(
+                x_s,
+                fout,
+                1,
+                use_bias=False,
+                name=name + ".conv_s",
+                is_test=is_test)
         else:
             x_s = x
-        dx = self.SPADE(x, seg, fin, name=name+".norm_0", is_test=is_test)
-        dx = fluid.layers.leaky_relu(dx, alpha=0.2, name=name+'_leaky_relu0')
-        dx = conv2d_spectral_norm(dx, fmiddle,3,padding=1,name=name + ".conv_0", use_bias=True, is_test=is_test)
-        
-        dx = self.SPADE(dx, seg, fmiddle, name=name+".norm_1", is_test=is_test)
-        dx = fluid.layers.leaky_relu(dx, alpha=0.2, name=name+'_leaky_relu1')
-        dx = conv2d_spectral_norm(dx, fout,3,padding=1,name=name + ".conv_1", use_bias=True, is_test=is_test)
+        dx = self.SPADE(x, seg, fin, name=name + ".norm_0", is_test=is_test)
+        dx = fluid.layers.leaky_relu(dx, alpha=0.2, name=name + '_leaky_relu0')
+        dx = conv2d_spectral_norm(
+            dx,
+            fmiddle,
+            3,
+            padding=1,
+            name=name + ".conv_0",
+            use_bias=True,
+            is_test=is_test)
+
+        dx = self.SPADE(
+            dx, seg, fmiddle, name=name + ".norm_1", is_test=is_test)
+        dx = fluid.layers.leaky_relu(dx, alpha=0.2, name=name + '_leaky_relu1')
+        dx = conv2d_spectral_norm(
+            dx,
+            fout,
+            3,
+            padding=1,
+            name=name + ".conv_1",
+            use_bias=True,
+            is_test=is_test)
 
         output = dx + x_s
         return output
 
-
     def SPADE(self, input, seg_map, norm_nc, name, is_test=False):
         nhidden = 128
         ks = 3
         pw = ks // 2
-        seg_map = fluid.layers.resize_nearest(seg_map, out_shape=input.shape[2:], align_corners=False)
-        actv = conv2d(seg_map, nhidden, ks, padding=pw, activation_fn='relu', name=name+".mlp_shared.0", use_bias=True)
-        gamma = conv2d(actv, norm_nc, ks, padding=pw, name=name+".mlp_gamma", use_bias=True)
-        beta = conv2d(actv, norm_nc, ks, padding=pw, name=name+".mlp_beta", use_bias=True)
+        seg_map = fluid.layers.resize_nearest(
+            seg_map, out_shape=input.shape[2:], align_corners=False)
+        actv = conv2d(
+            seg_map,
+            nhidden,
+            ks,
+            padding=pw,
+            activation_fn='relu',
+            name=name + ".mlp_shared.0",
+            use_bias=True)
+        gamma = conv2d(
+            actv,
+            norm_nc,
+            ks,
+            padding=pw,
+            name=name + ".mlp_gamma",
+            use_bias=True)
+        beta = conv2d(
+            actv,
+            norm_nc,
+            ks,
+            padding=pw,
+            name=name + ".mlp_beta",
+            use_bias=True)
         param_attr = fluid.ParamAttr(
             name=name + ".param_free_norm.weight",
-            initializer=fluid.initializer.Constant(value=1.0), trainable=False)
+            initializer=fluid.initializer.Constant(value=1.0),
+            trainable=False)
         bias_attr = fluid.ParamAttr(
-            name=name+".param_free_norm.bias", initializer=fluid.initializer.Constant(0.0), trainable=False)
-
-        norm = fluid.layers.batch_norm(input=input, name=name, param_attr=param_attr,
-        bias_attr=bias_attr, moving_mean_name=name+".param_free_norm.running_mean", moving_variance_name=name+".param_free_norm.running_var", is_test=is_test)
+            name=name + ".param_free_norm.bias",
+            initializer=fluid.initializer.Constant(0.0),
+            trainable=False)
+
+        norm = fluid.layers.batch_norm(
+            input=input,
+            name=name,
+            param_attr=param_attr,
+            bias_attr=bias_attr,
+            moving_mean_name=name + ".param_free_norm.running_mean",
+            moving_variance_name=name + ".param_free_norm.running_var",
+            is_test=is_test)
         out = norm * (1 + gamma) + beta
-        return out    
-
+        return out
 
     def network_D(self, input, name, cfg):
         num_D = 2
         result = []
         for i in range(num_D):
-            out = build_discriminator_Nlayers(input, name=name+"_%d"%i)
+            out = build_discriminator_Nlayers(input, name=name + "_%d" % i)
             result.append(out)
-            input = fluid.layers.pool2d(input, pool_size=3, pool_type="avg", pool_stride=2, pool_padding=1, name=name+"_pool%d"%i)
+            input = fluid.layers.pool2d(
+                input,
+                pool_size=3,
+                pool_type="avg",
+                pool_stride=2,
+                pool_padding=1,
+                name=name + "_pool%d" % i)
 
         return result
 
 
-
 def build_discriminator_Nlayers(input,
                                 name="discriminator",
                                 d_nlayers=4,
@@ -128,7 +224,7 @@ def build_discriminator_Nlayers(input,
     res_list.append(res1)
     for i in range(1, d_nlayers):
         conv_name = name + ".model{}.0.0".format(i)
-        nf = min(nf*2, 512)
+        nf = min(nf * 2, 512)
         stride = 1 if i == d_nlayers - 1 else 2
         dis_output = conv2d_spectral_norm(
             res_list[-1],
@@ -141,7 +237,8 @@ def build_discriminator_Nlayers(input,
             norm=norm_type,
             activation_fn='leaky_relu',
             relufactor=0.2,
-            use_bias=False, norm_affine=False)
+            use_bias=False,
+            norm_affine=False)
         res_list.append(dis_output)
     o_c4 = conv2d(
         res_list[-1],
@@ -154,4 +251,3 @@ def build_discriminator_Nlayers(input,
         use_bias=True)
     res_list.append(o_c4)
     return res_list
-