fix quick start code and doc

docs/en/tutorials/quick_start_en.md

@@ -40,33 +40,28 @@ cd ../../
 
 ## Environment
 
-### Set PYTHONPATH
-
-```bash
-export PYTHONPATH=./:$PYTHONPATH
-```
-
 ### Download pretrained model
 
+You can use the following commands to downdload the pretrained models.
 
 ```bash
-python tools/download.py -a ResNet50_vd -p ./pretrained -d True
-python tools/download.py -a ResNet50_vd_ssld -p ./pretrained -d True
-python tools/download.py -a MobileNetV3_large_x1_0 -p ./pretrained -d True
+mkdir pretrained
+cd pretrained
+wget https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_pretrained.tar
+wget https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_ssld_pretrained.tar
+wget https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x1_0_pretrained.tar
+tar -xf ResNet50_vd_pretrained.tar
+tar -xf ResNet50_vd_ssld_pretrained.tar
+tar -xf MobileNetV3_large_x1_0_pretrained.tar
+cd ../
 ```
 
-Paramters：
-+ `architecture`(shortname: a): model name.
-+ `path`(shortname: p) download path.
-+ `decompress`(shortname: d) whether to decompress.
-
+**Note**: If you want to download the pretrained models on Windows environment, you can copy the links to the web page and download, you can use the the thirdparty tools such as `7Zip` to uncompress the tar files.
 
+## Training
 
 * All experiments are running on the NVIDIA® Tesla® V100 sigle card.
 
-
-## Training
-
 ### Train from scratch
 
 * Train ResNet50_vd

docs/zh_CN/tutorials/install.md

@@ -9,7 +9,7 @@
 
 ## 二、安装PaddlePaddle
 
-运行PaddleClas需要PaddlePaddle Fluid v1.7或更高版本。请参照[安装文档](http://www.paddlepaddle.org.cn/install/quick)中的说明进行操作。
+运行PaddleClas需要`PaddlePaddle 2.0-beta`或更高版本。请参照[安装文档](http://www.paddlepaddle.org.cn/install/quick)中的说明进行操作。
 
 如果已经安装好了cuda、cudnn、nccl或者安装好了docker、nvidia-docker运行环境，可以pip安装最新GPU版本PaddlePaddle
 

docs/zh_CN/tutorials/quick_start.md

@@ -40,25 +40,23 @@ cd ../../
 
 ## 二、环境准备
 
-### 2.1 设置PYTHONPATH环境变量
+### 2.1 下载预训练模型
 
-```bash
-export PYTHONPATH=./:$PYTHONPATH
-```
-
-### 下载预训练模型
-通过tools/download.py下载所需要的预训练模型。
+通过下面的命令下载所需要的预训练模型。
 
 ```bash
-python tools/download.py -a ResNet50_vd -p ./pretrained -d True
-python tools/download.py -a ResNet50_vd_ssld -p ./pretrained -d True
-python tools/download.py -a MobileNetV3_large_x1_0 -p ./pretrained -d True
+mkdir pretrained
+cd pretrained
+wget https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_pretrained.tar
+wget https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_ssld_pretrained.tar
+wget https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x1_0_pretrained.tar
+tar -xf ResNet50_vd_pretrained.tar
+tar -xf ResNet50_vd_ssld_pretrained.tar
+tar -xf MobileNetV3_large_x1_0_pretrained.tar
+cd ../
 ```
 
-参数说明：
-+ `architecture`（简写 a）：模型结构
-+ `path`（简写 p）：下载路径
-+ `decompress` （简写 d）：是否解压
+**注意**：如果是在windows中下载预训练模型的话，需要把地址拷贝到网页中并下载，同时使用`7Zip`等工具进行解压。
 
 ### 2.2 环境说明
 
@@ -161,7 +159,7 @@ python -m paddle.distributed.launch \
 * 如果希望体验`3.6节`的知识蒸馏部分，可以首先保存训练得到的ResNet50_vd预训练模型到合适的位置，作为蒸馏时教师模型的预训练模型。脚本如下所示。
 
 ```shell
-cp -r output/ResNet50_vd/19/  ./pretrained/flowers102_R50_vd_final/
+cp -r output/ResNet50_vd/best_model/  ./pretrained/flowers102_R50_vd_final/
 ```
 
 ### 3.6 知识蒸馏小试牛刀

ppcls/modeling/architectures/resnet_vd.py

@@ -32,8 +32,7 @@ __all__ = [
 
 
 class ConvBNLayer(nn.Layer):
-    def __init__(
-            self,
+    def __init__(self,
                  num_channels,
                  num_filters,
                  filter_size,
@@ -41,9 +40,9 @@ class ConvBNLayer(nn.Layer):
                  groups=1,
                  is_vd_mode=False,
                  act=None,
-            name=None, ):
+                 lr_mult=1.0,
+                 name=None):
         super(ConvBNLayer, self).__init__()
-
         self.is_vd_mode = is_vd_mode
         self._pool2d_avg = AvgPool2d(
             kernel_size=2, stride=2, padding=0, ceil_mode=True)
@@ -54,7 +53,8 @@ class ConvBNLayer(nn.Layer):
             stride=stride,
             padding=(filter_size - 1) // 2,
             groups=groups,
-            weight_attr=ParamAttr(name=name + "_weights"),
+            weight_attr=ParamAttr(
+                name=name + "_weights", learning_rate=lr_mult),
             bias_attr=False)
         if name == "conv1":
             bn_name = "bn_" + name
@@ -83,6 +83,7 @@ class BottleneckBlock(nn.Layer):
                  stride,
                  shortcut=True,
                  if_first=False,
+                 lr_mult=1.0,
                  name=None):
         super(BottleneckBlock, self).__init__()
 
@@ -91,6 +92,7 @@ class BottleneckBlock(nn.Layer):
             num_filters=num_filters,
             filter_size=1,
             act='relu',
+            lr_mult=lr_mult,
             name=name + "_branch2a")
         self.conv1 = ConvBNLayer(
             num_channels=num_filters,
@@ -98,12 +100,14 @@ class BottleneckBlock(nn.Layer):
             filter_size=3,
             stride=stride,
             act='relu',
+            lr_mult=lr_mult,
             name=name + "_branch2b")
         self.conv2 = ConvBNLayer(
             num_channels=num_filters,
             num_filters=num_filters * 4,
             filter_size=1,
             act=None,
+            lr_mult=lr_mult,
             name=name + "_branch2c")
 
         if not shortcut:
@@ -137,6 +141,7 @@ class BasicBlock(nn.Layer):
                  stride,
                  shortcut=True,
                  if_first=False,
+                 lr_mult=1.0,
                  name=None):
         super(BasicBlock, self).__init__()
         self.stride = stride
@@ -178,7 +183,10 @@ class BasicBlock(nn.Layer):
 
 
 class ResNet_vd(nn.Layer):
-    def __init__(self, layers=50, class_dim=1000):
+    def __init__(self,
+                 layers=50,
+                 class_dim=1000,
+                 lr_mult_list=[1.0, 1.0, 1.0, 1.0, 1.0]):
         super(ResNet_vd, self).__init__()
 
         self.layers = layers
@@ -187,6 +195,16 @@ class ResNet_vd(nn.Layer):
             "supported layers are {} but input layer is {}".format(
                 supported_layers, layers)
 
+        self.lr_mult_list = lr_mult_list
+        assert isinstance(self.lr_mult_list, (
+            list, tuple
+        )), "lr_mult_list should be in (list, tuple) but got {}".format(
+            type(self.lr_mult_list))
+        assert len(
+            self.lr_mult_list
+        ) == 5, "lr_mult_list length should should be 5 but got {}".format(
+            len(self.lr_mult_list))
+
         if layers == 18:
             depth = [2, 2, 2, 2]
         elif layers == 34 or layers == 50:
@@ -207,6 +225,7 @@ class ResNet_vd(nn.Layer):
             filter_size=3,
             stride=2,
             act='relu',
+            lr_mult=self.lr_mult_list[0],
             name="conv1_1")
         self.conv1_2 = ConvBNLayer(
             num_channels=32,
@@ -214,6 +233,7 @@ class ResNet_vd(nn.Layer):
             filter_size=3,
             stride=1,
             act='relu',
+            lr_mult=self.lr_mult_list[0],
             name="conv1_2")
         self.conv1_3 = ConvBNLayer(
             num_channels=32,
@@ -221,6 +241,7 @@ class ResNet_vd(nn.Layer):
             filter_size=3,
             stride=1,
             act='relu',
+            lr_mult=self.lr_mult_list[0],
             name="conv1_3")
         self.pool2d_max = MaxPool2d(kernel_size=3, stride=2, padding=1)
 
@@ -245,6 +266,7 @@ class ResNet_vd(nn.Layer):
                             stride=2 if i == 0 and block != 0 else 1,
                             shortcut=shortcut,
                             if_first=block == i == 0,
+                            lr_mult=self.lr_mult_list[block + 1],
                             name=conv_name))
                     self.block_list.append(bottleneck_block)
                     shortcut = True
@@ -262,7 +284,8 @@ class ResNet_vd(nn.Layer):
                             stride=2 if i == 0 and block != 0 else 1,
                             shortcut=shortcut,
                             if_first=block == i == 0,
-                            name=conv_name))
+                            name=conv_name,
+                            lr_mult=lr_mult))
                     self.block_list.append(basic_block)
                     shortcut = True
 

ppcls/modeling/loss.py

@@ -53,9 +53,10 @@ class Loss(object):
         avg_cost = paddle.mean(cost)
         return avg_cost
 
-    def _kldiv(self, input, target):
-        cost = target * F.log(target / input) * self._class_dim
-        cost = paddle.sum(cost)
+    def _kldiv(self, input, target, name=None):
+        eps = 1.0e-10
+        cost = target * paddle.log(
+            (target + eps) / (input + eps)) * self._class_dim
         return cost
 
     def _jsdiv(self, input, target):