diff --git a/image_classification/README.md b/image_classification/README.md
index 0010fe5b0a106b3be0d31e91877bd99d3a55f9e8..39167fa19efa13b4c101227e1111269e63a7ec55 100644
--- a/image_classification/README.md
+++ b/image_classification/README.md
@@ -123,6 +123,11 @@ optimizer = paddle.optimizer.Momentum(
     learning_rate_schedule="discexp", )
 ```
 
+通过 `learning_rate_decay_a` (简写$a$） 、`learning_rate_decay_b` (简写$b$) 和 `learning_rate_schedule` 指定学习率调整策略，这里采用离散指数的方式调节学习率，计算公式如下， $n$ 代表已经处理过的累计总样本数，$lr_{0}$ 即为参数里设置的 `learning_rate`。
+
+$$  lr = lr_{0} * a^ {\lfloor \frac{n}{ b}\rfloor} $$
+
+
 ### 定义数据读取方法和事件处理程序
 
 读取数据时需要分别指定训练集和验证集的图像列表文件，这里假设这两个文件分别为`train.list`和`val.list`。
diff --git a/image_classification/googlenet.py b/image_classification/googlenet.py
index 2e4153ccb66291625360a21df746e374d92b6ed4..e21a0360249bd386d77ce7c9ef639a45347b19a0 100644
--- a/image_classification/googlenet.py
+++ b/image_classification/googlenet.py
@@ -3,56 +3,6 @@ import paddle.v2 as paddle
 __all__ = ['googlenet']
 
 
-def inception(name, input, channels, filter1, filter3R, filter3, filter5R,
-              filter5, proj):
-    cov1 = paddle.layer.conv_projection(
-        input=input,
-        filter_size=1,
-        num_channels=channels,
-        num_filters=filter1,
-        stride=1,
-        padding=0)
-
-    cov3r = paddle.layer.img_conv(
-        name=name + '_3r',
-        input=input,
-        filter_size=1,
-        num_channels=channels,
-        num_filters=filter3R,
-        stride=1,
-        padding=0)
-    cov3 = paddle.layer.conv_projection(
-        input=cov3r, filter_size=3, num_filters=filter3, stride=1, padding=1)
-
-    cov5r = paddle.layer.img_conv(
-        name=name + '_5r',
-        input=input,
-        filter_size=1,
-        num_channels=channels,
-        num_filters=filter5R,
-        stride=1,
-        padding=0)
-    cov5 = paddle.layer.conv_projection(
-        input=cov5r, filter_size=5, num_filters=filter5, stride=1, padding=2)
-
-    pool1 = paddle.layer.img_pool(
-        name=name + '_max',
-        input=input,
-        pool_size=3,
-        num_channels=channels,
-        stride=1,
-        padding=1)
-    covprj = paddle.layer.conv_projection(
-        input=pool1, filter_size=1, num_filters=proj, stride=1, padding=0)
-
-    cat = paddle.layer.concat(
-        name=name,
-        input=[cov1, cov3, cov5, covprj],
-        bias_attr=True,
-        act=paddle.activation.Relu())
-    return cat
-
-
 def inception2(name, input, channels, filter1, filter3R, filter3, filter5R,
                filter5, proj):
     cov1 = paddle.layer.img_conv(
diff --git a/image_classification/resnet.py b/image_classification/resnet.py
index 7ef551b3bb7ff946d3a316b066fd4c5f7c59ecbe..63bc4409b79f2d77e13efb3ce3b6e51ec6973065 100644
--- a/image_classification/resnet.py
+++ b/image_classification/resnet.py
@@ -31,7 +31,6 @@ def shortcut(input, n_out, stride, b_projection):
 
 
 def basicblock(input, ch_out, stride, b_projection):
-    # TODO: bug fix for ch_in = input.num_filters
     conv1 = conv_bn_layer(input, ch_out, 3, stride, 1)
     conv2 = conv_bn_layer(conv1, ch_out, 3, 1, 1, paddle.activation.Linear())
     short = shortcut(input, ch_out, stride, b_projection)
@@ -40,7 +39,6 @@ def basicblock(input, ch_out, stride, b_projection):
 
 
 def bottleneck(input, ch_out, stride, b_projection):
-    # TODO: bug fix for ch_in = input.num_filters
     conv1 = conv_bn_layer(input, ch_out, 1, stride, 0)
     conv2 = conv_bn_layer(conv1, ch_out, 3, 1, 1)
     conv3 = conv_bn_layer(conv2, ch_out * 4, 1, 1, 0,