Merge pull request #312 from guoshengCS/fix-resnet

Fix ResNet in image classification.

image_classification/resnet.py

@@ -22,24 +22,24 @@ def conv_bn_layer(input,
     return paddle.layer.batch_norm(input=tmp, act=active_type)
 
 
-def shortcut(input, ch_in, ch_out, stride):
-    if ch_in != ch_out:
+def shortcut(input, ch_out, stride):
+    if input.num_filters != ch_out:
         return conv_bn_layer(input, ch_out, 1, stride, 0,
                              paddle.activation.Linear())
     else:
         return input
 
 
-def basicblock(input, ch_in, ch_out, stride):
-    short = shortcut(input, ch_in, ch_out, stride)
+def basicblock(input, ch_out, stride):
+    short = shortcut(input, ch_out, stride)
     conv1 = conv_bn_layer(input, ch_out, 3, stride, 1)
     conv2 = conv_bn_layer(conv1, ch_out, 3, 1, 1, paddle.activation.Linear())
     return paddle.layer.addto(
         input=[short, conv2], act=paddle.activation.Relu())
 
 
-def bottleneck(input, ch_in, ch_out, stride):
-    short = shortcut(input, ch_in, ch_out * 4, stride)
+def bottleneck(input, ch_out, stride):
+    short = shortcut(input, ch_out * 4, stride)
     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,
@@ -48,10 +48,10 @@ def bottleneck(input, ch_in, ch_out, stride):
         input=[short, conv3], act=paddle.activation.Relu())
 
 
-def layer_warp(block_func, input, ch_in, ch_out, count, stride):
-    conv = block_func(input, ch_in, ch_out, stride)
+def layer_warp(block_func, input, ch_out, count, stride):
+    conv = block_func(input, ch_out, stride)
     for i in range(1, count):
-        conv = block_func(conv, ch_out, ch_out, 1)
+        conv = block_func(conv, ch_out, 1)
     return conv
 
 
@@ -67,10 +67,10 @@ def resnet_imagenet(input, class_dim, depth=50):
     conv1 = conv_bn_layer(
         input, ch_in=3, ch_out=64, filter_size=7, stride=2, padding=3)
     pool1 = paddle.layer.img_pool(input=conv1, pool_size=3, stride=2)
-    res1 = layer_warp(block_func, pool1, 64, 64, stages[0], 1)
-    res2 = layer_warp(block_func, res1, 64, 128, stages[1], 2)
-    res3 = layer_warp(block_func, res2, 128, 256, stages[2], 2)
-    res4 = layer_warp(block_func, res3, 256, 512, stages[3], 2)
+    res1 = layer_warp(block_func, pool1, 64, stages[0], 1)
+    res2 = layer_warp(block_func, res1, 128, stages[1], 2)
+    res3 = layer_warp(block_func, res2, 256, stages[2], 2)
+    res4 = layer_warp(block_func, res3, 512, stages[3], 2)
     pool2 = paddle.layer.img_pool(
         input=res4, pool_size=7, stride=1, pool_type=paddle.pooling.Avg())
     out = paddle.layer.fc(