Merge pull request #15901 from heavengate/release/1.3

heavengate · web-flow · commit b1e5699412d0 · 2019-02-25T14:49:19.000+08:00
cherry-pick pool/adaptive_pool/yolov3_loss doc fix
diff --git a/paddle/fluid/operators/detection/yolov3_loss_op.cc b/paddle/fluid/operators/detection/yolov3_loss_op.cc
@@ -144,34 +144,40 @@ class Yolov3LossOpMaker : public framework::OpProtoAndCheckerMaker {
                    "The ignore threshold to ignore confidence loss.")
         .SetDefault(0.7);
     AddComment(R"DOC(
-         This operator generate yolov3 loss by given predict result and ground
+         This operator generates yolov3 loss based on given predict result and ground
          truth boxes.
          
          The output of previous network is in shape [N, C, H, W], while H and W
-         should be the same, specify the grid size, each grid point predict given
-         number boxes, this given number is specified by anchors, it should be 
-         half anchors length, which following will be represented as S. In the 
-         second dimention(the channel dimention), C should be S * (class_num + 5),
-         class_num is the box categoriy number of source dataset(such as coco), 
-         so in the second dimention, stores 4 box location coordinates x, y, w, h 
-         and confidence score of the box and class one-hot key of each anchor box.
+         should be the same, H and W specify the grid size, each grid point predict 
+         given number boxes, this given number, which following will be represented as S,
+         is specified by the number of anchors, In the second dimension(the channel
+         dimension), C should be equal to S * (class_num + 5), class_num is the object 
+         category number of source dataset(such as 80 in coco dataset), so in the 
+         second(channel) dimension, apart from 4 box location coordinates x, y, w, h, 
+         also includes confidence score of the box and class one-hot key of each anchor box.
 
-         While the 4 location coordinates if $$tx, ty, tw, th$$, the box predictions
-         correspnd to:
+         Assume the 4 location coordinates are :math:`t_x, t_y, t_w, t_h`, the box predictions
+         should be as follows:
 
          $$
-         b_x = \sigma(t_x) + c_x
-         b_y = \sigma(t_y) + c_y
+         b_x = \\sigma(t_x) + c_x
+         $$
+         $$
+         b_y = \\sigma(t_y) + c_y
+         $$
+         $$
          b_w = p_w e^{t_w}
+         $$
+         $$
          b_h = p_h e^{t_h}
          $$
 
-         While $$c_x, c_y$$ is the left top corner of current grid and $$p_w, p_h$$
-         is specified by anchors.
+         In the equation above, :math:`c_x, c_y` is the left top corner of current grid
+         and :math:`p_w, p_h` is specified by anchors.
 
          As for confidence score, it is the logistic regression value of IoU between
          anchor boxes and ground truth boxes, the score of the anchor box which has 
-         the max IoU should be 1, and if the anchor box has IoU bigger then ignore 
+         the max IoU should be 1, and if the anchor box has IoU bigger than ignore 
          thresh, the confidence score loss of this anchor box will be ignored.
 
          Therefore, the yolov3 loss consist of three major parts, box location loss,
@@ -186,13 +192,13 @@ class Yolov3LossOpMaker : public framework::OpProtoAndCheckerMaker {
 
          In order to trade off box coordinate losses between big boxes and small 
          boxes, box coordinate losses will be mutiplied by scale weight, which is
-         calculated as follow.
+         calculated as follows.
 
          $$
          weight_{box} = 2.0 - t_w * t_h
          $$
 
-         Final loss will be represented as follow.
+         Final loss will be represented as follows.
 
          $$
          loss = (loss_{xy} + loss_{wh}) * weight_{box}
diff --git a/paddle/fluid/operators/pool_op.cc b/paddle/fluid/operators/pool_op.cc
@@ -168,9 +168,10 @@ void Pool2dOpMaker::Make() {
                             "be ignored.");  // TODO(Chengduo): Add checker.
                                              // (Currently,
   // TypedAttrChecker don't support vector type.)
-  AddAttr<bool>("global_pooling",
-                "(bool, default false) Whether to use the global pooling. "
-                "If global_pooling = true, ksize and paddings will be ignored.")
+  AddAttr<bool>(
+      "global_pooling",
+      "(bool, default false) Whether to use the global pooling. "
+      "If global_pooling = true, kernel size and paddings will be ignored.")
       .SetDefault(false);
   AddAttr<std::vector<int>>("strides",
                             "(vector<int>, default {1, 1}), strides(height, "
@@ -182,7 +183,7 @@ void Pool2dOpMaker::Make() {
       "paddings",
       "(vector<int>, default {0,0}), paddings(height, width) of pooling "
       "operator."
-      "If global_pooling = true, paddings and ksize will be ignored.")
+      "If global_pooling = true, paddings and kernel size will be ignored.")
       .SetDefault({0, 0});
   AddAttr<bool>(
       "exclusive",
@@ -204,7 +205,7 @@ void Pool2dOpMaker::Make() {
       .SetDefault(false);
   AddAttr<bool>(
       "ceil_mode",
-      "(bool, default false) Wether to use the ceil function to calculate "
+      "(bool, default false) Whether to use the ceil function to calculate "
       "output height and width. False is the default. If it is set to False, "
       "the floor function will be used.")
       .SetDefault(false);
@@ -259,31 +260,40 @@ The input(X) size and output(Out) size may be different.
        W_{out} = \\frac{(W_{in} - ksize[1] + 2 * paddings[1] + strides[1] - 1)}{strides[1]} + 1
        $$
 
-  For exclusive = true:
+  For exclusive = false:
        $$
        hstart = i * strides[0] - paddings[0]
+       $$
+       $$
        hend = hstart + ksize[0]
+       $$
+       $$
        wstart = j * strides[1] - paddings[1]
+       $$
+       $$
        wend = wstart + ksize[1]
+       $$
+       $$
        Output(i ,j) = \\frac{sum(Input[hstart:hend, wstart:wend])}{ksize[0] * ksize[1]}
        $$
-  For exclusive = false:
+
+  For exclusive = true:
        $$
        hstart = max(0, i * strides[0] - paddings[0])
+       $$
+       $$
        hend = min(H, hstart + ksize[0])
+       $$
+       $$
        wstart = max(0, j * strides[1] - paddings[1])
+       $$
+       $$
        wend = min(W, wstart + ksize[1])
+       $$
+       $$
        Output(i ,j) = \\frac{sum(Input[hstart:hend, wstart:wend])}{(hend - hstart) * (wend - wstart)}
        $$
 
-  For adaptive = true:
-      $$
-      hstart = floor(i * H_{in} / H_{out})
-      hend = ceil((i + 1) * H_{in} / H_{out})
-      wstart = floor(j * W_{in} / W_{out})
-      wend = ceil((j + 1) * W_{in} / W_{out})
-      Output(i ,j) = \\frac{sum(Input[hstart:hend, wstart:wend])}{(hend - hstart) * (wend - wstart)}
-      $$
 )DOC");
 }
 
@@ -324,7 +334,7 @@ void Pool3dOpMaker::Make() {
   AddAttr<bool>(
       "global_pooling",
       "(bool, default false) Whether to use the global pooling. "
-      "If global_pooling = true, ksize and paddings wille be ignored.")
+      "If global_pooling = true, kernel size and paddings will be ignored.")
       .SetDefault(false);
   AddAttr<std::vector<int>>(
       "strides",
@@ -359,7 +369,7 @@ void Pool3dOpMaker::Make() {
       .SetDefault(false);
   AddAttr<bool>(
       "ceil_mode",
-      "(bool, default false) Wether to use the ceil function to calculate "
+      "(bool, default false) Whether to use the ceil function to calculate "
       "output height and width. False is the default. If it is set to False, "
       "the floor function will be used.")
       .SetDefault(false);
@@ -392,48 +402,68 @@ width, respectively. The input(X) size and output(Out) size may be different.
   Output:
        Out shape: $(N, C, D_{out}, H_{out}, W_{out})$
   For ceil_mode = false:
-  $$
-       D_{out} = \frac{(D_{in} - ksize[0] + 2 * paddings[0])}{strides[0]} + 1 \\
-       H_{out} = \frac{(H_{in} - ksize[1] + 2 * paddings[1])}{strides[1]} + 1 \\
-       W_{out} = \frac{(W_{in} - ksize[2] + 2 * paddings[2])}{strides[2]} + 1
-  $$
+       $$
+       D_{out} = \\frac{(D_{in} - ksize[0] + 2 * paddings[0])}{strides[0]} + 1
+       $$
+       $$
+       H_{out} = \\frac{(H_{in} - ksize[1] + 2 * paddings[1])}{strides[2]} + 1
+       $$
+       $$
+       W_{out} = \\frac{(W_{in} - ksize[2] + 2 * paddings[2])}{strides[2]} + 1
+       $$
   For ceil_mode = true:
-  $$
-       D_{out} = \frac{(D_{in} - ksize[0] + 2 * paddings[0] + strides[0] -1)}{strides[0]} + 1 \\
-       H_{out} = \frac{(H_{in} - ksize[1] + 2 * paddings[1] + strides[1] -1)}{strides[1]} + 1 \\
-       W_{out} = \frac{(W_{in} - ksize[2] + 2 * paddings[2] + strides[2] -1)}{strides[2]} + 1
-  $$
-  For exclusive = true:
-  $$
-  dstart = i * strides[0] - paddings[0]
-  dend = dstart + ksize[0]
-  hstart = j * strides[1] - paddings[1]
-  hend = hstart + ksize[1]
-  wstart = k * strides[2] - paddings[2]
-  wend = wstart + ksize[2]
-  Output(i ,j, k) = \\frac{sum(Input[dstart:dend, hstart:hend, wstart:wend])}{ksize[0] * ksize[1] * ksize[2]}
-  $$
+       $$
+       D_{out} = \\frac{(D_{in} - ksize[0] + 2 * paddings[0] + strides[0] -1)}{strides[0]} + 1
+       $$
+       $$
+       H_{out} = \\frac{(H_{in} - ksize[1] + 2 * paddings[1] + strides[1] -1)}{strides[1]} + 1
+       $$
+       $$
+       W_{out} = \\frac{(W_{in} - ksize[2] + 2 * paddings[2] + strides[2] -1)}{strides[2]} + 1
+       $$
+
   For exclusive = false:
-  $$
-  dstart = max(0, i * strides[0] - paddings[0])
-  dend = min(D, dstart + ksize[0])
-  hstart = max(0, j * strides[1] - paddings[1])
-  hend = min(H, hstart + ksize[1])
-  wstart = max(0, k * strides[2] - paddings[2])
-  wend = min(W, wstart + ksize[2])
-  Output(i ,j, k) = \\frac{sum(Input[dstart:dend, hstart:hend, wstart:wend])}{(dend - dstart) * (hend - hstart) * (wend - wstart)}
-  $$
-
-  For adaptive = true:
-  $$
-  dstart = floor(i * D_{in} / D_{out})
-  dend = ceil((i + 1) * D_{in} / D_{out})
-  hstart = floor(j * H_{in} / H_{out})
-  hend = ceil((j + 1) * H_{in} / H_{out})
-  wstart = floor(k * W_{in} / W_{out})
-  wend = ceil((k + 1) * W_{in} / W_{out})
-  Output(i ,j, k) = \\frac{sum(Input[dstart:dend, hstart:hend, wstart:wend])}{(dend - dstart) * (hend - hstart) * (wend - wstart)}
-  $$
+       $$
+       dstart = i * strides[0] - paddings[0]
+       $$
+       $$
+       dend = dstart + ksize[0]
+       $$
+       $$
+       hstart = j * strides[1] - paddings[1]
+       $$
+       $$
+       hend = hstart + ksize[1]
+       $$
+       $$
+       wstart = k * strides[2] - paddings[2]
+       $$
+       $$
+       wend = wstart + ksize[2]
+       $$
+       $$
+       Output(i ,j, k) = \\frac{sum(Input[dstart:dend, hstart:hend, wstart:wend])}{ksize[0] * ksize[1] * ksize[2]}
+       $$
+
+  For exclusive = true:
+       $$
+       dstart = max(0, i * strides[0] - paddings[0])
+       $$
+       $$
+       dend = min(D, dstart + ksize[0])
+       $$
+       $$
+       hend = min(H, hstart + ksize[1])
+       $$
+       $$
+       wstart = max(0, k * strides[2] - paddings[2])
+       $$
+       $$
+       wend = min(W, wstart + ksize[2])
+       $$
+       $$
+       Output(i ,j, k) = \\frac{sum(Input[dstart:dend, hstart:hend, wstart:wend])}{(dend - dstart) * (hend - hstart) * (wend - wstart)}
+       $$
 
 )DOC");
 }
diff --git a/python/paddle/fluid/layers/detection.py b/python/paddle/fluid/layers/detection.py
@@ -545,15 +545,16 @@ def yolov3_loss(x,
         TypeError: Attr ignore_thresh of yolov3_loss must be a float number
 
     Examples:
-    .. code-block:: python
-
-        x = fluid.layers.data(name='x', shape=[255, 13, 13], dtype='float32')
-        gtbox = fluid.layers.data(name='gtbox', shape=[6, 5], dtype='float32')
-        gtlabel = fluid.layers.data(name='gtlabel', shape=[6, 1], dtype='int32')
-        anchors = [10, 13, 16, 30, 33, 23, 30, 61, 62, 45, 59, 119, 116, 90, 156, 198, 373, 326]
-        anchors = [0, 1, 2]
-        loss = fluid.layers.yolov3_loss(x=x, gtbox=gtbox, class_num=80, anchors=anchors, 
-                                        ignore_thresh=0.5, downsample_ratio=32)
+      .. code-block:: python
+
+          x = fluid.layers.data(name='x', shape=[255, 13, 13], dtype='float32')
+          gtbox = fluid.layers.data(name='gtbox', shape=[6, 5], dtype='float32')
+          gtlabel = fluid.layers.data(name='gtlabel', shape=[6, 1], dtype='int32')
+          anchors = [10, 13, 16, 30, 33, 23, 30, 61, 62, 45, 59, 119, 116, 90, 156, 198, 373, 326]
+          anchor_mask = [0, 1, 2]
+          loss = fluid.layers.yolov3_loss(x=x, gtbox=gtbox, gtlabel=gtlabel, anchors=anchors, 
+                                          anchor_mask=anchor_mask, class_num=80,
+                                          ignore_thresh=0.7, downsample_ratio=32)
     """
     helper = LayerHelper('yolov3_loss', **locals())
 
diff --git a/python/paddle/fluid/layers/nn.py b/python/paddle/fluid/layers/nn.py
