提交 4c9884e7 编写于 作者: J jerrywgz

refine unittest test=develop

上级 98c3294b
...@@ -132,7 +132,20 @@ class ROIAlignOpMaker : public framework::OpProtoAndCheckerMaker { ...@@ -132,7 +132,20 @@ class ROIAlignOpMaker : public framework::OpProtoAndCheckerMaker {
"and pooled_w, likewise for height") "and pooled_w, likewise for height")
.SetDefault(-1); .SetDefault(-1);
AddComment(R"DOC( AddComment(R"DOC(
**RoIAlign Operator**
Region of interest align (also known as RoI align) is to perform
bilinear interpolation on inputs of nonuniform sizes to obtain
fixed-size feature maps (e.g. 7*7)
Dividing each region proposal into equal-sized sections with
the pooled_width and pooled_height. Location remains the origin
result.
In each ROI bin, the value of the four regularly sampled locations
are computed directly through bilinear interpolation. The output is
the mean of four locations.
Thus avoid the misaligned problem.
)DOC"); )DOC");
} }
}; };
......
...@@ -167,4 +167,4 @@ class TestROIAlignOp(OpTest): ...@@ -167,4 +167,4 @@ class TestROIAlignOp(OpTest):
self.check_output() self.check_output()
def test_check_grad(self): def test_check_grad(self):
self.check_grad(['X'], 'Out', max_relative_error=0.005) self.check_grad(['X'], 'Out')
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册