- 08 1月, 2020 1 次提交
-
-
由 Double_V 提交于
1. Add a new input named batch_roi_nums for prroi_pool_op. batch_roi_nums includes the number of roi for each image in batch when rois is Tensor. This information is saved in rois's lod when rois is LoDTensor. 2. add grad check to prroi_pool_op and solve unnormal X grad diff in CPU.
-
- 11 10月, 2019 1 次提交
-
-
由 wopeizl 提交于
* fix the precise roi poop op test=develop add roi backward implementation, fix the output-channel
-
- 19 9月, 2019 1 次提交
-
-
由 wopeizl 提交于
* add precise roi pooling op test=develop * test=develop * test=develop * test=develop * test=develop * test=develop * test=develop * test=develop * test=develop * test=develop * test=develop * test=develop * test=develop * test=develop * detail the description test=develop * test=develop * elaborate the doc for return type test=develop * test=develop
-