“3fcd16ede3dd71b269fed8ae213d18491b65f186”上不存在“paddle/fluid/ir/pass/pd_op_to_kernel_pass.h”
- 07 4月, 2020 1 次提交
-
-
由 wangguanzhong 提交于
* add devices_num on reader * refine capacity value * refine bufsize
-
- 17 2月, 2020 1 次提交
-
-
由 Yang Zhang 提交于
* Replace `switch` ops with `cond` * Use func instead of lambda
-
- 13 2月, 2020 1 次提交
-
-
由 Yang Zhang 提交于
-
- 30 12月, 2019 1 次提交
-
-
由 qingqing01 提交于
-
- 19 12月, 2019 1 次提交
-
-
由 qingqing01 提交于
* Polish Reader to simplify preprocessing logic. # sample_transforms-> make batch -> batch_transforms in Reader. * Clean some code * Imporve yolov3_r50vd_dcn_obj365_pretrained_coco 41.4 to 41.8. * Update all configs.
-
- 16 10月, 2019 1 次提交
-
-
由 wangguanzhong 提交于
-
- 14 10月, 2019 1 次提交
-
-
由 wangguanzhong 提交于
* add multi-scale test
-
- 29 9月, 2019 2 次提交
-
-
由 Yang Zhang 提交于
* Place mixed precision inside PaddleDetection roll back to the monkey patch version as a temporary measure, before it is merged into paddle * Add command flag for `loss_scale` * Fix a stupid indentation error optimizer should be in the mixed precision context * Initial FP16 training * Add mixed precision training to rest of the detection models * Revert "Add support for mixed precision training (#3406)" This reverts commit 3a2c106271885071db7c0d85587540a8f83c24db. * Bug fixes and some tweaks
-
由 wangguanzhong 提交于
* Support finetune by custom dataset * add finetune args * add load finetune * reconstruct load * add transfer learning doc * add fruit demo * add quick start * add data preprocessing FAQ
-
- 23 7月, 2019 1 次提交
-
-
由 Yuan Gao 提交于
* add rpn recall function and class-aware rpn
-
- 18 7月, 2019 1 次提交
-
-
由 jerrywgz 提交于
-
- 28 6月, 2019 1 次提交
-
-
由 qingqing01 提交于
* Rename object_detection to PaddleDetection * Small fix for doc
-