- 11 10月, 2019 1 次提交
-
-
由 wangguanzhong 提交于
-
- 09 10月, 2019 2 次提交
-
-
由 Liufang Sang 提交于
-
由 Yang Zhang 提交于
* Document mixed precision training flags * Clarify GPU is required for mixed precision training
-
- 08 10月, 2019 5 次提交
-
-
由 Yang Zhang 提交于
-
由 wangguanzhong 提交于
-
由 wangchaochaohu 提交于
* refine build strategy for the model optimize test=develop * fix according develop test=develop
-
由 wangguanzhong 提交于
-
由 wangguanzhong 提交于
-
- 03 10月, 2019 1 次提交
-
-
由 wangguanzhong 提交于
-
- 30 9月, 2019 1 次提交
-
-
由 Guanghua Yu 提交于
* add CropImageWithDataAnchorSampling * Refine bbox sampling code * Update comments * fix import and variable problem
-
- 29 9月, 2019 7 次提交
-
-
由 Guanghua Yu 提交于
* Add backbone and architecture for FaceBoxes and Blazeface. * Add dataloader for WIDERFace dataset.
-
由 qingqing01 提交于
Update ppdet/utils/checkpoint.py to skip the var shape check when the var is not initialized. (#3452)
-
由 Yang Zhang 提交于
-
由 Yang Zhang 提交于
-
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 Yang Zhang 提交于
-
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
-
- 27 9月, 2019 1 次提交
-
-
由 Yang Zhang 提交于
-
- 25 9月, 2019 3 次提交
-
-
由 wangguanzhong 提交于
-
由 Yang Zhang 提交于
* Disable optimizer fusion for RCNN models waiting for upstream fix * Disable completely
-
由 Yang Zhang 提交于
* Add support for mixed precision training * Disable `fuse_all_reduce_ops` when training in mixed precision waiting for upstream fix
-
- 23 9月, 2019 1 次提交
-
-
由 Yang Zhang 提交于
* Initial support for distributed training * Housekeep on rank 0 only * Conform to models convention
-
- 19 9月, 2019 1 次提交
-
-
由 wangguanzhong 提交于
-
- 17 9月, 2019 3 次提交
-
-
由 wangguanzhong 提交于
-
由 wangguanzhong 提交于
* fix rcnn eval on voc * update comment
-
由 wangguanzhong 提交于
-
- 16 9月, 2019 2 次提交
-
-
由 Kaipeng Deng 提交于
* refine auto download logs
-
由 Kaipeng Deng 提交于
-
- 12 9月, 2019 1 次提交
-
-
由 wangguanzhong 提交于
-
- 10 9月, 2019 2 次提交
-
-
由 Zeng Jinle 提交于
-
由 Zeng Jinle 提交于
-
- 09 9月, 2019 2 次提交
-
-
由 David Lin 提交于
In PaddleDetection, making use of tb-paddle to record data, so as to display in TensorBoard. (#3295) * use tb_paddle to log data including: * loss * mAP * image * modified: requirements.txt * modify the missing argument --use_tb * modify GETTING_STARTED.md and docs/GETTING_STARTED_cn.md add the argument of tb-paddle in docs. * optimize the display name of image displaying.
-
由 wangguanzhong 提交于
-
- 05 9月, 2019 3 次提交
-
-
由 Guanghua Yu 提交于
-
由 qingqing01 提交于
* Add benchmark (fps) in MODEL_ZOO doc
-
由 Kaipeng Deng 提交于
* fix add map_type
-
- 04 9月, 2019 2 次提交
-
-
由 Kaipeng Deng 提交于
-
由 Kaipeng Deng 提交于
-
- 03 9月, 2019 1 次提交
-
-
由 wangguanzhong 提交于
* minor fix for PaddleDetection
-
- 02 9月, 2019 1 次提交
-
-
由 walloollaw 提交于
* fix bug in sharedmemory * fix bug in sharedmemory
-