- 29 9月, 2019 9 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 Bai Yifan 提交于
* fix resnet prefix * fix data path
-
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 3a2c1062. * Bug fixes and some tweaks
-
由 Yang Zhang 提交于
-
由 0YuanZhang0 提交于
* fix_bug_server * fix_readme
-
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 3 次提交
-
-
由 Jiabin Yang 提交于
* using new load api * merge * add dygraph user guide in models/dygraph * remove useless files
-
由 Yang Zhang 提交于
-
由 zhoushiyu 提交于
* fix deepfm failed in 2*1 local distributed training * fix deepfm preprocess bug * fix deepfm preprocess bug and README
-
- 26 9月, 2019 6 次提交
-
-
由 lvmengsi 提交于
-
由 Yiqun Liu 提交于
test=develop
-
由 Liufang Sang 提交于
* fix quantization doc
-
由 0YuanZhang0 提交于
-
由 Jiancheng Li 提交于
Update PaddleSlim LightNAS
-
由 LiuHao 提交于
* update * update * update * fix run_ernie.sh * Update README.md
-
- 25 9月, 2019 11 次提交
-
-
由 SunGaofeng 提交于
fix path of dir of files in windows
-
由 wangguanzhong 提交于
-
由 zhoushiyu 提交于
* PaddleRec xdeepfm add local distributed training * PaddleRec deepfm dcn add local distributed training * change PaddleRec deepfm README.md * add embedding is_sparse flag in argparser * fix deepfm failed in ver 1.5.2 when use transpiler * fix xdeepfm failed in ver 1.5.2 when use transpiler * fix some bugs in dnn deepfm and dcn * fix embedding size in deepfm
-
由 0YuanZhang0 提交于
-
由 0YuanZhang0 提交于
* MRQA2019-D-NET * delete_data_file
-
由 Bai Yifan 提交于
* add distillation demo and doc
-
由 Liufang Sang 提交于
* add classification quantization demo
-
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
-
由 whs 提交于
* Add pruning demo for classification
-
由 LielinJiang 提交于
-
- 24 9月, 2019 3 次提交
-
-
由 tianxin 提交于
* set encoding=utf8 for open * set encoding=utf8 for open
-
由 Jiancheng Li 提交于
-
由 tianxin 提交于
-
- 23 9月, 2019 8 次提交
-
-
由 Yang Zhang 提交于
* Initial support for distributed training * Housekeep on rank 0 only * Conform to models convention
-
由 Li Fuchen 提交于
add license for nlp models
-
由 lvmengsi 提交于
-
由 chengduo 提交于
* fix model save * fix doc
-
由 cuicheng01 提交于
* update TensorRT 1.5.2 inference time * add EfficientNet configuration in README
-
由 LielinJiang 提交于
* add notes for the ported weight of EfficientNet
-
由 lvmengsi 提交于
* fix_infer_pix2pixreader
-
由 lvmengsi 提交于
-