huangbingjian
|
f4ac2c7dbd
|
modify network_define for fasterrcnn/maskrcnn/maskrcnn_mobilenetv/deeptext
|
4 years ago |
dessyang
|
ad6d51cce2
|
Fix bug for loading checkpoint of the pure mindspore resnet backbone
|
4 years ago |
chenhaozhe
|
82c5486714
|
fix typos in lincense
|
4 years ago |
zhouneng
|
3cb75eb59d
|
fix fasterrcnn accuracy decrease by change the dtype of weights from float16 to float32
|
4 years ago |
|
dessyang
|
956b470b05
|
Add FasterRCNN training and evalution on GPU
|
4 years ago |
xiefangqi
|
8d0f80a79d
|
fix fasterrcnn x86 performance problem
|
4 years ago |
Ziyan
|
cc131193ec
|
remove parameter broadcast
|
4 years ago |
root
|
ec947ebf3d
|
modify the ckpt path
|
4 years ago |
linqingke
|
845ff342ed
|
Save the GPU backend multi card output in different folders.
|
5 years ago |
yao_yf
|
d4cfe55c04
|
rename mirror_mean to gradients_mean
|
5 years ago |
|
linqingke
|
4d9d8c3e74
|
Modelzoo interface change.
|
5 years ago |
mindspore-ci-bot
|
820f2cb4eb
|
!5351 move ParalleMode to Context
Merge pull request !5351 from yao_yf/parallel_context_collation
|
5 years ago |
|
yao_yf
|
07117e4dd4
|
mv ParallelMode to context
|
5 years ago |
yuchaojie
|
48efc182e0
|
change option choices for transformer
|
5 years ago |
zhouyuanshen
|
26327fa638
|
remove redundent codes in eval.py
|
5 years ago |
|
zhouyuanshen
|
99f4de1a74
|
fix a bug that causes failure when running muti-p from origin dataset,not from MR
|
5 years ago |
|
linqingke
|
a41337dab5
|
mass and fasterrcnn path change.
|
5 years ago |
