106ece221d
modify version to r0.6 for master
5 years ago
3d7732a7b3
!3726 add lite op PriorBox
...
Merge pull request !3726 from zhaozhenlong/lite/op/prior_box
5 years ago
7d3f56c54f
!3688 Add deconv parser
...
Merge pull request !3688 from ghzl/add-deconv-parser
5 years ago
9ba4e4d88d
!3844 little optimization for depth wise kernels
...
Merge pull request !3844 from lixian/master
5 years ago
9eb0a7697f
!3713 detect model fix bug
...
Merge pull request !3713 from ghzl/deconv-adapter
5 years ago
d7bc28dcde
!3835 add lite kernel relu_int8 and hswish_int8
...
Merge pull request !3835 from sunsuodong/int8_relu_hswish
5 years ago
f894ffe6ad
little optimization for depth wise kernels
5 years ago
bab5aedd49
!3843 fix kernel registry bug
...
Merge pull request !3843 from fuzhiye/mindspore
5 years ago
cf4533da68
!3810 update the performance of concat ops
...
Merge pull request !3810 from pengyongrong/master
5 years ago
1eb86b7df2
fix kernel registry bug
5 years ago
90553fef08
add lite op PriorBox
5 years ago
514ba6e976
Optimize performance for master branch
...
modify CMakeLists.txt
remove old MINDSPORE_HCCL_CONFIG_PATH in model zoo
decoupling core and debug
add lite/test
add gpu python
pad fp32 support less than 4d input
repair distribute training for vgg in D
5 years ago
668db1dd7d
deconv adapter
5 years ago
d1b3096418
!3837 add_test_for_mindrecord 3
...
Merge pull request !3837 from liucunwei/add_test_for_mindrecord3
5 years ago
64c2f195b7
int8_relu_hswish
5 years ago
5338128283
!3833 rewrite op register func
...
Merge pull request !3833 from fuzhiye/mindspore
5 years ago
3a70fd23ce
rewrite op register func
5 years ago
5a3b557354
!3814 enhance: map file label start begin 0 in imagenet_to_mr tool
...
Merge pull request !3814 from liucunwei/enhance_map_file_for_imagenet
5 years ago
11f786c9bd
!3808 remove predict
...
Merge pull request !3808 from 张学同/to_merge
5 years ago
53c40d0ec7
!3836 1. multithreading support for fc_int8_op. 2. change asm matmul output layout
...
Merge pull request !3836 from zhanyuan/master
5 years ago
3819945547
!3776 fix compilation bugs on arm32 & add BiasAdd/Relu/DW kernels on arm64
...
Merge pull request !3776 from lixian/master
5 years ago
87668d6ea2
remove predict
5 years ago
8b99114f6d
add mindrecord test case
5 years ago
6e759cd487
!3815 compute threshold only once in post training quantization
...
Merge pull request !3815 from xutianchun/quant_0731
5 years ago
e52aa2b12f
fix compile bugs on arm32 and add BiasAdd/Relu/Dw arm64 kernels
5 years ago
9cab9f7a91
1. multithreading support for fc_int8_op. 2. change asm matmul output layout from col8x8 to row8x8
5 years ago
fae78e11a7
1. compute threshold only once
...
2. fix anf_exporter bug: pool, concat op may not set into metagraph
3. fix weight trans pass will return error when post quantization
4. make anf_exporter reentrant: do not set PrimitiveT * to nullptr
5 years ago
6c4ee3f3d1
!3827 add run_test.sh & fix bug in type_id.h build.sh gtest
...
Merge pull request !3827 from hangq/master
5 years ago
b5f317c29f
!3610 Add C++ API support for Concat and Zip
...
Merge pull request !3610 from TinaMengtingZhang/cpp-api-concat
5 years ago
1595faadc3
!3829 C++ API: Reorder transforms.h alphabetically
...
Merge pull request !3829 from cathwong/ckw_c_api_transform_hdr_alpha
5 years ago
e57d849618
add concat op and extend zip support to cpp api
5 years ago
6945eb2821
!3622 Added option to distributed sampler
...
Merge pull request !3622 from EricZ/distributed_sampler_fix
5 years ago
49a1e01390
C++ API: Reorder transforms.h alphabetically
5 years ago
2449e4e7f1
!3760 Fix GPU-ResizeNearestNeighbor
...
Merge pull request !3760 from 34bunny/GPU-ResizeNearestNeighbor-fix
5 years ago
e1f93ec28c
!3619 NMSWithMask - CUDA Impl
...
Merge pull request !3619 from danishnxt/GPU_One
5 years ago
8c018da468
Fixing issues in distributed sampler
...
Added Distributed sampler option
Fix style
5 years ago
ac05742619
add run_test.sh & fix bug in type_id.h build.sh gtest
5 years ago
1165b27f41
!3693 Change the column order and add drop_reminder option to make the generated dataset compatible with BertCLS
...
Merge pull request !3693 from dessyang/master
5 years ago
634d797ca3
!3549 MapOp refactor for device augmentation (part 1)
...
Merge pull request !3549 from anthonyaje/device_augment_mapop_refactor1
5 years ago
27e51c5a63
!3553 Unify np array comparisons
...
Merge pull request !3553 from tony_liu2/staging
5 years ago
d8d502bfb6
!3801 fix header include that was deleted by mistake
...
Merge pull request !3801 from liubuyu/master
5 years ago
82b103a740
!3780 add gpu BinaryCrossEntropy
...
Merge pull request !3780 from baihuawei/losscuda
5 years ago
88ba8ee449
add deconv parser
5 years ago
741c2898dd
update RELEASE.md.
5 years ago
953f91cef8
!3739 not eliminate memcpy when nexe node is graph output
...
Merge pull request !3739 from laiyongqiang/eliminate_memcpy_bug
5 years ago
fd1f0d3cb6
!3804 Fix cmake not aware of new files
...
Merge pull request !3804 from hexia/fix_pb2
5 years ago
c9453a614e
!3239 Insert concat for outputs of AllGather
...
Merge pull request !3239 from YuJianfeng/allgther
5 years ago
6adcb5a859
!3719 resnet101 changes for GPU
...
Merge pull request !3719 from RobinGrosman/master
5 years ago
59aaf56a1e
!3728 modify optimizer calculation formula
...
Merge pull request !3728 from lijiaqi/add_calculation
5 years ago
c133059c59
enhance: imagenet to mindrecord mapfile
5 years ago
changzherui
mindspore-ci-bot
lixian
fuzhiye
zhaozhenlong
pengyongrong
guohongzilong
sunsuodong
z00505269
liucunwei
zhanyuan
xutianchun
tinazhang
Cathy Wong
Eric
hangq
lujiale