08dad79529
!7533 fix bug of gpu‘s kernel setter
...
Merge pull request !7533 from lianliguang/master
5 years ago
02650e2655
optimize the deepfm test case network structure
5 years ago
b0822ba908
add lite string interface
5 years ago
17d6433d27
primivte_target
5 years ago
a3458a2fdf
mod_matmul
5 years ago
8f59cdb63a
add parser of pow
5 years ago
c8ec34d638
move train.quant to compression module & add QuantizationAwareTraining
5 years ago
ff85533155
!7566 [MD]add comment for ExtractOp and Split op
...
Merge pull request !7566 from xulei/lite_test0905
5 years ago
a8dc0f5c1b
!7557 [MD] Add merge image proccessing
...
Merge pull request !7557 from jiangzhiwen/lite/merge
5 years ago
376c4aaf26
set proto env
5 years ago
bbcdd81d1b
fix reduce precision: deal tuplegetitem and param
5 years ago
639a085d93
fix bugs
5 years ago
8709b4fa00
fix cannot find python-dev
...
signed-off-by: zhoufeng <zhoufeng54@huawei.com>
5 years ago
7271ac8a80
add fp32 deconv merge assembly
5 years ago
f887618662
!7524 remove OpenCLKernel's member op_format_
...
Merge pull request !7524 from 王东旭/remove_op_format
5 years ago
d1e22904a2
!7562 modify primivite_target
...
Merge pull request !7562 from lijiaqi/primivte_target
5 years ago
7c15afcc66
!7478 Add st for Ascend dynamic shape
...
Merge pull request !7478 from caifubi/dynamic_shape
5 years ago
ce4f64021e
!7561 mode_export_v3
...
Merge pull request !7561 from baiyangfan/mode_export_v3
5 years ago
eb6f4e3ce8
update repeated calculation
5 years ago
8d1e65ad6b
Add implementation of transpose to adapt different dimensions.
5 years ago
f429fe7888
Decouple GraphKernel ops from akg op register
...
1. Extract op info from AnfNode when generating composite operators.
2. Ignore the op register info when selecting kernel.
3. Update akg submodule.
4. Remove akg gpu op registers that added for GraphKernel.
5. Add an interface `IsNodeInGraphKernel` into `AnfRuntimeAlgorithm`, next to the `IsGraphKernel`.
6. Sort included fils for the clang-format rule is changed.
TODO: Remove the json generator in GraphKernelExpander, it's ok to call this interface.
5 years ago
6a1b2f9ba3
add comment for ExtractOp and Split op
5 years ago
6d3d6633cb
fix type convert error in arm32
5 years ago
2ab0b3d67a
support ops elu and elugrad on gpu
5 years ago
9607778f01
mode_export_v3
5 years ago
319ecedb24
primivte_target
5 years ago
359543d663
!7320 add GPU efficientnet-b0 to modelzoo
...
Merge pull request !7320 from 34bunny/GPU-efficientnet
5 years ago
7f29df6988
remove_op_format
5 years ago
9b2b062642
!7527 [MS][LITE][Develop]add fp32 deconv kernels
...
Merge pull request !7527 from lixian/master
5 years ago
baa4241b82
!7553 Modify warning for data_sink_mode in model.eval
...
Merge pull request !7553 from liuyang/sink_mode
5 years ago
f14593f5f3
!7517 Choose the date type for idx in the infer implementation for Unique
...
Merge pull request !7517 from YuJianfeng/master
5 years ago
8e785648da
add merge image processing
5 years ago
9733780f4b
!7551 [MS][LITE][CPU]move funcs
...
Merge pull request !7551 from fuzhiye/tmp
5 years ago
f89387f9b6
!7552 onehot support 3 inputs
...
Merge pull request !7552 from zhaozhenlong/lite/issue/onehot_adapt_onnx_3_input
5 years ago
fd8ebde400
!7545 GPU reshape add type
...
Merge pull request !7545 from VectorSL/int64
5 years ago
89cd882077
!7520 Critical path performance optimization
...
Merge pull request !7520 from chenweifeng/resnet50-profiling
5 years ago
688c7c104b
!6795 rewrite schduler & fix subGraph segmentation bug
...
Merge pull request !6795 from hangq/primitive
5 years ago
eaab26f7a9
!7547 mode_export_note
...
Merge pull request !7547 from baiyangfan/mode_export_note
5 years ago
ca85fcef40
[ME] change some format code.
5 years ago
af40b005fb
onehot support 3 inputs
5 years ago
290b0aa194
!7502 delete launch file
...
Merge pull request !7502 from zhaoting/mobilenet
5 years ago
a3c6ad09a0
rewrite schduler & fix subGraph segmentation bug
5 years ago
66d67f1eb2
modify data sink mode for model.eval
5 years ago
5fe2164a70
!7543 modify_cmake
...
Merge pull request !7543 from lilei/modify_cmake
5 years ago
98f3fe665c
!7532 fix concat memory leak
...
Merge pull request !7532 from zhaodezan/master
5 years ago
8efde6f09a
move quant preprocess func
5 years ago
7e8dad791a
!7526 [MSLITE][Develop] optimize conv dw arm cpu int8 op: add 3x3
...
Merge pull request !7526 from yangruoqi713/conv_dw
5 years ago
6f96610832
mode_export_note
5 years ago
aa94e5a91e
add fp32 deconv kernels
5 years ago
52eec881ec
Refactor ImageFolderNode and BatchNode into its separate files
...
fix ci
fix ci
address review cmmts, fix ci
remove dup code in datasets.cc
5 years ago
mindspore-ci-bot
wsq3
sunsuodong
Jiaqi
wanyiming
yankai
yuchaojie
changzherui
VectorSL
lihongkang
zhoufeng
lixian
yangzhenzhang
wang_shaocong
dayschan
xulei2020
zhouyuanshen
bai-yangfan
wangdongxu
jiangzhiwen
chenzomi
zhaozhenlong
hangq
liuyang_655
fuzhiye
Zirui Wu