c2763dbb6f
!11918 [MS_LITE] support tf model
...
From: @YeFeng_24
Reviewed-by:
Signed-off-by:
4 years ago
258afe86f9
!11965 delete todo codes
...
From: @zhoufeng54
Reviewed-by: @xu-yfei,@kisnwang
Signed-off-by: @xu-yfei
4 years ago
0bb80995bc
fix param check for unexpected_format
4 years ago
18311ad312
some words are misssplelled in centernet script
4 years ago
fe90be3bb4
move mul/add/div/sub from arithmetic_fp32
4 years ago
aa130a2ab3
delete todo code
...
Signed-off-by: zhoufeng <zhoufeng54@huawei.com>
4 years ago
a24ff36d9c
!11777 stitch fusion
...
From: @r1chardf1d0
Reviewed-by:
Signed-off-by:
4 years ago
9efbef72fc
!11622 【GraphKernel】Moved ShapeOpsSplitter before GraphKernelSplitter
...
From: @dayschan
Reviewed-by: @gaoxiong1,@dylangeng
Signed-off-by: @gaoxiong1
4 years ago
e02058133e
!11526 unifiled lite & cloud api
...
From: @zhoufeng54
Reviewed-by:
Signed-off-by:
4 years ago
9757a97d5b
batch_space
4 years ago
7ff981cd19
!11942 [MS][LITE][DEVELOP]support deconv parser
...
From: @cjh9368
Reviewed-by:
Signed-off-by:
4 years ago
894d93b4fd
!11859 Added Wavenet model Scripts in CPU mode.
...
From: @huangbo77
Reviewed-by:
Signed-off-by:
4 years ago
c3d18401ab
fasterrcnn_crop run precision
4 years ago
0dd5acc055
!11889 Fix the bug of Profiler timestamp variated between each process in multi-card scene
...
From: @gzhcv
Reviewed-by:
Signed-off-by:
4 years ago
e375c86d0c
allow list as parameter input & store op info using op_name instead of primitive id
4 years ago
856d6f58cf
!11363 recitify table format for maskrcnn README_CN
...
From: @gengdongjie
Reviewed-by: @oacjiewen,@wuxuejian
Signed-off-by: @wuxuejian
4 years ago
f9228a3e6a
Add rpn proposals
4 years ago
3cce60452f
!11792 [MSLITE] prior-box strideslice split
...
From: @ling_qiao_min
Reviewed-by:
Signed-off-by:
4 years ago
7a7f8b5e13
unify SpaceToBatchND's attr
4 years ago
e897eb4c41
!11915 Change TensorAdd to Add, merge from r1.1 to master
...
From: @liangzhibo
Reviewed-by: @ginfung,@zh_qh
Signed-off-by: @zh_qh
4 years ago
7d2fd6e76c
cxx api refactor: tensor/status/model
4 years ago
f1009cb21b
!11855 [MD] Cache: Add new "server_info" command to show configuration of cache server
...
From: @tina_mengting_zhang
Reviewed-by: @mikef,@robingrosman
Signed-off-by: @robingrosman
4 years ago
6d229d078e
!11787 Migrate repeat_pass to IR optimizer
...
From: @nsyca
Reviewed-by:
Signed-off-by:
4 years ago
5a7dc0accc
Migrate repeat_pass.cc to IR optimizer and remove ExecTree optimizer
4 years ago
a559fc7f5f
Add new command for displaying server configurations
4 years ago
c16b45ab23
!11943 rectify control_depend and deprecated
...
From: @zhangbuxue
Reviewed-by: @zh_qh,@ginfung
Signed-off-by: @zh_qh
4 years ago
df265b6d6b
!11912 update submoudle akg, close graph kernel ascend ci testcases
...
From: @looop5
Reviewed-by:
Signed-off-by:
4 years ago
930fdc4e31
modify uncorrect name
4 years ago
0e73e82bab
!11880 add yolov4 310 dvpp_aipp_mindir infer
...
From: @lihongkang1
Reviewed-by:
Signed-off-by:
4 years ago
41540dbae4
!11914 add ssd network 310 dvpp aipp mindir inference
...
From: @zhangxiaoxiao16
Reviewed-by: @c_34,@wuxuejian
Signed-off-by: @c_34
4 years ago
8846b50c7f
fix cutout issue & pad doc
4 years ago
25a4382921
rectify control_depend and deprecated
4 years ago
17d0c2eb9e
support deconv parser
4 years ago
320ea51308
!11853 Add call for decoupled image and text ops
...
From: @alexyuyue
Reviewed-by:
Signed-off-by:
4 years ago
7baf313bcd
!11924 reset cube compute mode
...
From: @liubuyu
Reviewed-by: @zhoufeng54,@ljl0711
Signed-off-by: @ljl0711
4 years ago
9ec100d069
Change TensorAdd to Add, from r1.1 to master
4 years ago
6b99d66162
!11801 add environment setting checkings
...
From: @ngtony
Reviewed-by: @lixiaohui33
Signed-off-by:
4 years ago
4d2e0ea91f
!11907 Fix the bug of gpu step_trace cannot recognize correct fp/bp node in train_eval mode
...
From: @gzhcv
Reviewed-by: @yelihua,@ouwenchang
Signed-off-by: @ouwenchang
4 years ago
066ebe516e
!11794 remove useless code of dot
...
From: @yuan_shen_zhou
Reviewed-by: @liangchenghui
Signed-off-by: @liangchenghui
4 years ago
e3a01fea1c
!11899 [MSLITE][DEVELOP] add cpu fp16 op: instance norm
...
From: @yangruoqi713
Reviewed-by:
Signed-off-by:
4 years ago
08345c54ea
[GraphKernel] Replace Assign with InplaceAssign
...
1. added a pass to replace Assign with InplaceAssign.
2. bugfix in eliminate_redundant_output. the side-effect node should not be eliminated.
3. bugfix in graph_kernel/splitter.py, the kernel includes InplaceAssign should be a composite node.
4. added two tool functions GetAllInputDeviceTypes and GetAllOutputDeviceTypes into AnfAlgo.
5. do not fuse a single Assign in pass BasicOpsFusion.
4 years ago
9979f29135
!11932 Fix bugs for changing from GatherV2 to Gather
...
From: @liangzhibo
Reviewed-by: @ginfung,@zh_qh
Signed-off-by: @zh_qh
4 years ago
7ec4aa92c7
!11582 dataset: add cpu utilization profiling
...
From: @ms_yan
Reviewed-by:
Signed-off-by:
4 years ago
58366cbeb9
[MSLITE][DEVELOP] add cpu fp16 op: instance norm
4 years ago
eee0144367
!11878 add op actor interface
...
From: @limingqi107
Reviewed-by:
Signed-off-by:
4 years ago
177bdd8f4b
Modify cnnctc network save checkpoint.
4 years ago
3795cd37d9
!11758 support recording dict value as string for dataset_graph
...
From: @luopengting
Reviewed-by: @ouwenchang,@wenkai_dist
Signed-off-by: @wenkai_dist
4 years ago
e258315885
!11920 Refactor code under engine/cache/perf to pass lizard check
...
From: @lixiachen
Reviewed-by: @liucunwei,@pandoublefeng
Signed-off-by: @liucunwei
4 years ago
9585aa6fdb
[MSLITE] strided-slice split
4 years ago
0161209e40
update submoudle akg, close graph kernel ascend ci testcases
4 years ago
mindspore-ci-bot
jiangshuqiang
CaoJian
smurf
zhoufeng
yefeng
yeyunpeng
simson
zhouyaqiang
yuchaojie
lixian
Nat Sutyanyong
tinazhang
gaojing
luoyang
buxue
cjh9368
l00591931
dayschan
yangruoqi713
zhanghuiyao
ling
looop5