lvhan028
|
c3986cebe8
|
bump version to v0.12.0 (#1594)
|
2022-12-30 16:17:37 +08:00 |
hanrui1sensetime
|
20b2aff660
|
[Fix] Fix batch inference error for Mask R-CNN (#1575)
* fix Mask R-CNN for multi-batch
* fix flake8
* fix bug
* use Sequence instead list
* fix docstring
* only test_img accept list input
|
2022-12-30 14:26:33 +08:00 |
Li Zhang
|
20e0563682
|
[Enhancement] Optimize pose tracker (#1460)
* sync master
* suppress overlapped tracks
* add CUDA WarpAffine
* export symbols
* fix linkage
* update pose tracker
* clean-up
* fix MSVC build
* fix MSVC build
* add ffmpeg cli command
|
2022-12-29 19:12:55 +08:00 |
tpoisonooo
|
f62352a5fa
|
fix(README): badge error and add github action status (#1548)
* fix(README): badge error and add github action status
* docs(REAMDE): fix badge
* docs(README): update color
* docs(REAMEDE): update color
* docs(README): update table
|
2022-12-29 16:08:29 +08:00 |
|
hanrui1sensetime
|
f21dc4e7d3
|
Cherry-pick #1352 to fix ops unittest seg-fault error (#1556)
* cherry-pick PR1352 to master
* fix test_ops with teardown and skip
* remove useless line
* fix lint
Co-authored-by: q.yao <yaoqian@sensetime.com>
|
2022-12-29 12:08:40 +08:00 |
q.yao
|
fc98472e9c
|
[Refactor] update tutorial about how to support new backend (#1574)
|
2022-12-29 12:05:31 +08:00 |
|
Li Zhang
|
e3f033ee5d
|
build monolithic SDK by default (#1577)
|
2022-12-28 11:44:20 +08:00 |
AllentDan
|
85b7b967ee
|
[Feature] Support probability output for segmentation (#1379)
* add do_argmax flag
* sdk support
* update doc
* replace do_argmax with with_argmax
* add todo
|
2022-12-26 15:48:07 +08:00 |
|
q.yao
|
d113a5f1c7
|
[Refactor] refactor is_available, check_env (#1540)
* refactor is available
* remove try catch in apis
* fix trt check env
* fix ops_info
* update default value
* remove backend list
* optimial pycuda
* update requirement, check env for rknn
|
2022-12-23 12:06:32 +08:00 |
|
q.yao
|
5285caf30a
|
[Refactor] Add 'to_backend' in BackendManager (#1522)
* Refactor to backend
* export_postprocess_mask = False as defailt
* update zh_cn docs
* solve comment
* fix comment
|
2022-12-21 14:04:16 +08:00 |
|
AllentDan
|
26d71ce0a8
|
add 'is_batched' argument to pipeline.json (#1560)
|
2022-12-21 10:45:00 +08:00 |
BuxianChen
|
f9f351ae1f
|
update FAQ about copying onnxruntime dll to 'mmdeploy/lib' (#1554)
|
2022-12-20 14:39:31 +08:00 |
Michał Antoszkiewicz
|
202bf00eb7
|
Fix 'cannot seek vector iterator' in debug windows build (#1555)
Signed-off-by: Michal Antoszkiewicz <mantoszkiewicz@codeflyers.com>
Signed-off-by: Michal Antoszkiewicz <mantoszkiewicz@codeflyers.com>
|
2022-12-20 10:13:33 +08:00 |
Chen Xin
|
dbc4b26dc1
|
fix cuda10.2 build (#1539)
|
2022-12-16 10:15:15 +08:00 |
|
tpoisonooo
|
77c2ee5feb
|
fix(tools/scripts): build aarch option (#1530)
|
2022-12-15 20:41:59 +08:00 |
|
Chen Xin
|
c72f2eaa31
|
[Docs] Add mmaction2 sphinx-doc link (#1541)
* add mmaction2 sphinx doc
* consistent with other doc formats
* change title
* fix ci
* add missing coreml sphinx doc
|
2022-12-15 19:01:34 +08:00 |
GY
|
05ed8e16ea
|
update to ppl.nn v0.9.1 and ppl.cv v0.7.1 (#1356)
|
2022-12-13 14:21:24 +08:00 |
q.yao
|
7cb4b9b18a
|
[Enhancement] Support tvm (#1216)
* finish framework
* add autotvm and auto-scheduler tuner
* add python deploy api
* add SDK net(WIP
* add sdk support
* support det, support vm
* fix vm sdk
* support two stage detector
* add instance seg support
* add docstring
* update docs and ut
* add quantize
* update doc
* update docs
* synchronize stream
* support dlpack
* remove submodule
* fix stride
* add alignment
* support dlpack
* remove submodule
* replace exclusive_scan
* add backend check
* add build script
* fix comment
* add ci
* fix ci
* ci fix2
* update build script
* update ci
* add pytest
* update sed command
* update sed again
* add xgboost
* remove tvm ut
* update ansor runner
* add stream sync
* fix topk
* sync default stream
* fix tvm net
* fix window
|
2022-12-12 21:19:40 +08:00 |
|
q.yao
|
ac47cad407
|
[Improvements] Support TorchAllocator as TensorRT Gpu Allocator (#1493)
* add TorchAllocator for TensorRT
* check mdcn input shape
|
2022-12-12 18:43:59 +08:00 |
|
Chen Xin
|
52fd4fe9f3
|
[Fix] Remove cudnn dependency for transform 'mmaction2::format_shape' (#1509)
* fix format shape
* merge common code
* use throw_exception
* udpate code format
|
2022-12-12 14:34:15 +08:00 |
RunningLeon
|
ae785f42e1
|
fix typo: rename 'stable.yml' as 'stale.yml' (#1510)
|
2022-12-12 11:17:40 +08:00 |
|
q.yao
|
af4d304004
|
support torchjit mdcn (#1508)
|
2022-12-12 10:28:49 +08:00 |
|
RunningLeon
|
c1ca5a3dbf
|
add stale workflow to check issues and PRs (#1504)
|
2022-12-09 18:41:36 +08:00 |
|
q.yao
|
1748780c91
|
[Refactor] ease build wrapper master (#1475)
* ease build wrapper
* import eanum only when necessary
* update docs
* rename manager
* update for comment
* replace staticmethod with classmethod
* fix torchjit
|
2022-12-09 17:19:34 +08:00 |
|
q.yao
|
8ea3dc943f
|
[Fix] Fix for torch113 for master (#1488)
|
2022-12-08 17:17:27 +08:00 |
|
q.yao
|
4046e13146
|
Reformat multi-line logs and docstrings (#1489)
|
2022-12-06 19:50:58 +08:00 |
HinGwenWoong
|
7b3c3bc223
|
[Enhancement] Add pip source in dockerfile for `master` branch (#1492)
* Add pip source
* Add pip source
|
2022-12-06 19:46:01 +08:00 |
|
RunningLeon
|
2a1fed91c9
|
bump mmdeploy sdk version to 0.11.0 (#1473)
|
2022-11-30 17:54:40 +08:00 |
|
RunningLeon
|
55a3c8cf78
|
Bump version to v0.11.0 (#1470)
* bump version v0.11.0
* fix
|
2022-11-30 17:18:13 +08:00 |
|
q.yao
|
bf80653446
|
fix gelu torch>1.12 (#1458)
|
2022-11-30 14:05:48 +08:00 |
|
tpoisonooo
|
f6b35f3b68
|
fix(CI): ncnn script install (#1459)
* CI(script): fix ncnn install
* docs(build): update ncnn version to 20221128
* fix(CI): trigger
|
2022-11-29 20:37:06 +08:00 |
|
Chen Xin
|
2c9861555f
|
[Enhancement] add mmaction.yml for test (#1455)
* add mmaction.yml for test
* t# This is a combination of 2 commits.
add missing file
* fix typo
* remove
|
2022-11-29 18:48:29 +08:00 |
|
Chen Xin
|
c97aed1a96
|
fix total time (#1451)
|
2022-11-29 13:45:50 +08:00 |
Xin Li
|
73afa61bd8
|
update master branch (#1452)
|
2022-11-29 13:42:47 +08:00 |
|
Chen Xin
|
0830acb40c
|
[FIX] Fix csharp net48 and batch inference (#1370)
* fix csharp net48
* add missing file
* update
* fix batch inference
* update demo
* update
* update version
|
2022-11-29 11:48:36 +08:00 |
|
AllentDan
|
047ab67c78
|
[Fix] fix visualization for partition (#1424)
* init
* lint
* pass output_names outside
* docstring & type hint
|
2022-11-29 11:40:00 +08:00 |
|
q.yao
|
b521e7da03
|
fix topk (#1439)
|
2022-11-28 17:35:15 +08:00 |
|
hanrui1sensetime
|
9ea8610133
|
[Fix] fix ncnn torch 1.12 master (#1430)
* fix ncnn torch 1.12 master
* remove debug line
* add docstring
|
2022-11-28 17:34:39 +08:00 |
|
AllentDan
|
d9d3ded8bc
|
concat datasets pytorch metric (#1447)
|
2022-11-28 17:34:02 +08:00 |
|
Li Zhang
|
d77aeaa480
|
[Refactor] Decouple preprocess operation and transformation (#1353)
* refactor SDK registry
* fix lint
* decouple transform logic and operations
* data management
* improve data management
* improve data management
* context management
* fix ResizeOCR
* fix operation fallback logic
* fix MSVC build
* clean-up
* sync master
* fix lint
* Normalize - add `to_float`, merge `cvtcolor` operations
* fix macOS build
* rename
* cleanup
* fix lint
* fix macOS build
* fix MSVC build
* support elena
* fix
* fix
* optimize normalize
* fix
* fix MSVC build
* simplify
* profiler
* use `throw_exception`
* misc
* fix typo
|
2022-11-28 14:46:05 +08:00 |
|
Chen Xin
|
3d1c135297
|
[Enhancement] refactor profiler (#1403)
* reduce profile node name
* add profiler for pipeline
* add profiler for cond
* udpate
|
2022-11-28 10:44:54 +08:00 |
|
Li Zhang
|
6468ef180d
|
[Fix] Relax module adapter template constraints (#1366)
* relax module adapter constraint
* remove forwarding `operator()`
|
2022-11-27 11:58:09 +08:00 |
|
Li Zhang
|
385f5b6102
|
[Fix] Fix det_pose demo (#1419)
* fix det_pose demo
* remove useless input
|
2022-11-27 11:56:59 +08:00 |
|
RunningLeon
|
10e5cf6e0f
|
update reg test (#1440)
* give model path if stead of 'x' when conversion failed
* set --models with default value ['all']
* fix mmseg yml
|
2022-11-25 21:16:22 +08:00 |
|
q.yao
|
0d16f6ec30
|
fix pad to square (#1436)
* fix pad to square
* fix topk
* remove comment
* recovery topk
|
2022-11-25 17:31:44 +08:00 |
|
q.yao
|
4e1c83ab5b
|
[Fix] fix yolohead trt8.2 (#1433)
* fix yolohead trt8.2
* remove score_threshold
|
2022-11-25 15:35:09 +08:00 |
|
Li Zhang
|
4d4c10a2dc
|
[Enhancement] Avoid copying dense arrays in Python API (#1349)
* eliminate copying for segmentor
* fix segmentor
* eliminate copying in Python API
* minor fix
|
2022-11-24 18:23:34 +08:00 |
|
Chen Xin
|
73e095a4b8
|
[Fix] fix mmaction2 docs (#1410)
* fix typo and add link to README.md
* fix
|
2022-11-24 16:40:56 +08:00 |
Jiahao Sun
|
9bbe3c0355
|
[Feat] Add end2end pointpillars & centerpoint(pillar) deployment for mmdet3d (#1178)
* add end2end pointpillars & centerpoint(pillar)
* fix centerpoint UT
* uncomment pycuda
* add nvidia copyright and remove post_process for voxel_detection_model
* keep comments
* add anchor3d_head init
* remove pycuda comment
* add pcd test sample
|
2022-11-24 16:14:50 +08:00 |
|
AllentDan
|
301035a06f
|
[Fix] fix cls head in SDK (#1420)
* fix cls head
* resolve comments
|
2022-11-24 14:15:34 +08:00 |