Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Npu dev #2385

Merged
merged 45 commits into from
Nov 3, 2022
Merged

Npu dev #2385

merged 45 commits into from
Nov 3, 2022

Conversation

ckirchhoff2021
Copy link
Collaborator

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.

Motivation

Please describe the motivation of this PR and the goal you want to achieve through this PR.

Modification

Please briefly describe what modification is made in this PR.

BC-breaking (Optional)

Does the modification introduce changes that break the backward-compatibility of the downstream repositories?
If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.

Use cases (Optional)

If this PR introduces a new feature, it is better to list some use cases here, and update the documentation.

Checklist

Before PR:

  • I have read and followed the workflow indicated in the CONTRIBUTING.md to create this PR.
  • Pre-commit or linting tools indicated in CONTRIBUTING.md are used to fix the potential lint issues.
  • Bug fixes are covered by unit tests, the case that causes the bug should be added in the unit tests.
  • New functionalities are covered by complete unit tests. If not, please add more unit test to ensure the correctness.
  • The documentation has been modified accordingly, including docstring or example tutorials.

After PR:

  • If the modification has potential influence on downstream or other related projects, this PR should be tested with some of those projects, like MMDet or MMCls.
  • CLA has been signed and all committers have signed the CLA in this PR.

ZShaopeng and others added 30 commits September 8, 2022 17:19
@ZShaopeng
[Feature] Support RoipointPool3d with cambricon MLU backend (open-mml…
83bedf5 
…ab#2247)

* [Feature] Support RoipointPool3d with cambricon MLU backend

* [Feature] Support RoipointPool3d with cambricon MLU backend

* [Feature] Support RoipointPool3d with cambricon MLU backend

* [Feature] Support RoipointPool3d with cambricon MLU backend

* [Feature] Support RoipointPool3d with cambricon MLU backend
@zhouzaida
[Docs] Add zhihu articles (open-mmlab#2157)
3a311e8 
* [Docs] Add zhihu articles

* add OpenMMLabCourse link

* fix typo
@triple-Mu @zhouzaida
Add type hints for mmcv/image (open-mmlab#2089)
2fb2b91 
* Fix typehint

* minor fix

* minor fix

* minor fix

Co-authored-by: zhouzaida <zhouzaida@163.com>
@zstreet87
[Fix] Use ROCm backened within the PyTorch framework (open-mmlab#1918)
2046a39 
* modified code for using ROCm backened within the PyTorch framework

* added hip runtime header

* flake8 linting fix
@okotaku
[Feature] Register a new activatation layer SiLU to ACTIVATION_LAYERS (…
55c51e1 
…open-mmlab#2256)
Fix spconv clang-format (open-mmlab#2260)
25f533b
@datumbox
[Enhancement] Add support of TorchVision's Model Registration API on …
3b9b905 
…MMCV (open-mmlab#2246)

* Add support of TorchVision's Model Registration API.

* fix linter

* formatting with yapf
@zhouzaida @yxzhao2022
Pick commits from 2.x branch (open-mmlab#2284)
629ef89 
* [Fix] Fix the calculation error of out_w in MaskedConv2dFunction (open-mmlab#2264)

* [Fix] Fix two intergers can not use / operator in torch1.6

* should not use kernel_h when calculates out_w

* [Docs] Fix some mistakes in data_process.md (open-mmlab#2283)

* correction

* correction en docs

Co-authored-by: yxzhao <33384732+yxzhao2022@users.noreply.github.com>
@zhouzaida
Bump version to v1.6.2 (open-mmlab#2285)
847612d
@okotaku @zhouzaida
[Enhancement] Support SiLU with torch < 1.7.0 (open-mmlab#2278)
afff388 
* support silu torch<1.7.0

* fix test

* fix test

* fix inplace

* fix inplace

* Update tests/test_cnn/test_silu.py

Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
Update onnx registry (open-mmlab#2294)
9250417 
* update onnx registry

* move import
@wangjiangben-hw @ckirchhoff2021 @zhouzaida
[Feature] Support training on NPU device (open-mmlab#2262)
a5db5f6 
* init npu

* add npu extension and focal loss adapter

* clean code

* clean code

* clean code

* clean code

* fix autocast bugs on npu (open-mmlab#2273)

fix autocast bugs on npu (open-mmlab#2273)

* code format

* code format

* code format

* bug fix

* pytorch_npu_helper.hpp clean code

* Npu dev (open-mmlab#2306)

* fix autocast bugs on npu
* using scatter_kwargs in mmcv.device.scatter_gather

* raise ImportError when compile with npu

* add npu test case (open-mmlab#2307)

* add npu test case

* Update focal_loss.py

* add comment

* clean lint

* update dtype assert

* update DDP forward and comment

* fix bug

Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

Co-authored-by: ckirchhoff <515629648@qq.com>
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
@zhouzaida
Upgrade pre commit hooks (open-mmlab#2321)
b6a7fd9 
* Upgrade the versions of pre-commit hooks

* update the versions of zh-cn.yaml
@tpoisonooo
Fix warning of CUDA ops (open-mmlab#2324)
8e844d1
@defei-coder @budefei
[Refactor] Adapt mlu code to cntoolkit3.0.1 (open-mmlab#2248)
b1711db 
* [Refactor] Adapt mlu code to cntoolkit3.0.1

* [Refactor] Modify the code style

Co-authored-by: budefei <budefei@cambricon.com>
Co-authored-by: budefei <budefei@cambricon>
[Refactor] Refactor the nms3d op to support MLU (open-mmlab#2296)
c001e2f 
* update iou3d

* fix parrot

* update to device

* replace count_nonzero with fill

* update build.yml
@CokeDong
[Feature] Support PrRoI op for Parrots (open-mmlab#2280)
dd5b415 
* Support parrots extension for op PrRoI

* Fix lint

* Fix cpp lint

* Fix testcase failure by false requires_grad in self-defined autograd Funtion

* Fix issues

* Fix flake8

* Fix isort

* Adaption for typechecking for PrRoIPoolFunction

* Fix lint

* Support only float32

* bugfix
@shcheklein @zhouzaida
[Enhancement] Add ability to pass logger instance to frameworks (open…
e417035 
…-mmlab#2317)

* Add ability to pass logger instance to frameworks

* refine docstring

* Update mmcv/runner/hooks/logger/dvclive.py

Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
@zhouzaida
[Docs] Refine README and installation documentations (open-mmlab#1977)
bd1da5a 
* [Docs] Refine README

* refine table

* minor refinement

* refine

* refine

* add version info

* add version info

* update version info

* refine

* refine

* add module links in docs/en/introduction

* update docs/en

* fix typo

* update docs/en

* add version.json in zh_cn

* minor refinement

* update version.json

* update Dockerfile

* minor fix

* update installation of macOS

* resolve comments
@defei-coder @budefei
[Feature] Add getJobLimitCapability interface and use it in nms (open…
be684ee 
…-mmlab#2337)

Co-authored-by: budefei <budefei@cambricon.com>
@defei-coder @budefei
[Fix] Fix the bug of uninitialized prarmeter (open-mmlab#2345)
04ec054 
* [Fix] Fix the bug of uninitialized prarmeter

* refactor code for lint

Co-authored-by: budefei <budefei@cambricon.com>
[Fix] Fix three nn op can not accept half tensor (open-mmlab#2348)
6cf9ac0 
* Fix three nn half inpt

* update test
@zhouzaida
Build macOS wheel in Github Action (open-mmlab#2311)
6d9e4a9 
* Bump version to

* update
@cathyzhang222
[Feature] Support Iou3d with cambricon MLU backend (open-mmlab#2339)
7fd7058 
* [Feature] Support Iou3d with cambricon MLU backend

* [Feature] add double line

* [Feature] add line
[Fix] Fix Correlation op (open-mmlab#2274)
ff18904 
* fix correlation

* fix lint
@okotaku @zhouzaida
[Enhancement] Add a new argument define_metric in wandb hook (open-mm…
9709ff3 
…lab#2237)

* wandb define_metric

* add test and some fix based on mmengine PR

* fix test

* add summary warnings

* Update mmcv/runner/hooks/logger/wandb.py

Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

* Update mmcv/runner/hooks/logger/wandb.py

Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
@ZCMax
[Fix] Fix the potential NaN bug in calc_square_dist() (open-mmlab#2356)
3c35bab
@zhouzaida
[Docs] Update README and fix typo in docs (open-mmlab#2358)
1eef4f5
@grimoire @zhouzaida
[Fix] Fix MPS ops for torch1.12+ (open-mmlab#2302)
f48975b
@zytx121 @zhouzaida
[Feature] Add box_iou_quadri & nms_quadri (open-mmlab#2277)
a4f304a 
* update

* update

* fix link

* fix bug

* update nms_quadri

* fix lint

* Update test_nms_quadri.py

* Update box_iou_quadri.py

* fix bug

* Update test_nms_quadri.py

* Update box_iou_rotated_utils.hpp

* Update box_iou_quadri.py

* Update mmcv/ops/nms.py
VVsssssk and others added 15 commits October 28, 2022 16:53
@VVsssssk @zhouzaida
[Features] Add stack ball query and stack group points ops (open-mmla…
93fe482 
…b#2292)

* add stack sa model ops

* fix lint

* fix lint

* fix comments

* fix bug

* fix lint

* fix comments

* fix lint

* fix lint

* fix
@zhouzaida
Build torch1.13 pre-built package for macOS in CI (open-mmlab#2366)
b513419 
* Add torch1.13 for macOS in CI

* update

* fix typo

* Update
@wangjiangben-hw
[Fix] Fix set_device bug when using multi-machine multi-device (open-…
14e8e49 
…mmlab#2370)
@momo609 @wangjiangben-hw @zhouzaida
[Docs] Add steps to install mmcv-full on NPU machine (open-mmlab#2363)
e2c9fc4 
* Add steps to install mmcv-full on NPU machine

Co-authored-by: wangxiaoxin_sherie <wangxiaoxin7@huawei.com>
Co-authored-by: wangjiangben-hw <111729245+wangjiangben-hw@users.noreply.github.com>
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
@zhouzaida
[Docs] Add maintenance plan and print deprecated message (open-mmlab#…
ff8e0c8 
…2357)

* [Docs] Add maintenance plan

* Update maintenance plan

* Update compatibility.md

* Update README

* resolve comments

* Update README

* Add warning info

* update

* fix typo
@zhouzaida
Bump version to v1.7.0 (open-mmlab#2362)
270c293 
* Bump version to v1.7.0

* remove deprecated message
@ZhangLearning
[Feature] Support RoIAwarePool3d with cambricon MLU backend (open-mml…
b622fb2 
…ab#2359)

* [Feature] Support RoiawarePool3d with cambricon MLU backend.

* [Feature] Support RoiawarePool3d with cambricon MLU backend.
@wangjiangben-hw @ckirchhoff2021
init npu
ff3ffbb
@ckirchhoff2021
add npu extension and focal loss adapter
57e4171
@ckirchhoff2021
clean code
65b5fe1
@ckirchhoff2021
clean code
f38b1b2
@ckirchhoff2021
clean code
f5c156f
@ckirchhoff2021
add modulatedDeformConv npu adapter
c5ffc60
@ckirchhoff2021
merge master branch 20221103
bd3ec11
@ckirchhoff2021
remove conflicts
74d3181
@ckirchhoff2021 ckirchhoff2021 merged commit 632e853 into open-mmlab:npu-dev Nov 3, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees

@zhouzaida zhouzaida

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.