[Feature] Support RoITransRoIHead by nijkah · Pull Request #713 · open-mmlab/mmdeploy

nijkah · 2022-07-06T10:55:29Z

Motivation

Support RoITransRoIHead for RoI-Transformer in MMrotate.
Note that it can be used after #650 is merged, which fixes rotated_rpn_head.

Modification

Add Rewriter for RoITransRoIHead.simple_test.

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

add rewritings for RoITransRoIHead
Performance check with TensorRT model
Add docs
Add a unit test

mmrotate				Pytorch	ONNXRuntime	TensorRT		PPLNN	OpenVINO
model	task	dataset	metrics	fp32	fp32	fp32	fp16	fp16	fp32
RoITransformer R50	Rotated Detection	DOTA-v1.0	mAP	0.761	-	0.758	-	-	-
RoITransformer Swin-tiny	Rotated Detection	DOTA-v1.0	mAP	0.775	-	0.774	-	-	-

mmdeploy/codebase/mmrotate/models/roi_trans_roi_head.py

docs/en/03-benchmark/benchmark.md

nijkah · 2022-07-13T06:05:27Z

I found that the predicted result is quite different compared to the pytorch model in some scenes.
Tested with roi_trans_swin_tiny_fpn_1x_dota_le90

# root @ ws-hakjin-6db678b6-nvvqr in ~/workspace/mmrotate on git:main x [5:44:50]
$ head ~/workspace/mmdeploy/roi_trans_2643/Task1_results/Task1_baseball-diamond.txt                                                                                                                                                    31s
P2643 0.637549102306366 4702.72 3994.82 4804.41 3979.51 4819.57 4080.20 4717.88 4095.52
P2643 0.5205038189888 4357.66 3713.31 4459.15 3715.00 4457.63 3806.84 4356.13 3805.15
P2643 0.2156124860048294 3813.04 1393.61 4096.71 1429.80 4067.03 1662.41 3783.37 1626.22
P2643 0.17779527604579926 4675.29 3776.19 4789.58 3777.87 4788.11 3877.54 4673.82 3875.86
P2643 0.13109613955020905 4043.61 1685.51 4193.22 1657.14 4220.51 1801.02 4070.89 1829.39
P2643 0.11649016290903091 4798.06 3864.99 4907.36 3865.03 4907.32 3969.31 4798.02 3969.26
P2643 0.07121634483337402 5127.67 1503.08 5233.58 1514.99 5221.62 1621.30 5115.71 1609.39
P2643 0.06801088899374008 4566.45 3689.70 4668.94 3691.34 4667.43 3785.29 4564.94 3783.65

# root @ ws-hakjin-6db678b6-nvvqr in ~/workspace/mmrotate on git:main x [5:45:27]
$ head roi_trans_2643/Task1_results/Task1_baseball-diamond.txt                                                                                                                                                                         0s
P2643 0.698990523815155 4709.87 3986.23 4813.27 3987.07 4812.44 4089.49 4709.03 4088.65
P2643 0.5733247995376587 4366.51 3707.61 4462.31 3721.79 4448.91 3812.37 4353.11 3798.19
P2643 0.21527588367462158 3813.04 1393.60 4096.72 1429.80 4067.03 1662.42 3783.36 1626.22
P2643 0.2114844024181366 4564.14 3693.04 4667.32 3690.62 4669.47 3782.47 4566.29 3784.88
P2643 0.1629500836133957 4042.65 1700.25 4193.81 1666.58 4221.50 1790.89 4070.35 1824.57
P2643 0.12476478517055511 4670.28 3782.63 4790.91 3778.71 4793.93 3871.49 4673.29 3875.41
P2643 0.11624093353748322 4790.71 3878.29 4899.42 3859.01 4917.20 3959.27 4808.49 3978.55
P2643 0.08829200267791748 5123.39 1503.52 5229.69 1507.54 5225.33 1622.82 5119.03 1618.80

grimoire · 2022-07-13T09:36:03Z

@nijkah I have fixed a bug of TRT Rotated NMS in #650. Not sure if it is related to the accuracy.

RunningLeon · 2022-07-14T07:16:08Z

@nijkah Hi, since #650 is merged, could merge master and fix the conflicts?

mmdeploy/codebase/mmrotate/models/roi_heads/roi_trans_roi_head.py

tests/test_codebase/test_mmrotate/test_mmrotate_models.py

nijkah · 2022-07-14T09:26:00Z

I found that the predicted result is quite different compared to the pytorch model in some scenes. Tested with roi_trans_swin_tiny_fpn_1x_dota_le90

# root @ ws-hakjin-6db678b6-nvvqr in ~/workspace/mmrotate on git:main x [5:44:50]
$ head ~/workspace/mmdeploy/roi_trans_2643/Task1_results/Task1_baseball-diamond.txt                                                                                                                                                    31s
P2643 0.637549102306366 4702.72 3994.82 4804.41 3979.51 4819.57 4080.20 4717.88 4095.52
P2643 0.5205038189888 4357.66 3713.31 4459.15 3715.00 4457.63 3806.84 4356.13 3805.15
P2643 0.2156124860048294 3813.04 1393.61 4096.71 1429.80 4067.03 1662.41 3783.37 1626.22
P2643 0.17779527604579926 4675.29 3776.19 4789.58 3777.87 4788.11 3877.54 4673.82 3875.86
P2643 0.13109613955020905 4043.61 1685.51 4193.22 1657.14 4220.51 1801.02 4070.89 1829.39
P2643 0.11649016290903091 4798.06 3864.99 4907.36 3865.03 4907.32 3969.31 4798.02 3969.26
P2643 0.07121634483337402 5127.67 1503.08 5233.58 1514.99 5221.62 1621.30 5115.71 1609.39
P2643 0.06801088899374008 4566.45 3689.70 4668.94 3691.34 4667.43 3785.29 4564.94 3783.65

# root @ ws-hakjin-6db678b6-nvvqr in ~/workspace/mmrotate on git:main x [5:45:27]
$ head roi_trans_2643/Task1_results/Task1_baseball-diamond.txt                                                                                                                                                                         0s
P2643 0.698990523815155 4709.87 3986.23 4813.27 3987.07 4812.44 4089.49 4709.03 4088.65
P2643 0.5733247995376587 4366.51 3707.61 4462.31 3721.79 4448.91 3812.37 4353.11 3798.19
P2643 0.21527588367462158 3813.04 1393.60 4096.72 1429.80 4067.03 1662.42 3783.36 1626.22
P2643 0.2114844024181366 4564.14 3693.04 4667.32 3690.62 4669.47 3782.47 4566.29 3784.88
P2643 0.1629500836133957 4042.65 1700.25 4193.81 1666.58 4221.50 1790.89 4070.35 1824.57
P2643 0.12476478517055511 4670.28 3782.63 4790.91 3778.71 4793.93 3871.49 4673.29 3875.41
P2643 0.11624093353748322 4790.71 3878.29 4899.42 3859.01 4917.20 3959.27 4808.49 3978.55
P2643 0.08829200267791748 5123.39 1503.52 5229.69 1507.54 5225.33 1622.82 5119.03 1618.80

@RunningLeon, I am debugging the performance gap between the pytorch model and ONNX & TRT models.
Until now, I found that the result from the TRT wrapper and the result from the pytorch model are same exactly.
But the merged results are quite different like

# root @ ws-hakjin-69b98d88f6-sm7sz in ~/workspace/mmdeploy on git:fa57490 x [9:23:39] C:130
$ head roi_trans_r50_new_trt/Task1_results/Task1_baseball-diamond.txt                                                                                                                                                                  58s
P2643 0.7715607285499573 3740.97 1459.14 4017.96 1389.74 4064.57 1575.78 3787.58 1645.17
P2643 0.733237624168396 4710.55 3990.44 4813.93 3984.44 4819.73 4084.44 4716.35 4090.44
P2643 0.5749783515930176 4351.68 3725.28 4454.60 3708.67 4469.04 3798.17 4366.12 3814.78
P2643 0.5543936491012573 4570.47 3689.56 4668.08 3688.10 4669.53 3784.78 4571.91 3786.24
P2643 0.5379559397697449 4473.94 3808.90 4575.48 3805.35 4578.92 3904.00 4477.39 3907.54
P2643 0.46451470255851746 4666.36 3789.71 4774.49 3766.58 4796.84 3871.09 4688.71 3894.22
P2643 0.3679143488407135 3994.14 1690.57 4183.64 1632.95 4237.47 1809.98 4047.96 1867.60
P2643 0.27642694115638733 5123.77 1526.21 5217.41 1516.35 5225.56 1593.80 5131.92 1603.65
P2643 0.2661984860897064 4447.88 3595.96 4552.39 3602.76 4546.04 3700.35 4441.53 3693.55
P2643 0.24539612233638763 4803.45 3866.50 4909.08 3874.35 4901.79 3972.31 4796.17 3964.45

# root @ ws-hakjin-69b98d88f6-sm7sz in ~/workspace/mmdeploy on git:fa57490 x [9:23:44]
$ head ../mmrotate/roi_trans_r50/Task1_results/Task1_baseball-diamond.txt                                                                                                                                                               0s
P2643 0.7718087434768677 3740.95 1459.16 4017.98 1389.70 4064.62 1575.74 3787.59 1645.20
P2643 0.7333663702011108 4710.55 3990.44 4813.93 3984.45 4819.72 4084.44 4716.34 4090.43
P2643 0.5752703547477722 4351.69 3725.28 4454.60 3708.68 4469.04 3798.18 4366.13 3814.78
P2643 0.554319441318512 4570.46 3689.57 4668.08 3688.09 4669.55 3784.76 4571.93 3786.25
P2643 0.5378356575965881 4473.93 3808.91 4575.46 3805.34 4578.94 3903.98 4477.40 3907.55
P2643 0.4634431302547455 4666.34 3789.74 4774.46 3766.56 4796.87 3871.07 4688.74 3894.25
P2643 0.431684672832489 5122.15 1530.39 5211.60 1512.09 5227.39 1589.27 5137.94 1607.57
P2643 0.40507709980010986 4025.09 1672.99 4196.97 1659.46 4210.63 1832.99 4038.75 1846.52
P2643 0.35206887125968933 4795.44 3873.99 4903.55 3864.99 4911.75 3963.35 4803.63 3972.35
P2643 0.26584571599960327 4442.42 3600.27 4545.86 3593.95 4551.90 3692.87 4448.46 3699.19

I wonder where the postprocessing_params are used in. I suspect the difference arises in the postprocessing part.

RunningLeon · 2022-07-15T02:19:37Z

@nijkah Hi, postprocess params are used in nms like here:

mmdeploy/mmdeploy/codebase/mmrotate/models/dense_heads/rotated_rpn_head.py

Line 136 in d216af8

return multiclass_nms(

grimoire · 2022-07-15T02:25:23Z

Hi, which ONNXRuntime version are you using? The unit test failed with log:

onnxruntime.capi.onnxruntime_pybind11_state.NotImplemented: [ONNXRuntimeError] : 9 : NOT_IMPLEMENTED : Could not find an implementation for Floor(6) node with name 'Floor_4'

nijkah · 2022-07-15T04:08:04Z

Hi, which ONNXRuntime version are you using? The unit test failed with log:

onnxruntime.capi.onnxruntime_pybind11_state.NotImplemented: [ONNXRuntimeError] : 9 : NOT_IMPLEMENTED : Could not find an implementation for Floor(6) node with name 'Floor_4'

I'm sorry, I faced the same error. I am still troubleshooting this.
FYI, I already tested with the onnx_static and onnx_dynamic deploy_cfg, and checked the conversion and the prediction is normal.

nijkah · 2022-07-18T02:56:31Z

@grimoire ~~The error raises in the SingleRoIExtractor which is not rewritten. I am troubleshooting to use rewriten SingleRoIExtractor to test mmrotate models.~~

The error raises in the line,
https://github.com/open-mmlab/mmdetection/blob/56e42e72cdf516bebb676e586f408b98f854d84c/mmdet/models/roi_heads/roi_extractors/single_level_roi_extractor.py#L53.
I'm troubleshooting now.

nijkah · 2022-07-18T05:29:12Z

@grimoire @RunningLeon I may find the cause. Since finest_scale is set to 56, the proposal should be larger than this.
Can I ask you to check it?

In addition to this, is it okay to insert mmrotate in the requirements/codebases.txt to test the code by CircleCI?

RunningLeon · 2022-07-19T01:48:29Z

@grimoire @RunningLeon I may find the cause. Since finest_scale is set to 56, the proposal should be larger than this. Can I ask you to check it?

In addition to this, is it okay to insert mmrotate in the requirements/codebases.txt to test the code by CircleCI?

@nijkah Hi, adding mmrotate to requirements/codebases.txt is OK for me.

nijkah · 2022-07-19T02:30:17Z

The new requirement installation is currently canceled due to a dependency conflict between numba and numpy.
https://app.circleci.com/pipelines/github/open-mmlab/mmdeploy/1235/workflows/88534aa7-1147-47ec-855d-568b4caf027d/jobs/1983?invite=true#step-110-336

It happened in the previous PRs too. CircleCI Link

Should we specify the supported numpy version?

RunningLeon · 2022-07-19T07:00:16Z

The new requirement installation is currently canceled due to a dependency conflict between numba and numpy. https://app.circleci.com/pipelines/github/open-mmlab/mmdeploy/1235/workflows/88534aa7-1147-47ec-855d-568b4caf027d/jobs/1983?invite=true#step-110-336

It happened in the previous PRs too. CircleCI Link

Should we specify the supported numpy version?

In that case, maybe we should not add mmrotate in circleci. This PR would be tested locally. The numpy version conflicts in CI should be coped with carefully in another PR.

This reverts commit 0434900.

RunningLeon

LGTM

nijkah · 2022-07-20T02:40:27Z

I am still troubleshooting the test code related to the line of SingleRoIExtractor.map_roi_levels. (It works well in tools/deploy.py and tools/test.py)

The failure reason of the test code is that the tensor is cast to Double type, although it is float type in tests/test_codebase/test_mmdet/test_mmdet_models.py::test_cascade_roi_head.

After changing the line as

        target_lvls = torch.floor(torch.log2(scale / self.finest_scale + 1e-6)).float()

I found it works.

Changing the test sample for proposals or casting it to float type doesn't work. 😢
So I'm still debugging it.

RunningLeon · 2022-07-20T03:51:29Z

I am still troubleshooting the test code related to the line of SingleRoIExtractor.map_roi_levels. (It works well in tools/deploy.py and tools/test.py)

The failure reason of the test code is that the tensor is cast to Double type, although it is float type in tests/test_codebase/test_mmdet/test_mmdet_models.py::test_cascade_roi_head.

After changing the line as
        target_lvls = torch.floor(torch.log2(scale / self.finest_scale + 1e-6)).float()
I found it works.

Changing the test sample for proposals or casting it to float type doesn't work. cry So I'm still debugging it.

test_simple_test_of_roi_trans_roi_head runs successfully on my side with onnx==1.11.0 and onnxruntime==1.8.0

nijkah · 2022-07-20T04:14:49Z

Okay, I understand. The following issues will be left as future work. I'll follow these issues.

Close performance gap between TRT and pytorch model. (Maybe due to the logic of merging patched results or polygonization error? not sure)
Add a mmrotate in requirements to support the unit test in CircleCI
Check a unit test in other settings (different onnx and onnxruntime version)

RunningLeon · 2022-07-21T09:37:32Z

I found it works.
Changing the test sample for proposals or casting it to float type doesn't work. cry So I'm still debugging it.

test_simple_test_of_roi_trans_roi_head runs successfully on my side with onnx==1.11.0 and onnxruntime==1.8.0

@nijkah
Seems OK with me.

nijkah · 2022-07-22T00:28:22Z

@RunningLeon I apologize for my ambiguous words. I meant that I will follow related issues after this PR is merged.
I agree that the PR is ready to be merged.

grimoire

LGTM

* make -install -> make install (#621) change `make -install` to `make install` #618 * [Fix] fix csharp api detector release result (#620) * fix csharp api detector release result * fix wrong count arg of xxx_release_result in c# api * [Enhancement] Support two-stage rotated detector TensorRT. (#530) * upload * add fake_multiclass_nms_rotated * delete unused code * align with pytorch * Update delta_midpointoffset_rbbox_coder.py * add trt rotated roi align * add index feature in nms * not good * fix index * add ut * add benchmark * move to csrc/mmdeploy * update unit test Co-authored-by: zytx121 <592267829@qq.com> * Reduce mmcls version dependency (#635) * fix shufflenetv2 with trt (#645) * fix shufflenetv2 and pspnet * fix ci * remove print * ' -> " (#654) If there is a variable in the string, single quotes will ignored it, while double quotes will bring the variable into the string after parsing * ' -> " (#655) same with #654 * Support deployment of Segmenter (#587) * support segmentor with ncnn * update regression yml * replace chunk with split to support ts * update regression yml * update docs * fix segmenter ncnn inference failure brought by #477 * add test * fix test for ncnn and trt * fix lint * export nn.linear to Gemm op in onnx for ncnn * fix ci * simplify `Expand` (#617) * Fix typo (#625) * Add make install in en docs * Add make install in zh docs * Fix typo * Merge and add windows build Co-authored-by: tripleMu <865626@163.com> * [Enhancement] Fix ncnn unittest (#626) * optmize-csp-darknet * replace floordiv to torch.div * update csp_darknet default implement * fix test * [Enhancement] TensorRT Anchor generator plugin (#646) * custom trt anchor generator * add ut * add docstring, update doc * Add partition doc and sample code (#599) * update torch2onnx tool to support onnx partition * add model partition of yolov3 * add cn doc * update torch2onnx tool to support onnx partition * add model partition of yolov3 * add cn doc * add to index.rst * resolve comment * resolve comments * fix lint * change caption level in docs * update docs (#624) * Add java apis and demos (#563) * add java classifier detector * add segmentor * fix lint * add ImageRestorer java apis and demo * remove useless count parameter for Segmentor and Restorer, add PoseDetector * add RotatedDetection java api and demo * add Ocr java demo and apis * remove mmrotate ncnn java api and demo * fix lint * sync java api folder after rebase to master * fix include * remove record * fix java apis dir path in cmake * add java demo readme * fix lint mdformat * add test javaapi ci * fix lint * fix flake8 * fix test javaapi ci * refactor readme.md * fix install opencv for ci * fix install opencv : add permission * add all codebases and mmcv install * add torch * install mmdeploy * fix image path * fix picture path * fix import ncnn * fix import ncnn * add submodule of pybind * fix pybind submodule * change download to git clone for submodule * fix ncnn dir * fix README error * simplify the github ci * fix ci * fix yapf * add JNI as required * fix Capitalize * fix Capitalize * fix copyright * ignore .class changed * add OpenJDK installation docs * install target of javaapi * simplify ci * add jar * fix ci * fix ci * fix test java command * debugging what failed * debugging what failed * debugging what failed * add java version info * install openjdk * add java env var * fix export * fix export * fix export * fix export * fix picture path * fix picture path * fix file name * fix file name * fix README * remove java_api strategy * fix python version * format task name * move args position * extract common utils code * show image class result * add detector result * segmentation result format * add ImageRestorer result * add PoseDetection java result format * fix ci * stage ocr * add visualize * move utils * fix lint * fix ocr bugs * fix ci demo * fix java classpath for ci * fix popd * fix ocr demo text garbled * fix ci * fix ci * fix ci * fix path of utils ci * update the circleci config file by adding workflows both for linux, windows and linux-gpu (#368) * update circleci by adding more workflows * fix test workflow failure on windows platform * fix docker exec command for SDK unittests * Fixed tensorrt plugin not found in Windows (#672) * update introduction.png (#674) * [Enhancement] Add fuse select assign pass (#589) * Add fuse select assign pass * move code to csrc * add config flag * remove bool cast * fix export sdk info of input shape (#667) * Update get_started.md (#675) Fix backend model assignment * Update get_started.md (#676) Fix backend model assignment * [Fix] fix clang build (#677) * fix clang build * fix ndk build * fix ndk build * switch to `std::filesystem` for clang-7 and later * Deploy the Swin Transformer on TensorRT. (#652) * resolve conflicts * update ut and docs * fix ut * refine docstring * add comments and refine UT * resolve comments * resolve comments * update doc * add roll export * check backend * update regression test * bump version to 0.6.0 (#680) * bump vertion to 0.6.0 * update version * pass img_metas while exporting to onnx (#681) * pass img_metas while exporting to onnx * remove try-catch in tools for beter debugging * use get * fix typo * [Fix] fix ssd ncnn ut (#692) * fix ssd ncnn ut * fix yapf * fix passing img_metas to pytorch2onnx for mmedit (#700) * fix passing img_metas for mmdet3d (#707) * [Fix] Fix android build (#698) * fix android build * fix cmake * fix url link * fix wrong exit code in pipeline_manager (#715) * fix exit * change to general exit errorcode=1 * fix passing wrong backend type (#719) * Rename onnx2ncnn to mmdeploy_onnx2ncnn (#694) * improvement(tools/onnx2ncnn.py): rename to mmdeploy_onnx2ncnn * format(tools/deploy.py): clean code * fix(init_plugins.py): improve if condition * fix(CI): update target * fix(test_onnx2ncnn.py): update desc * Update init_plugins.py * [Fix] Fix mmdet ort static shape bug (#687) * fix shape * add device * fix yapf * fix rewriter for transforms * reverse image shape * fix ut of distance2bbox * fix rewriter name * fix c4 for torchscript (#724) * [Enhancement] Standardize C API (#634) * unify C API naming * fix demo and move apis/c/* -> apis/c/mmdeploy/* * fix lint * fix C# project * fix Java API * [Enhancement] Support Slide Vertex TRT (#650) * reorgnize mmrotate * fix * add hbb2obb * add ut * fix rotated nms * update docs * update benchmark * update test * remove ort regression test, remove comment * Fix get-started rendering issues in readthedocs (#740) * fix mermaid markdown rendering issue in readthedocs * fix error in C++ example * fix error in c++ example in zh_cn get_started doc * [Fix] set default topk for dump info (#702) * set default topk for dump info * remove redundant docstrings * add ci densenet * fix classification warnings * fix mmcls version * fix logger.warnings * add version control (#754) * fix satrn for ORT (#753) * fix satrn for ORT * move rewrite into pytorch * Add inference latency test tool (#665) * add profile tool * remove print envs in profile tool * set cudnn_benchmark to True * add doc * update tests * fix typo * support test with images from a directory * update doc * resolve comments * [Enhancement] Add CSE ONNX pass (#647) * Add fuse select assign pass * move code to csrc * add config flag * Add fuse select assign pass * Add CSE for ONNX * remove useless code * Test robot Just test robot * Update README.md Revert * [Fix] fix yolox point_generator (#758) * fix yolox point_generator * add a UT * resolve comments * fix comment lines * limit markdown version (#773) * [Enhancement] Better index put ONNX export. (#704) * Add rewriter for tensor setitem * add version check * Upgrade Dockerfile to use TensorRT==8.2.4.2 (#706) * Upgrade TensorRT to 8.2.4.2 * upgrade pytorch&mmcv in CPU Dockerfile * Delete redundant port example in Docker * change 160x160-608x608 to 64x64-608x608 for yolov3 * [Fix] reduce log verbosity & improve error reporting (#755) * reduce log verbosity & improve error reporting * improve error reporting * [Enhancement] Support latest ppl.nn & ppl.cv (#564) * support latest ppl.nn * fix pplnn for model convertor * fix lint * update memory policy * import algo from buffer * update ppl.cv * use `ppl.cv==0.7.0` * document supported ppl.nn version * skip pplnn dependency when building shared libs * [Fix][P0] Fix for torch1.12 (#751) * fix for torch1.12 * add comment * fix check env (#785) * [Fix] fix cascade mask rcnn (#787) * fix cascade mask rcnn * fix lint * add regression * [Feature] Support RoITransRoIHead (#713) * [Feature] Support RoITransRoIHead * Add docs * Add mmrotate models regression test * Add a draft for test code * change the argument name * fix test code * fix minor change for not class agnostic case * fix sample for test code * fix sample for test code * Add mmrotate in requirements * Revert "Add mmrotate in requirements" This reverts commit 0434900. * [Fix] fix triu (#792) * fix triu * triu -> triu_default * [Enhancement] Install Optimizer by setuptools (#690) * Add fuse select assign pass * move code to csrc * add config flag * Add fuse select assign pass * Add CSE for ONNX * remove useless code * Install optimizer by setup tools * fix comment * [Feature] support MMRotate model with le135 (#788) * support MMRotate model with le135 * cse before fuse select assign * remove unused import * [Fix] Support macOS build (#762) * fix macOS build * fix missing * add option to build & install examples (#822) * [Fix] Fix setup on non-linux-x64 (#811) * fix setup * replace long to int64_t * [Feature] support build single sdk library (#806) * build single lib for c api * update csharp doc & project * update test build * fix test build * fix * update document for building android sdk (#817) Co-authored-by: dwSun <dwsunny@icloud.com> * [Enhancement] support kwargs in SDK python bindings (#794) * support-kwargs * make '__call__' as single image inference and add 'batch' API to deal with batch images inference * fix linting error and typo * fix lint * improvement(sdk): add sdk code coverage (#808) * feat(doc): add CI * CI(sdk): add sdk coverage * style(test): code format * fix(CI): update coverage.info path * improvement(CI): use internal image * improvement(CI): push coverage info once * [Feature] Add C++ API for SDK (#831) * add C++ API * unify result type & add examples * minor fix * install cxx API headers * fix Mat, add more examples * fix monolithic build & fix lint * install examples correctly * fix lint * feat(tools/deploy.py): support snpe (#789) * fix(tools/deploy.py): support snpe * improvement(backend/snpe): review advices * docs(backend/snpe): update build * docs(backend/snpe): server support specify port * docs(backend/snpe): update path * fix(backend/snpe): time counter missing argument * docs(backend/snpe): add missing argument * docs(backend/snpe): update download and using * improvement(snpe_net.cpp): load model with modeldata * Support setup on environment with no PyTorch (#843) * support test with multi batch (#829) * support test with multi batch * resolve comment * import algorithm from buffer (#793) * [Enhancement] build sdk python api in standard-alone manner (#810) * build sdk python api in standard-alone manner * enable MMDEPLOY_BUILD_SDK_MONOLITHIC and MMDEPLOY_BUILD_EXAMPLES in prebuild config * link mmdeploy to python target when monolithic option is on * checkin README to describe precompiled package build procedure * use packaging.version.parse(python_version) instead of list(python_version) * fix according to review results * rebase master * rollback cmake.in and apis/python/CMakeLists.txt * reorganize files in install/example * let cmake detect visual studio instead of specifying 2019 * rename whl name of precompiled package * fix according to review results * Fix SDK backend (#844) * fix mmpose python api (#852) * add prebuild package usage docs on windows (#816) * add prebuild package usage docs on windows * fix lint * update * try fix lint * add en docs * update * update * udpate faq * fix typo (#862) * [Enhancement] Improve get_started documents and bump version to 0.7.0 (#813) * simplify commands in get_started * add installation commands for Windows * fix typo * limit markdown and sphinx_markdown_tables version * adopt html <details open> tag * bump mmdeploy version * bump mmdeploy version * update get_started * update get_started * use python3.8 instead of python3.7 * remove duplicate section * resolve issue #856 * update according to review results * add reference to prebuilt_package_windows.md * fix error when build sdk demos * fix mmcls Co-authored-by: Ryan_Huang <44900829+DrRyanHuang@users.noreply.github.com> Co-authored-by: Chen Xin <xinchen.tju@gmail.com> Co-authored-by: q.yao <yaoqian@sensetime.com> Co-authored-by: zytx121 <592267829@qq.com> Co-authored-by: Li Zhang <lzhang329@gmail.com> Co-authored-by: tripleMu <gpu@163.com> Co-authored-by: tripleMu <865626@163.com> Co-authored-by: hanrui1sensetime <83800577+hanrui1sensetime@users.noreply.github.com> Co-authored-by: lvhan028 <lvhan_028@163.com> Co-authored-by: Bryan Glen Suello <11388006+bgsuello@users.noreply.github.com> Co-authored-by: zambranohally <63218980+zambranohally@users.noreply.github.com> Co-authored-by: AllentDan <41138331+AllentDan@users.noreply.github.com> Co-authored-by: tpoisonooo <khj.application@aliyun.com> Co-authored-by: Hakjin Lee <nijkah@gmail.com> Co-authored-by: 孙德伟 <5899962+dwSun@users.noreply.github.com> Co-authored-by: dwSun <dwsunny@icloud.com> Co-authored-by: Chen Xin <irexyc@gmail.com>

* make -install -> make install (#621) change `make -install` to `make install` #618 * [Fix] fix csharp api detector release result (#620) * fix csharp api detector release result * fix wrong count arg of xxx_release_result in c# api * [Enhancement] Support two-stage rotated detector TensorRT. (#530) * upload * add fake_multiclass_nms_rotated * delete unused code * align with pytorch * Update delta_midpointoffset_rbbox_coder.py * add trt rotated roi align * add index feature in nms * not good * fix index * add ut * add benchmark * move to csrc/mmdeploy * update unit test Co-authored-by: zytx121 <592267829@qq.com> * Reduce mmcls version dependency (#635) * fix shufflenetv2 with trt (#645) * fix shufflenetv2 and pspnet * fix ci * remove print * ' -> " (#654) If there is a variable in the string, single quotes will ignored it, while double quotes will bring the variable into the string after parsing * ' -> " (#655) same with #654 * Support deployment of Segmenter (#587) * support segmentor with ncnn * update regression yml * replace chunk with split to support ts * update regression yml * update docs * fix segmenter ncnn inference failure brought by #477 * add test * fix test for ncnn and trt * fix lint * export nn.linear to Gemm op in onnx for ncnn * fix ci * simplify `Expand` (#617) * Fix typo (#625) * Add make install in en docs * Add make install in zh docs * Fix typo * Merge and add windows build Co-authored-by: tripleMu <865626@163.com> * [Enhancement] Fix ncnn unittest (#626) * optmize-csp-darknet * replace floordiv to torch.div * update csp_darknet default implement * fix test * [Enhancement] TensorRT Anchor generator plugin (#646) * custom trt anchor generator * add ut * add docstring, update doc * Add partition doc and sample code (#599) * update torch2onnx tool to support onnx partition * add model partition of yolov3 * add cn doc * update torch2onnx tool to support onnx partition * add model partition of yolov3 * add cn doc * add to index.rst * resolve comment * resolve comments * fix lint * change caption level in docs * update docs (#624) * Add java apis and demos (#563) * add java classifier detector * add segmentor * fix lint * add ImageRestorer java apis and demo * remove useless count parameter for Segmentor and Restorer, add PoseDetector * add RotatedDetection java api and demo * add Ocr java demo and apis * remove mmrotate ncnn java api and demo * fix lint * sync java api folder after rebase to master * fix include * remove record * fix java apis dir path in cmake * add java demo readme * fix lint mdformat * add test javaapi ci * fix lint * fix flake8 * fix test javaapi ci * refactor readme.md * fix install opencv for ci * fix install opencv : add permission * add all codebases and mmcv install * add torch * install mmdeploy * fix image path * fix picture path * fix import ncnn * fix import ncnn * add submodule of pybind * fix pybind submodule * change download to git clone for submodule * fix ncnn dir * fix README error * simplify the github ci * fix ci * fix yapf * add JNI as required * fix Capitalize * fix Capitalize * fix copyright * ignore .class changed * add OpenJDK installation docs * install target of javaapi * simplify ci * add jar * fix ci * fix ci * fix test java command * debugging what failed * debugging what failed * debugging what failed * add java version info * install openjdk * add java env var * fix export * fix export * fix export * fix export * fix picture path * fix picture path * fix file name * fix file name * fix README * remove java_api strategy * fix python version * format task name * move args position * extract common utils code * show image class result * add detector result * segmentation result format * add ImageRestorer result * add PoseDetection java result format * fix ci * stage ocr * add visualize * move utils * fix lint * fix ocr bugs * fix ci demo * fix java classpath for ci * fix popd * fix ocr demo text garbled * fix ci * fix ci * fix ci * fix path of utils ci * update the circleci config file by adding workflows both for linux, windows and linux-gpu (#368) * update circleci by adding more workflows * fix test workflow failure on windows platform * fix docker exec command for SDK unittests * Fixed tensorrt plugin not found in Windows (#672) * update introduction.png (#674) * [Enhancement] Add fuse select assign pass (#589) * Add fuse select assign pass * move code to csrc * add config flag * remove bool cast * fix export sdk info of input shape (#667) * Update get_started.md (#675) Fix backend model assignment * Update get_started.md (#676) Fix backend model assignment * [Fix] fix clang build (#677) * fix clang build * fix ndk build * fix ndk build * switch to `std::filesystem` for clang-7 and later * Deploy the Swin Transformer on TensorRT. (#652) * resolve conflicts * update ut and docs * fix ut * refine docstring * add comments and refine UT * resolve comments * resolve comments * update doc * add roll export * check backend * update regression test * bump version to 0.6.0 (#680) * bump vertion to 0.6.0 * update version * pass img_metas while exporting to onnx (#681) * pass img_metas while exporting to onnx * remove try-catch in tools for beter debugging * use get * fix typo * [Fix] fix ssd ncnn ut (#692) * fix ssd ncnn ut * fix yapf * fix passing img_metas to pytorch2onnx for mmedit (#700) * fix passing img_metas for mmdet3d (#707) * [Fix] Fix android build (#698) * fix android build * fix cmake * fix url link * fix wrong exit code in pipeline_manager (#715) * fix exit * change to general exit errorcode=1 * fix passing wrong backend type (#719) * Rename onnx2ncnn to mmdeploy_onnx2ncnn (#694) * improvement(tools/onnx2ncnn.py): rename to mmdeploy_onnx2ncnn * format(tools/deploy.py): clean code * fix(init_plugins.py): improve if condition * fix(CI): update target * fix(test_onnx2ncnn.py): update desc * Update init_plugins.py * [Fix] Fix mmdet ort static shape bug (#687) * fix shape * add device * fix yapf * fix rewriter for transforms * reverse image shape * fix ut of distance2bbox * fix rewriter name * fix c4 for torchscript (#724) * [Enhancement] Standardize C API (#634) * unify C API naming * fix demo and move apis/c/* -> apis/c/mmdeploy/* * fix lint * fix C# project * fix Java API * [Enhancement] Support Slide Vertex TRT (#650) * reorgnize mmrotate * fix * add hbb2obb * add ut * fix rotated nms * update docs * update benchmark * update test * remove ort regression test, remove comment * Fix get-started rendering issues in readthedocs (#740) * fix mermaid markdown rendering issue in readthedocs * fix error in C++ example * fix error in c++ example in zh_cn get_started doc * [Fix] set default topk for dump info (#702) * set default topk for dump info * remove redundant docstrings * add ci densenet * fix classification warnings * fix mmcls version * fix logger.warnings * add version control (#754) * fix satrn for ORT (#753) * fix satrn for ORT * move rewrite into pytorch * Add inference latency test tool (#665) * add profile tool * remove print envs in profile tool * set cudnn_benchmark to True * add doc * update tests * fix typo * support test with images from a directory * update doc * resolve comments * [Enhancement] Add CSE ONNX pass (#647) * Add fuse select assign pass * move code to csrc * add config flag * Add fuse select assign pass * Add CSE for ONNX * remove useless code * Test robot Just test robot * Update README.md Revert * [Fix] fix yolox point_generator (#758) * fix yolox point_generator * add a UT * resolve comments * fix comment lines * limit markdown version (#773) * [Enhancement] Better index put ONNX export. (#704) * Add rewriter for tensor setitem * add version check * Upgrade Dockerfile to use TensorRT==8.2.4.2 (#706) * Upgrade TensorRT to 8.2.4.2 * upgrade pytorch&mmcv in CPU Dockerfile * Delete redundant port example in Docker * change 160x160-608x608 to 64x64-608x608 for yolov3 * [Fix] reduce log verbosity & improve error reporting (#755) * reduce log verbosity & improve error reporting * improve error reporting * [Enhancement] Support latest ppl.nn & ppl.cv (#564) * support latest ppl.nn * fix pplnn for model convertor * fix lint * update memory policy * import algo from buffer * update ppl.cv * use `ppl.cv==0.7.0` * document supported ppl.nn version * skip pplnn dependency when building shared libs * [Fix][P0] Fix for torch1.12 (#751) * fix for torch1.12 * add comment * fix check env (#785) * [Fix] fix cascade mask rcnn (#787) * fix cascade mask rcnn * fix lint * add regression * [Feature] Support RoITransRoIHead (#713) * [Feature] Support RoITransRoIHead * Add docs * Add mmrotate models regression test * Add a draft for test code * change the argument name * fix test code * fix minor change for not class agnostic case * fix sample for test code * fix sample for test code * Add mmrotate in requirements * Revert "Add mmrotate in requirements" This reverts commit 0434900. * [Fix] fix triu (#792) * fix triu * triu -> triu_default * [Enhancement] Install Optimizer by setuptools (#690) * Add fuse select assign pass * move code to csrc * add config flag * Add fuse select assign pass * Add CSE for ONNX * remove useless code * Install optimizer by setup tools * fix comment * [Feature] support MMRotate model with le135 (#788) * support MMRotate model with le135 * cse before fuse select assign * remove unused import * [Fix] Support macOS build (#762) * fix macOS build * fix missing * add option to build & install examples (#822) * [Fix] Fix setup on non-linux-x64 (#811) * fix setup * replace long to int64_t * [Feature] support build single sdk library (#806) * build single lib for c api * update csharp doc & project * update test build * fix test build * fix * update document for building android sdk (#817) Co-authored-by: dwSun <dwsunny@icloud.com> * [Enhancement] support kwargs in SDK python bindings (#794) * support-kwargs * make '__call__' as single image inference and add 'batch' API to deal with batch images inference * fix linting error and typo * fix lint * improvement(sdk): add sdk code coverage (#808) * feat(doc): add CI * CI(sdk): add sdk coverage * style(test): code format * fix(CI): update coverage.info path * improvement(CI): use internal image * improvement(CI): push coverage info once * [Feature] Add C++ API for SDK (#831) * add C++ API * unify result type & add examples * minor fix * install cxx API headers * fix Mat, add more examples * fix monolithic build & fix lint * install examples correctly * fix lint * feat(tools/deploy.py): support snpe (#789) * fix(tools/deploy.py): support snpe * improvement(backend/snpe): review advices * docs(backend/snpe): update build * docs(backend/snpe): server support specify port * docs(backend/snpe): update path * fix(backend/snpe): time counter missing argument * docs(backend/snpe): add missing argument * docs(backend/snpe): update download and using * improvement(snpe_net.cpp): load model with modeldata * Support setup on environment with no PyTorch (#843) * support test with multi batch (#829) * support test with multi batch * resolve comment * import algorithm from buffer (#793) * [Enhancement] build sdk python api in standard-alone manner (#810) * build sdk python api in standard-alone manner * enable MMDEPLOY_BUILD_SDK_MONOLITHIC and MMDEPLOY_BUILD_EXAMPLES in prebuild config * link mmdeploy to python target when monolithic option is on * checkin README to describe precompiled package build procedure * use packaging.version.parse(python_version) instead of list(python_version) * fix according to review results * rebase master * rollback cmake.in and apis/python/CMakeLists.txt * reorganize files in install/example * let cmake detect visual studio instead of specifying 2019 * rename whl name of precompiled package * fix according to review results * Fix SDK backend (#844) * fix mmpose python api (#852) * add prebuild package usage docs on windows (#816) * add prebuild package usage docs on windows * fix lint * update * try fix lint * add en docs * update * update * udpate faq * fix typo (#862) * [Enhancement] Improve get_started documents and bump version to 0.7.0 (#813) * simplify commands in get_started * add installation commands for Windows * fix typo * limit markdown and sphinx_markdown_tables version * adopt html <details open> tag * bump mmdeploy version * bump mmdeploy version * update get_started * update get_started * use python3.8 instead of python3.7 * remove duplicate section * resolve issue #856 * update according to review results * add reference to prebuilt_package_windows.md * fix error when build sdk demos * improvement(dockerfile): use make -j$(nporc) when build ncnn (#840) * use make -j$(nporc) when build ncnn * improve cpu dockerfile * fix error when set device cpu && fix docs error (#866) * [Feature]support pointpillar nus version (#391) * support pointpillar nus version * support pointpillar nus version * add regression test config for mmdet3d * fix exit with no error code * fix cfg * fix worksize * fix worksize * fix cfg * support nus pp * fix yaml * fix yaml * fix yaml * add ut * fix ut Co-authored-by: RunningLeon <mnsheng@yeah.net> * Fix doc error of building C examples (#879) * fix doc error of building C demo examples Path error in cmake compilation of C demo examples * fix en doc error of building C demo examples Path error in cmake compilation of C demo examples * fix adaptive_avg_pool exporting to onnx (#857) * fix adaptive_avg_pool exporting to onnx * remove debug codes * fix ci * resolve comment * docs(project): sync en and zh docs (#842) * docs(en): update file structure * docs(zh_cn): update * docs(structure): update * docs(snpe): update * docs(README): update * fix(CI): update * fix(CI): index.rst error * fix(docs): update * fix(docs): remove mermaid * fix(docs): remove useless * fix(docs): update link * docs(en): update * docs(en): update * docs(zh_cn): remove \[ * docs(zh_cn): format * docs(en): remove blank * fix(CI): doc link error * docs(project): remove "./" prefix * docs(zh_cn): fix mdformat * docs(en): update title * fix(CI): update docs * fix mmdeploy_pplnn_net build error when target device is cpu (#896) * docs(zh_cn): add architect (#882) * docs(zh_cn): add architect docs(en): add architect fix(docs): readthedocs index * docs(en): update architect.md * docs(README.md): update * docs(architecture): fix review advices * add device backend check (#886) * add device backend check * safe check * only activated for tensorrt and openvino * resolve comments * support multi-batch test in profile tool (#868) * test batch profile with resnet pspnet yolov3 srcnn * update doc * update docs * fix ut * fix mmdet * support batch mmorc and mmrotate * fix mmcls export to sdk * resolve comments * rename to fix #819 * fix conflicts with master * [Fix] fix device error in dump-info (#912) * fix device error in dump-info * fix UT * improvement(cmake): simplify build option and doc (#832) * improvement(cmake): simplify build option improvement(cmake): convert target_backends with directory * fix(dockerfile): build error * fix(CI): circle CI * fix(docs): snpe and cmake option * fix(docs): revert update cmake * fix(docs): revert * update(docs): remove useless * set test_mode for mmdet (#920) * fix * update * [Doc] How to write a customized TensorRT plugin (#290) * first edition * fix lint * add 06, 07 * resolve comments * update index.rst * update title * update img * [Feature] add swin for cls (#911) * add swin for cls * add ut and doc * reduce trt batch size * add regression test * resolve comments * remove useless rewriting logic * docs(mmdet3d): give detail model path (#940) * add cflags explicitly in ci (#945) * improvement(installation): add script install mmdeploy (#919) * feat(tools): add build ubuntu x64 ncnn * ci(tools): add ncnn auto install * fix(ci): auto install ncnn * fix(tools): no interactive * docs(build): add script build * CI(ncnn): script install ncnn * docs(zh_cn): fix error os * fix * CI(tools/script): test ort install passed * update * CI(tools): support pplnn * CI(build): add pplnn * docs(tools): update * fix * CI(tools): script install torchscript * docs(build): add torchscript * fix(tools): clean code and doc * update * fix(CI): requirements install failed * debug CI * update * update * update * feat(tools/script): support user specify make jobs * fix(tools/script): fix build pplnn with cuda * fix(tools/script): torchscript add tips and simplify install mmcv * fix(tools/script): check nvcc version first * fix(tools/scripts): pplnn checkout * fix(CI): add simple check install succcess * fix * debug CI * fix * fix(CI): pplnn install mis wheel * fix(CI): build error * fix(CI): remove misleading message * Support risc-v platform (#910) * add ppl.nn riscv engine * update ppl.nn riscv engine * udpate riscv service (ncnn backend) * update _build_wrapper for ncnn * fix build * fix lint * update default uri * update file structure & add cn doc * remove copy input data * update docs * remove ncnn server * fix docs * update zh doc * update toolchain * remove unused * update doc * update doc * update doc * rename cross build dirname * add riscv.md to build_from_source.md * update cls model * test ci * test ci * test ci * test ci * test ci * update ci * update ci * [Feature] TorchScript SDK backend (#890) * WIP SDK torchscript support * support detection task * make torchvision optional * force link torchvision if enabled * support torch-1.12 * fix export & sync cuda stream * hide internal classes * handle error * set `MMDEPLOY_USE_CUDA` when CUDA is enabled * [Bug] fix setitem with scalar or single element tensor (#941) * fix setitem * add copy symbolic * docs(convert_model): update description (#956) * [Enhancement] Support DETR (#924) * add detr support * fix softmax * add reg test, update document * fix ut failed (#951) * [Enhancement] Rewriter support pre-import function (#899) * support preimport * update rewriter * fix batched nms ort * add_multi_label_postprocess (#950) * 'add_multi_label_postprocess' * fix pre-commit * delete partial_sort * delete idx * delete num_classes and num_classes_ * Fix right brackets and spelling errors in lines 19 and 20 Co-authored-by: gaoying <gaoying@xiaobaishiji.com> * fix ci (#964) * [Fix] Close onnx optimizer for ncnn (#961) * close onnx optimizer for ncnn * fix docformatter * fix lint * remove Release dir in mmdeploy package (#960) * CI(tools/scripts): add submodule init and update (#977) * fix mmroate (#976) * Fix mmseg pointrend (#903) * support mmseg:pointrend * update docs * update docs for torchscript * resolve comments * Add CI to test full pipeline (#966) * add mmcls full pipeline test ci * update * update * add mmcv * install torch * install mmdeploy * change clone with https * install mmcls * update * change mmcls version * add mmcv version * update mmcls version * test sdk * tast with imagnet * sed pipeline * print env * update * move to backend-ort ci * install mim * fix regression test (#958) * fix reg * set sdk wrapper device id * resolve comment * fix(CI): typo (#983) * fix(CI): ort test all pipeline (#985) * add missing sqrt for PAAHead's score calculation (#984) Co-authored-by: xianghongyi1 <xianghongyi1@sensetime.com> * Fix: skip tests for uninstalled codebases (#987) * skip tests if codebase not installed * skip ort run test * fix mmseg * [Feature] Ascend backend (#747) * add acl backend * support dynamic batch size and dynamic image size * add preliminary ascend backend * support dtypes other than float * support dynamic_dims in SDK * fix dynamic batch size * better error handling * remove debug info * [WIP] dynamic shape support * fix static shape * fix dynamic batch size * add retinanet support * fix dynamic image size * fix dynamic image size * fix dynamic dims * fix dynamic dims * simplify config files * fix yolox support * fix negative index * support faster rcnn * add seg config * update benchmark * fix onnx2ascend dynamic shape * update docstring and benchmark * add unit test, update documents * fix wrapper * fix ut * fix for vit * error handling * context handling & multi-device support * build with stub libraries * add ci * fix lint * fix lint * update doc ref * fix typo * down with `target_link_directories` * setup python * makedir * fix ci * fix ci * remove verbose logs * fix UBs * export Error * fix lint * update checkenv Co-authored-by: grimoire <yaoqian@sensetime.com> * fix(backend): disable cublaslt for cu102 (#947) * fix(backend): disable cublaslt for cu102 * fix * fix(backend): update * fix(tensorrt/util.py): add find cuda version * fix * fix(CI): first use cmd to get cuda version * docs(tensorrt/utils.py): update docstring * TensorRT dot product attention ops (#949) * add detr support * fix softmax * add placeholder * add implement * add docs and ut * update testcase * update docs * update docs * fix mmdet showresult (#999) * fix mmdet showresult * Consider compatibility * mmdet showresult add *args * Revert "mmdet showresult add *args" This reverts commit 82265a3. Co-authored-by: whhuang <whhuang@hitotek.com> * support coreml (#760) * sdk inference * fix typo * fix typo * add convert things * fix missling name * add cls support * add more pytorch rewriter * add det support * support det wip * make Model export model_path * fix nms * add output back * add docstring * fix lint * add coreml build action * add zh docs * add coreml backend check * update ci * update * update * update * update * update * fix lint * update configs * add return value when error occured * update docs * update docs * update docs * fix lint * udpate docs * udpate docs * update Co-authored-by: grimoire <streetyao@live.com> * fix mmdet ut (#1001) * [Feature] Add option to fuse transform. (#741) * add collect_impl.cpp to cuda device * add dummy compute node wich device elena * add compiler & dynamic library loader * add code to compile with gen code(elena) * move folder * fix lint * add tracer module * add license * update type id * add fuse kernel registry * remove compilier & dynamic_library * update fuse kernel interface * Add elena-mmdeploy project in 3rd-party * Fix README.md * fix cmake file * Support cuda device and clang format all file * Add cudaStreamSynchronize for cudafree * fix cudaStreamSynchronize * rename to __tracer__ * remove unused code * update kernel * update extract elena script * update gitignore * fix ci * Change the crop_size to crop_h and crop_w in arglist * update Tracer * remove cond * avoid allocate memory * add build.sh for elena * remove code * update test * Support bilinear resize with float input * Rename elena-mmdeploy to delete * Introduce public submodule * use get_ref * update elena * update tools * update tools * update fuse transform docs * add fuse transform doc link to get_started * fix shape in crop * remove fuse_transform_ == true check * remove fuse_transform_ member * remove elena_int.h * doesn't dump transform_static.json * update tracer * update CVFusion to remove compile warning * remove mmcv version > 1.5.1 dep * fix tests * update docs * add elena use option * remove submodule of CVFusion * update doc * use auto * use throw_exception(eEntryNotFound); * update Co-authored-by: cx <cx@ubuntu20.04> Co-authored-by: miraclezqc <969226879@qq.com> * Add RKNN support. (#865) * save codes * support resnet and yolov3 * support yolox * fix lint * add mmseg support and a doc * add UT * update supported model list * fix ci * refine docstring * resolve comments * remote output_tensor_type * resolve comments * update readme * [Fix] Add isolated option for TorchScript SDK backend (#1002) * add option for TorchScript SDK backend * add doc * format * bump version to v0.8.0 (#1009) * fix(CI): update link checker (#1008) * New issue template (#1007) * update bug report * update issue template * update bug-report * fix mmdeploy builder on windows (#1018) * fix mmdeploy builder on windows * add pyyaml * fix lint * BUG P0 (#1044) * update api in doc (#1021) * fix two stage batch dynamic (#1046) * docs(scripts): update auto install desc (#1036) * Fix `RoIAlignFunction` error for CoreML backend (#1029) * Fixed typo for install commands for TensorRT runtime (#1025) * Fixed typo for install commands for TensorRT runtime * Apply typo-fix on 'cn' documentation Co-authored-by: Tümer Tosik <tumer_t@hotmail.de> * merge master@a1a19f0 documents to dev-1.x * missed ubuntu_utils.py * change benchmark reference in readme_zh-CN Co-authored-by: Ryan_Huang <44900829+DrRyanHuang@users.noreply.github.com> Co-authored-by: Chen Xin <xinchen.tju@gmail.com> Co-authored-by: q.yao <yaoqian@sensetime.com> Co-authored-by: zytx121 <592267829@qq.com> Co-authored-by: RunningLeon <mnsheng@yeah.net> Co-authored-by: Li Zhang <lzhang329@gmail.com> Co-authored-by: tripleMu <gpu@163.com> Co-authored-by: tripleMu <865626@163.com> Co-authored-by: hanrui1sensetime <83800577+hanrui1sensetime@users.noreply.github.com> Co-authored-by: Bryan Glen Suello <11388006+bgsuello@users.noreply.github.com> Co-authored-by: zambranohally <63218980+zambranohally@users.noreply.github.com> Co-authored-by: AllentDan <41138331+AllentDan@users.noreply.github.com> Co-authored-by: tpoisonooo <khj.application@aliyun.com> Co-authored-by: Hakjin Lee <nijkah@gmail.com> Co-authored-by: 孙德伟 <5899962+dwSun@users.noreply.github.com> Co-authored-by: dwSun <dwsunny@icloud.com> Co-authored-by: Chen Xin <irexyc@gmail.com> Co-authored-by: OldDreamInWind <108687632+OldDreamInWind@users.noreply.github.com> Co-authored-by: VVsssssk <88368822+VVsssssk@users.noreply.github.com> Co-authored-by: 梦阳 <49838178+liu-mengyang@users.noreply.github.com> Co-authored-by: gy77 <64619863+gy-7@users.noreply.github.com> Co-authored-by: gaoying <gaoying@xiaobaishiji.com> Co-authored-by: Hongyi Xiang <Groexhy@users.noreply.github.com> Co-authored-by: xianghongyi1 <xianghongyi1@sensetime.com> Co-authored-by: munhou <51435578+munhou@users.noreply.github.com> Co-authored-by: whhuang <whhuang@hitotek.com> Co-authored-by: grimoire <streetyao@live.com> Co-authored-by: cx <cx@ubuntu20.04> Co-authored-by: miraclezqc <969226879@qq.com> Co-authored-by: Jelle Maas <typiqally@gmail.com> Co-authored-by: ichitaka <tuemerffm@hotmail.com> Co-authored-by: Tümer Tosik <tumer_t@hotmail.de>

* make -install -> make install (open-mmlab#621) change `make -install` to `make install` open-mmlab#618 * [Fix] fix csharp api detector release result (open-mmlab#620) * fix csharp api detector release result * fix wrong count arg of xxx_release_result in c# api * [Enhancement] Support two-stage rotated detector TensorRT. (open-mmlab#530) * upload * add fake_multiclass_nms_rotated * delete unused code * align with pytorch * Update delta_midpointoffset_rbbox_coder.py * add trt rotated roi align * add index feature in nms * not good * fix index * add ut * add benchmark * move to csrc/mmdeploy * update unit test Co-authored-by: zytx121 <592267829@qq.com> * Reduce mmcls version dependency (open-mmlab#635) * fix shufflenetv2 with trt (open-mmlab#645) * fix shufflenetv2 and pspnet * fix ci * remove print * ' -> " (open-mmlab#654) If there is a variable in the string, single quotes will ignored it, while double quotes will bring the variable into the string after parsing * ' -> " (open-mmlab#655) same with open-mmlab#654 * Support deployment of Segmenter (open-mmlab#587) * support segmentor with ncnn * update regression yml * replace chunk with split to support ts * update regression yml * update docs * fix segmenter ncnn inference failure brought by open-mmlab#477 * add test * fix test for ncnn and trt * fix lint * export nn.linear to Gemm op in onnx for ncnn * fix ci * simplify `Expand` (open-mmlab#617) * Fix typo (open-mmlab#625) * Add make install in en docs * Add make install in zh docs * Fix typo * Merge and add windows build Co-authored-by: tripleMu <865626@163.com> * [Enhancement] Fix ncnn unittest (open-mmlab#626) * optmize-csp-darknet * replace floordiv to torch.div * update csp_darknet default implement * fix test * [Enhancement] TensorRT Anchor generator plugin (open-mmlab#646) * custom trt anchor generator * add ut * add docstring, update doc * Add partition doc and sample code (open-mmlab#599) * update torch2onnx tool to support onnx partition * add model partition of yolov3 * add cn doc * update torch2onnx tool to support onnx partition * add model partition of yolov3 * add cn doc * add to index.rst * resolve comment * resolve comments * fix lint * change caption level in docs * update docs (open-mmlab#624) * Add java apis and demos (open-mmlab#563) * add java classifier detector * add segmentor * fix lint * add ImageRestorer java apis and demo * remove useless count parameter for Segmentor and Restorer, add PoseDetector * add RotatedDetection java api and demo * add Ocr java demo and apis * remove mmrotate ncnn java api and demo * fix lint * sync java api folder after rebase to master * fix include * remove record * fix java apis dir path in cmake * add java demo readme * fix lint mdformat * add test javaapi ci * fix lint * fix flake8 * fix test javaapi ci * refactor readme.md * fix install opencv for ci * fix install opencv : add permission * add all codebases and mmcv install * add torch * install mmdeploy * fix image path * fix picture path * fix import ncnn * fix import ncnn * add submodule of pybind * fix pybind submodule * change download to git clone for submodule * fix ncnn dir * fix README error * simplify the github ci * fix ci * fix yapf * add JNI as required * fix Capitalize * fix Capitalize * fix copyright * ignore .class changed * add OpenJDK installation docs * install target of javaapi * simplify ci * add jar * fix ci * fix ci * fix test java command * debugging what failed * debugging what failed * debugging what failed * add java version info * install openjdk * add java env var * fix export * fix export * fix export * fix export * fix picture path * fix picture path * fix file name * fix file name * fix README * remove java_api strategy * fix python version * format task name * move args position * extract common utils code * show image class result * add detector result * segmentation result format * add ImageRestorer result * add PoseDetection java result format * fix ci * stage ocr * add visualize * move utils * fix lint * fix ocr bugs * fix ci demo * fix java classpath for ci * fix popd * fix ocr demo text garbled * fix ci * fix ci * fix ci * fix path of utils ci * update the circleci config file by adding workflows both for linux, windows and linux-gpu (open-mmlab#368) * update circleci by adding more workflows * fix test workflow failure on windows platform * fix docker exec command for SDK unittests * Fixed tensorrt plugin not found in Windows (open-mmlab#672) * update introduction.png (open-mmlab#674) * [Enhancement] Add fuse select assign pass (open-mmlab#589) * Add fuse select assign pass * move code to csrc * add config flag * remove bool cast * fix export sdk info of input shape (open-mmlab#667) * Update get_started.md (open-mmlab#675) Fix backend model assignment * Update get_started.md (open-mmlab#676) Fix backend model assignment * [Fix] fix clang build (open-mmlab#677) * fix clang build * fix ndk build * fix ndk build * switch to `std::filesystem` for clang-7 and later * Deploy the Swin Transformer on TensorRT. (open-mmlab#652) * resolve conflicts * update ut and docs * fix ut * refine docstring * add comments and refine UT * resolve comments * resolve comments * update doc * add roll export * check backend * update regression test * bump version to 0.6.0 (open-mmlab#680) * bump vertion to 0.6.0 * update version * pass img_metas while exporting to onnx (open-mmlab#681) * pass img_metas while exporting to onnx * remove try-catch in tools for beter debugging * use get * fix typo * [Fix] fix ssd ncnn ut (open-mmlab#692) * fix ssd ncnn ut * fix yapf * fix passing img_metas to pytorch2onnx for mmedit (open-mmlab#700) * fix passing img_metas for mmdet3d (open-mmlab#707) * [Fix] Fix android build (open-mmlab#698) * fix android build * fix cmake * fix url link * fix wrong exit code in pipeline_manager (open-mmlab#715) * fix exit * change to general exit errorcode=1 * fix passing wrong backend type (open-mmlab#719) * Rename onnx2ncnn to mmdeploy_onnx2ncnn (open-mmlab#694) * improvement(tools/onnx2ncnn.py): rename to mmdeploy_onnx2ncnn * format(tools/deploy.py): clean code * fix(init_plugins.py): improve if condition * fix(CI): update target * fix(test_onnx2ncnn.py): update desc * Update init_plugins.py * [Fix] Fix mmdet ort static shape bug (open-mmlab#687) * fix shape * add device * fix yapf * fix rewriter for transforms * reverse image shape * fix ut of distance2bbox * fix rewriter name * fix c4 for torchscript (open-mmlab#724) * [Enhancement] Standardize C API (open-mmlab#634) * unify C API naming * fix demo and move apis/c/* -> apis/c/mmdeploy/* * fix lint * fix C# project * fix Java API * [Enhancement] Support Slide Vertex TRT (open-mmlab#650) * reorgnize mmrotate * fix * add hbb2obb * add ut * fix rotated nms * update docs * update benchmark * update test * remove ort regression test, remove comment * Fix get-started rendering issues in readthedocs (open-mmlab#740) * fix mermaid markdown rendering issue in readthedocs * fix error in C++ example * fix error in c++ example in zh_cn get_started doc * [Fix] set default topk for dump info (open-mmlab#702) * set default topk for dump info * remove redundant docstrings * add ci densenet * fix classification warnings * fix mmcls version * fix logger.warnings * add version control (open-mmlab#754) * fix satrn for ORT (open-mmlab#753) * fix satrn for ORT * move rewrite into pytorch * Add inference latency test tool (open-mmlab#665) * add profile tool * remove print envs in profile tool * set cudnn_benchmark to True * add doc * update tests * fix typo * support test with images from a directory * update doc * resolve comments * [Enhancement] Add CSE ONNX pass (open-mmlab#647) * Add fuse select assign pass * move code to csrc * add config flag * Add fuse select assign pass * Add CSE for ONNX * remove useless code * Test robot Just test robot * Update README.md Revert * [Fix] fix yolox point_generator (open-mmlab#758) * fix yolox point_generator * add a UT * resolve comments * fix comment lines * limit markdown version (open-mmlab#773) * [Enhancement] Better index put ONNX export. (open-mmlab#704) * Add rewriter for tensor setitem * add version check * Upgrade Dockerfile to use TensorRT==8.2.4.2 (open-mmlab#706) * Upgrade TensorRT to 8.2.4.2 * upgrade pytorch&mmcv in CPU Dockerfile * Delete redundant port example in Docker * change 160x160-608x608 to 64x64-608x608 for yolov3 * [Fix] reduce log verbosity & improve error reporting (open-mmlab#755) * reduce log verbosity & improve error reporting * improve error reporting * [Enhancement] Support latest ppl.nn & ppl.cv (open-mmlab#564) * support latest ppl.nn * fix pplnn for model convertor * fix lint * update memory policy * import algo from buffer * update ppl.cv * use `ppl.cv==0.7.0` * document supported ppl.nn version * skip pplnn dependency when building shared libs * [Fix][P0] Fix for torch1.12 (open-mmlab#751) * fix for torch1.12 * add comment * fix check env (open-mmlab#785) * [Fix] fix cascade mask rcnn (open-mmlab#787) * fix cascade mask rcnn * fix lint * add regression * [Feature] Support RoITransRoIHead (open-mmlab#713) * [Feature] Support RoITransRoIHead * Add docs * Add mmrotate models regression test * Add a draft for test code * change the argument name * fix test code * fix minor change for not class agnostic case * fix sample for test code * fix sample for test code * Add mmrotate in requirements * Revert "Add mmrotate in requirements" This reverts commit 0434900. * [Fix] fix triu (open-mmlab#792) * fix triu * triu -> triu_default * [Enhancement] Install Optimizer by setuptools (open-mmlab#690) * Add fuse select assign pass * move code to csrc * add config flag * Add fuse select assign pass * Add CSE for ONNX * remove useless code * Install optimizer by setup tools * fix comment * [Feature] support MMRotate model with le135 (open-mmlab#788) * support MMRotate model with le135 * cse before fuse select assign * remove unused import * [Fix] Support macOS build (open-mmlab#762) * fix macOS build * fix missing * add option to build & install examples (open-mmlab#822) * [Fix] Fix setup on non-linux-x64 (open-mmlab#811) * fix setup * replace long to int64_t * [Feature] support build single sdk library (open-mmlab#806) * build single lib for c api * update csharp doc & project * update test build * fix test build * fix * update document for building android sdk (open-mmlab#817) Co-authored-by: dwSun <dwsunny@icloud.com> * [Enhancement] support kwargs in SDK python bindings (open-mmlab#794) * support-kwargs * make '__call__' as single image inference and add 'batch' API to deal with batch images inference * fix linting error and typo * fix lint * improvement(sdk): add sdk code coverage (open-mmlab#808) * feat(doc): add CI * CI(sdk): add sdk coverage * style(test): code format * fix(CI): update coverage.info path * improvement(CI): use internal image * improvement(CI): push coverage info once * [Feature] Add C++ API for SDK (open-mmlab#831) * add C++ API * unify result type & add examples * minor fix * install cxx API headers * fix Mat, add more examples * fix monolithic build & fix lint * install examples correctly * fix lint * feat(tools/deploy.py): support snpe (open-mmlab#789) * fix(tools/deploy.py): support snpe * improvement(backend/snpe): review advices * docs(backend/snpe): update build * docs(backend/snpe): server support specify port * docs(backend/snpe): update path * fix(backend/snpe): time counter missing argument * docs(backend/snpe): add missing argument * docs(backend/snpe): update download and using * improvement(snpe_net.cpp): load model with modeldata * Support setup on environment with no PyTorch (open-mmlab#843) * support test with multi batch (open-mmlab#829) * support test with multi batch * resolve comment * import algorithm from buffer (open-mmlab#793) * [Enhancement] build sdk python api in standard-alone manner (open-mmlab#810) * build sdk python api in standard-alone manner * enable MMDEPLOY_BUILD_SDK_MONOLITHIC and MMDEPLOY_BUILD_EXAMPLES in prebuild config * link mmdeploy to python target when monolithic option is on * checkin README to describe precompiled package build procedure * use packaging.version.parse(python_version) instead of list(python_version) * fix according to review results * rebase master * rollback cmake.in and apis/python/CMakeLists.txt * reorganize files in install/example * let cmake detect visual studio instead of specifying 2019 * rename whl name of precompiled package * fix according to review results * Fix SDK backend (open-mmlab#844) * fix mmpose python api (open-mmlab#852) * add prebuild package usage docs on windows (open-mmlab#816) * add prebuild package usage docs on windows * fix lint * update * try fix lint * add en docs * update * update * udpate faq * fix typo (open-mmlab#862) * [Enhancement] Improve get_started documents and bump version to 0.7.0 (open-mmlab#813) * simplify commands in get_started * add installation commands for Windows * fix typo * limit markdown and sphinx_markdown_tables version * adopt html <details open> tag * bump mmdeploy version * bump mmdeploy version * update get_started * update get_started * use python3.8 instead of python3.7 * remove duplicate section * resolve issue open-mmlab#856 * update according to review results * add reference to prebuilt_package_windows.md * fix error when build sdk demos * fix mmcls Co-authored-by: Ryan_Huang <44900829+DrRyanHuang@users.noreply.github.com> Co-authored-by: Chen Xin <xinchen.tju@gmail.com> Co-authored-by: q.yao <yaoqian@sensetime.com> Co-authored-by: zytx121 <592267829@qq.com> Co-authored-by: Li Zhang <lzhang329@gmail.com> Co-authored-by: tripleMu <gpu@163.com> Co-authored-by: tripleMu <865626@163.com> Co-authored-by: hanrui1sensetime <83800577+hanrui1sensetime@users.noreply.github.com> Co-authored-by: lvhan028 <lvhan_028@163.com> Co-authored-by: Bryan Glen Suello <11388006+bgsuello@users.noreply.github.com> Co-authored-by: zambranohally <63218980+zambranohally@users.noreply.github.com> Co-authored-by: AllentDan <41138331+AllentDan@users.noreply.github.com> Co-authored-by: tpoisonooo <khj.application@aliyun.com> Co-authored-by: Hakjin Lee <nijkah@gmail.com> Co-authored-by: 孙德伟 <5899962+dwSun@users.noreply.github.com> Co-authored-by: dwSun <dwsunny@icloud.com> Co-authored-by: Chen Xin <irexyc@gmail.com>

* make -install -> make install (open-mmlab#621) change `make -install` to `make install` open-mmlab#618 * [Fix] fix csharp api detector release result (open-mmlab#620) * fix csharp api detector release result * fix wrong count arg of xxx_release_result in c# api * [Enhancement] Support two-stage rotated detector TensorRT. (open-mmlab#530) * upload * add fake_multiclass_nms_rotated * delete unused code * align with pytorch * Update delta_midpointoffset_rbbox_coder.py * add trt rotated roi align * add index feature in nms * not good * fix index * add ut * add benchmark * move to csrc/mmdeploy * update unit test Co-authored-by: zytx121 <592267829@qq.com> * Reduce mmcls version dependency (open-mmlab#635) * fix shufflenetv2 with trt (open-mmlab#645) * fix shufflenetv2 and pspnet * fix ci * remove print * ' -> " (open-mmlab#654) If there is a variable in the string, single quotes will ignored it, while double quotes will bring the variable into the string after parsing * ' -> " (open-mmlab#655) same with open-mmlab#654 * Support deployment of Segmenter (open-mmlab#587) * support segmentor with ncnn * update regression yml * replace chunk with split to support ts * update regression yml * update docs * fix segmenter ncnn inference failure brought by open-mmlab#477 * add test * fix test for ncnn and trt * fix lint * export nn.linear to Gemm op in onnx for ncnn * fix ci * simplify `Expand` (open-mmlab#617) * Fix typo (open-mmlab#625) * Add make install in en docs * Add make install in zh docs * Fix typo * Merge and add windows build Co-authored-by: tripleMu <865626@163.com> * [Enhancement] Fix ncnn unittest (open-mmlab#626) * optmize-csp-darknet * replace floordiv to torch.div * update csp_darknet default implement * fix test * [Enhancement] TensorRT Anchor generator plugin (open-mmlab#646) * custom trt anchor generator * add ut * add docstring, update doc * Add partition doc and sample code (open-mmlab#599) * update torch2onnx tool to support onnx partition * add model partition of yolov3 * add cn doc * update torch2onnx tool to support onnx partition * add model partition of yolov3 * add cn doc * add to index.rst * resolve comment * resolve comments * fix lint * change caption level in docs * update docs (open-mmlab#624) * Add java apis and demos (open-mmlab#563) * add java classifier detector * add segmentor * fix lint * add ImageRestorer java apis and demo * remove useless count parameter for Segmentor and Restorer, add PoseDetector * add RotatedDetection java api and demo * add Ocr java demo and apis * remove mmrotate ncnn java api and demo * fix lint * sync java api folder after rebase to master * fix include * remove record * fix java apis dir path in cmake * add java demo readme * fix lint mdformat * add test javaapi ci * fix lint * fix flake8 * fix test javaapi ci * refactor readme.md * fix install opencv for ci * fix install opencv : add permission * add all codebases and mmcv install * add torch * install mmdeploy * fix image path * fix picture path * fix import ncnn * fix import ncnn * add submodule of pybind * fix pybind submodule * change download to git clone for submodule * fix ncnn dir * fix README error * simplify the github ci * fix ci * fix yapf * add JNI as required * fix Capitalize * fix Capitalize * fix copyright * ignore .class changed * add OpenJDK installation docs * install target of javaapi * simplify ci * add jar * fix ci * fix ci * fix test java command * debugging what failed * debugging what failed * debugging what failed * add java version info * install openjdk * add java env var * fix export * fix export * fix export * fix export * fix picture path * fix picture path * fix file name * fix file name * fix README * remove java_api strategy * fix python version * format task name * move args position * extract common utils code * show image class result * add detector result * segmentation result format * add ImageRestorer result * add PoseDetection java result format * fix ci * stage ocr * add visualize * move utils * fix lint * fix ocr bugs * fix ci demo * fix java classpath for ci * fix popd * fix ocr demo text garbled * fix ci * fix ci * fix ci * fix path of utils ci * update the circleci config file by adding workflows both for linux, windows and linux-gpu (open-mmlab#368) * update circleci by adding more workflows * fix test workflow failure on windows platform * fix docker exec command for SDK unittests * Fixed tensorrt plugin not found in Windows (open-mmlab#672) * update introduction.png (open-mmlab#674) * [Enhancement] Add fuse select assign pass (open-mmlab#589) * Add fuse select assign pass * move code to csrc * add config flag * remove bool cast * fix export sdk info of input shape (open-mmlab#667) * Update get_started.md (open-mmlab#675) Fix backend model assignment * Update get_started.md (open-mmlab#676) Fix backend model assignment * [Fix] fix clang build (open-mmlab#677) * fix clang build * fix ndk build * fix ndk build * switch to `std::filesystem` for clang-7 and later * Deploy the Swin Transformer on TensorRT. (open-mmlab#652) * resolve conflicts * update ut and docs * fix ut * refine docstring * add comments and refine UT * resolve comments * resolve comments * update doc * add roll export * check backend * update regression test * bump version to 0.6.0 (open-mmlab#680) * bump vertion to 0.6.0 * update version * pass img_metas while exporting to onnx (open-mmlab#681) * pass img_metas while exporting to onnx * remove try-catch in tools for beter debugging * use get * fix typo * [Fix] fix ssd ncnn ut (open-mmlab#692) * fix ssd ncnn ut * fix yapf * fix passing img_metas to pytorch2onnx for mmedit (open-mmlab#700) * fix passing img_metas for mmdet3d (open-mmlab#707) * [Fix] Fix android build (open-mmlab#698) * fix android build * fix cmake * fix url link * fix wrong exit code in pipeline_manager (open-mmlab#715) * fix exit * change to general exit errorcode=1 * fix passing wrong backend type (open-mmlab#719) * Rename onnx2ncnn to mmdeploy_onnx2ncnn (open-mmlab#694) * improvement(tools/onnx2ncnn.py): rename to mmdeploy_onnx2ncnn * format(tools/deploy.py): clean code * fix(init_plugins.py): improve if condition * fix(CI): update target * fix(test_onnx2ncnn.py): update desc * Update init_plugins.py * [Fix] Fix mmdet ort static shape bug (open-mmlab#687) * fix shape * add device * fix yapf * fix rewriter for transforms * reverse image shape * fix ut of distance2bbox * fix rewriter name * fix c4 for torchscript (open-mmlab#724) * [Enhancement] Standardize C API (open-mmlab#634) * unify C API naming * fix demo and move apis/c/* -> apis/c/mmdeploy/* * fix lint * fix C# project * fix Java API * [Enhancement] Support Slide Vertex TRT (open-mmlab#650) * reorgnize mmrotate * fix * add hbb2obb * add ut * fix rotated nms * update docs * update benchmark * update test * remove ort regression test, remove comment * Fix get-started rendering issues in readthedocs (open-mmlab#740) * fix mermaid markdown rendering issue in readthedocs * fix error in C++ example * fix error in c++ example in zh_cn get_started doc * [Fix] set default topk for dump info (open-mmlab#702) * set default topk for dump info * remove redundant docstrings * add ci densenet * fix classification warnings * fix mmcls version * fix logger.warnings * add version control (open-mmlab#754) * fix satrn for ORT (open-mmlab#753) * fix satrn for ORT * move rewrite into pytorch * Add inference latency test tool (open-mmlab#665) * add profile tool * remove print envs in profile tool * set cudnn_benchmark to True * add doc * update tests * fix typo * support test with images from a directory * update doc * resolve comments * [Enhancement] Add CSE ONNX pass (open-mmlab#647) * Add fuse select assign pass * move code to csrc * add config flag * Add fuse select assign pass * Add CSE for ONNX * remove useless code * Test robot Just test robot * Update README.md Revert * [Fix] fix yolox point_generator (open-mmlab#758) * fix yolox point_generator * add a UT * resolve comments * fix comment lines * limit markdown version (open-mmlab#773) * [Enhancement] Better index put ONNX export. (open-mmlab#704) * Add rewriter for tensor setitem * add version check * Upgrade Dockerfile to use TensorRT==8.2.4.2 (open-mmlab#706) * Upgrade TensorRT to 8.2.4.2 * upgrade pytorch&mmcv in CPU Dockerfile * Delete redundant port example in Docker * change 160x160-608x608 to 64x64-608x608 for yolov3 * [Fix] reduce log verbosity & improve error reporting (open-mmlab#755) * reduce log verbosity & improve error reporting * improve error reporting * [Enhancement] Support latest ppl.nn & ppl.cv (open-mmlab#564) * support latest ppl.nn * fix pplnn for model convertor * fix lint * update memory policy * import algo from buffer * update ppl.cv * use `ppl.cv==0.7.0` * document supported ppl.nn version * skip pplnn dependency when building shared libs * [Fix][P0] Fix for torch1.12 (open-mmlab#751) * fix for torch1.12 * add comment * fix check env (open-mmlab#785) * [Fix] fix cascade mask rcnn (open-mmlab#787) * fix cascade mask rcnn * fix lint * add regression * [Feature] Support RoITransRoIHead (open-mmlab#713) * [Feature] Support RoITransRoIHead * Add docs * Add mmrotate models regression test * Add a draft for test code * change the argument name * fix test code * fix minor change for not class agnostic case * fix sample for test code * fix sample for test code * Add mmrotate in requirements * Revert "Add mmrotate in requirements" This reverts commit 0434900. * [Fix] fix triu (open-mmlab#792) * fix triu * triu -> triu_default * [Enhancement] Install Optimizer by setuptools (open-mmlab#690) * Add fuse select assign pass * move code to csrc * add config flag * Add fuse select assign pass * Add CSE for ONNX * remove useless code * Install optimizer by setup tools * fix comment * [Feature] support MMRotate model with le135 (open-mmlab#788) * support MMRotate model with le135 * cse before fuse select assign * remove unused import * [Fix] Support macOS build (open-mmlab#762) * fix macOS build * fix missing * add option to build & install examples (open-mmlab#822) * [Fix] Fix setup on non-linux-x64 (open-mmlab#811) * fix setup * replace long to int64_t * [Feature] support build single sdk library (open-mmlab#806) * build single lib for c api * update csharp doc & project * update test build * fix test build * fix * update document for building android sdk (open-mmlab#817) Co-authored-by: dwSun <dwsunny@icloud.com> * [Enhancement] support kwargs in SDK python bindings (open-mmlab#794) * support-kwargs * make '__call__' as single image inference and add 'batch' API to deal with batch images inference * fix linting error and typo * fix lint * improvement(sdk): add sdk code coverage (open-mmlab#808) * feat(doc): add CI * CI(sdk): add sdk coverage * style(test): code format * fix(CI): update coverage.info path * improvement(CI): use internal image * improvement(CI): push coverage info once * [Feature] Add C++ API for SDK (open-mmlab#831) * add C++ API * unify result type & add examples * minor fix * install cxx API headers * fix Mat, add more examples * fix monolithic build & fix lint * install examples correctly * fix lint * feat(tools/deploy.py): support snpe (open-mmlab#789) * fix(tools/deploy.py): support snpe * improvement(backend/snpe): review advices * docs(backend/snpe): update build * docs(backend/snpe): server support specify port * docs(backend/snpe): update path * fix(backend/snpe): time counter missing argument * docs(backend/snpe): add missing argument * docs(backend/snpe): update download and using * improvement(snpe_net.cpp): load model with modeldata * Support setup on environment with no PyTorch (open-mmlab#843) * support test with multi batch (open-mmlab#829) * support test with multi batch * resolve comment * import algorithm from buffer (open-mmlab#793) * [Enhancement] build sdk python api in standard-alone manner (open-mmlab#810) * build sdk python api in standard-alone manner * enable MMDEPLOY_BUILD_SDK_MONOLITHIC and MMDEPLOY_BUILD_EXAMPLES in prebuild config * link mmdeploy to python target when monolithic option is on * checkin README to describe precompiled package build procedure * use packaging.version.parse(python_version) instead of list(python_version) * fix according to review results * rebase master * rollback cmake.in and apis/python/CMakeLists.txt * reorganize files in install/example * let cmake detect visual studio instead of specifying 2019 * rename whl name of precompiled package * fix according to review results * Fix SDK backend (open-mmlab#844) * fix mmpose python api (open-mmlab#852) * add prebuild package usage docs on windows (open-mmlab#816) * add prebuild package usage docs on windows * fix lint * update * try fix lint * add en docs * update * update * udpate faq * fix typo (open-mmlab#862) * [Enhancement] Improve get_started documents and bump version to 0.7.0 (open-mmlab#813) * simplify commands in get_started * add installation commands for Windows * fix typo * limit markdown and sphinx_markdown_tables version * adopt html <details open> tag * bump mmdeploy version * bump mmdeploy version * update get_started * update get_started * use python3.8 instead of python3.7 * remove duplicate section * resolve issue open-mmlab#856 * update according to review results * add reference to prebuilt_package_windows.md * fix error when build sdk demos * improvement(dockerfile): use make -j$(nporc) when build ncnn (open-mmlab#840) * use make -j$(nporc) when build ncnn * improve cpu dockerfile * fix error when set device cpu && fix docs error (open-mmlab#866) * [Feature]support pointpillar nus version (open-mmlab#391) * support pointpillar nus version * support pointpillar nus version * add regression test config for mmdet3d * fix exit with no error code * fix cfg * fix worksize * fix worksize * fix cfg * support nus pp * fix yaml * fix yaml * fix yaml * add ut * fix ut Co-authored-by: RunningLeon <mnsheng@yeah.net> * Fix doc error of building C examples (open-mmlab#879) * fix doc error of building C demo examples Path error in cmake compilation of C demo examples * fix en doc error of building C demo examples Path error in cmake compilation of C demo examples * fix adaptive_avg_pool exporting to onnx (open-mmlab#857) * fix adaptive_avg_pool exporting to onnx * remove debug codes * fix ci * resolve comment * docs(project): sync en and zh docs (open-mmlab#842) * docs(en): update file structure * docs(zh_cn): update * docs(structure): update * docs(snpe): update * docs(README): update * fix(CI): update * fix(CI): index.rst error * fix(docs): update * fix(docs): remove mermaid * fix(docs): remove useless * fix(docs): update link * docs(en): update * docs(en): update * docs(zh_cn): remove \[ * docs(zh_cn): format * docs(en): remove blank * fix(CI): doc link error * docs(project): remove "./" prefix * docs(zh_cn): fix mdformat * docs(en): update title * fix(CI): update docs * fix mmdeploy_pplnn_net build error when target device is cpu (open-mmlab#896) * docs(zh_cn): add architect (open-mmlab#882) * docs(zh_cn): add architect docs(en): add architect fix(docs): readthedocs index * docs(en): update architect.md * docs(README.md): update * docs(architecture): fix review advices * add device backend check (open-mmlab#886) * add device backend check * safe check * only activated for tensorrt and openvino * resolve comments * support multi-batch test in profile tool (open-mmlab#868) * test batch profile with resnet pspnet yolov3 srcnn * update doc * update docs * fix ut * fix mmdet * support batch mmorc and mmrotate * fix mmcls export to sdk * resolve comments * rename to fix open-mmlab#819 * fix conflicts with master * [Fix] fix device error in dump-info (open-mmlab#912) * fix device error in dump-info * fix UT * improvement(cmake): simplify build option and doc (open-mmlab#832) * improvement(cmake): simplify build option improvement(cmake): convert target_backends with directory * fix(dockerfile): build error * fix(CI): circle CI * fix(docs): snpe and cmake option * fix(docs): revert update cmake * fix(docs): revert * update(docs): remove useless * set test_mode for mmdet (open-mmlab#920) * fix * update * [Doc] How to write a customized TensorRT plugin (open-mmlab#290) * first edition * fix lint * add 06, 07 * resolve comments * update index.rst * update title * update img * [Feature] add swin for cls (open-mmlab#911) * add swin for cls * add ut and doc * reduce trt batch size * add regression test * resolve comments * remove useless rewriting logic * docs(mmdet3d): give detail model path (open-mmlab#940) * add cflags explicitly in ci (open-mmlab#945) * improvement(installation): add script install mmdeploy (open-mmlab#919) * feat(tools): add build ubuntu x64 ncnn * ci(tools): add ncnn auto install * fix(ci): auto install ncnn * fix(tools): no interactive * docs(build): add script build * CI(ncnn): script install ncnn * docs(zh_cn): fix error os * fix * CI(tools/script): test ort install passed * update * CI(tools): support pplnn * CI(build): add pplnn * docs(tools): update * fix * CI(tools): script install torchscript * docs(build): add torchscript * fix(tools): clean code and doc * update * fix(CI): requirements install failed * debug CI * update * update * update * feat(tools/script): support user specify make jobs * fix(tools/script): fix build pplnn with cuda * fix(tools/script): torchscript add tips and simplify install mmcv * fix(tools/script): check nvcc version first * fix(tools/scripts): pplnn checkout * fix(CI): add simple check install succcess * fix * debug CI * fix * fix(CI): pplnn install mis wheel * fix(CI): build error * fix(CI): remove misleading message * Support risc-v platform (open-mmlab#910) * add ppl.nn riscv engine * update ppl.nn riscv engine * udpate riscv service (ncnn backend) * update _build_wrapper for ncnn * fix build * fix lint * update default uri * update file structure & add cn doc * remove copy input data * update docs * remove ncnn server * fix docs * update zh doc * update toolchain * remove unused * update doc * update doc * update doc * rename cross build dirname * add riscv.md to build_from_source.md * update cls model * test ci * test ci * test ci * test ci * test ci * update ci * update ci * [Feature] TorchScript SDK backend (open-mmlab#890) * WIP SDK torchscript support * support detection task * make torchvision optional * force link torchvision if enabled * support torch-1.12 * fix export & sync cuda stream * hide internal classes * handle error * set `MMDEPLOY_USE_CUDA` when CUDA is enabled * [Bug] fix setitem with scalar or single element tensor (open-mmlab#941) * fix setitem * add copy symbolic * docs(convert_model): update description (open-mmlab#956) * [Enhancement] Support DETR (open-mmlab#924) * add detr support * fix softmax * add reg test, update document * fix ut failed (open-mmlab#951) * [Enhancement] Rewriter support pre-import function (open-mmlab#899) * support preimport * update rewriter * fix batched nms ort * add_multi_label_postprocess (open-mmlab#950) * 'add_multi_label_postprocess' * fix pre-commit * delete partial_sort * delete idx * delete num_classes and num_classes_ * Fix right brackets and spelling errors in lines 19 and 20 Co-authored-by: gaoying <gaoying@xiaobaishiji.com> * fix ci (open-mmlab#964) * [Fix] Close onnx optimizer for ncnn (open-mmlab#961) * close onnx optimizer for ncnn * fix docformatter * fix lint * remove Release dir in mmdeploy package (open-mmlab#960) * CI(tools/scripts): add submodule init and update (open-mmlab#977) * fix mmroate (open-mmlab#976) * Fix mmseg pointrend (open-mmlab#903) * support mmseg:pointrend * update docs * update docs for torchscript * resolve comments * Add CI to test full pipeline (open-mmlab#966) * add mmcls full pipeline test ci * update * update * add mmcv * install torch * install mmdeploy * change clone with https * install mmcls * update * change mmcls version * add mmcv version * update mmcls version * test sdk * tast with imagnet * sed pipeline * print env * update * move to backend-ort ci * install mim * fix regression test (open-mmlab#958) * fix reg * set sdk wrapper device id * resolve comment * fix(CI): typo (open-mmlab#983) * fix(CI): ort test all pipeline (open-mmlab#985) * add missing sqrt for PAAHead's score calculation (open-mmlab#984) Co-authored-by: xianghongyi1 <xianghongyi1@sensetime.com> * Fix: skip tests for uninstalled codebases (open-mmlab#987) * skip tests if codebase not installed * skip ort run test * fix mmseg * [Feature] Ascend backend (open-mmlab#747) * add acl backend * support dynamic batch size and dynamic image size * add preliminary ascend backend * support dtypes other than float * support dynamic_dims in SDK * fix dynamic batch size * better error handling * remove debug info * [WIP] dynamic shape support * fix static shape * fix dynamic batch size * add retinanet support * fix dynamic image size * fix dynamic image size * fix dynamic dims * fix dynamic dims * simplify config files * fix yolox support * fix negative index * support faster rcnn * add seg config * update benchmark * fix onnx2ascend dynamic shape * update docstring and benchmark * add unit test, update documents * fix wrapper * fix ut * fix for vit * error handling * context handling & multi-device support * build with stub libraries * add ci * fix lint * fix lint * update doc ref * fix typo * down with `target_link_directories` * setup python * makedir * fix ci * fix ci * remove verbose logs * fix UBs * export Error * fix lint * update checkenv Co-authored-by: grimoire <yaoqian@sensetime.com> * fix(backend): disable cublaslt for cu102 (open-mmlab#947) * fix(backend): disable cublaslt for cu102 * fix * fix(backend): update * fix(tensorrt/util.py): add find cuda version * fix * fix(CI): first use cmd to get cuda version * docs(tensorrt/utils.py): update docstring * TensorRT dot product attention ops (open-mmlab#949) * add detr support * fix softmax * add placeholder * add implement * add docs and ut * update testcase * update docs * update docs * fix mmdet showresult (open-mmlab#999) * fix mmdet showresult * Consider compatibility * mmdet showresult add *args * Revert "mmdet showresult add *args" This reverts commit 82265a3. Co-authored-by: whhuang <whhuang@hitotek.com> * support coreml (open-mmlab#760) * sdk inference * fix typo * fix typo * add convert things * fix missling name * add cls support * add more pytorch rewriter * add det support * support det wip * make Model export model_path * fix nms * add output back * add docstring * fix lint * add coreml build action * add zh docs * add coreml backend check * update ci * update * update * update * update * update * fix lint * update configs * add return value when error occured * update docs * update docs * update docs * fix lint * udpate docs * udpate docs * update Co-authored-by: grimoire <streetyao@live.com> * fix mmdet ut (open-mmlab#1001) * [Feature] Add option to fuse transform. (open-mmlab#741) * add collect_impl.cpp to cuda device * add dummy compute node wich device elena * add compiler & dynamic library loader * add code to compile with gen code(elena) * move folder * fix lint * add tracer module * add license * update type id * add fuse kernel registry * remove compilier & dynamic_library * update fuse kernel interface * Add elena-mmdeploy project in 3rd-party * Fix README.md * fix cmake file * Support cuda device and clang format all file * Add cudaStreamSynchronize for cudafree * fix cudaStreamSynchronize * rename to __tracer__ * remove unused code * update kernel * update extract elena script * update gitignore * fix ci * Change the crop_size to crop_h and crop_w in arglist * update Tracer * remove cond * avoid allocate memory * add build.sh for elena * remove code * update test * Support bilinear resize with float input * Rename elena-mmdeploy to delete * Introduce public submodule * use get_ref * update elena * update tools * update tools * update fuse transform docs * add fuse transform doc link to get_started * fix shape in crop * remove fuse_transform_ == true check * remove fuse_transform_ member * remove elena_int.h * doesn't dump transform_static.json * update tracer * update CVFusion to remove compile warning * remove mmcv version > 1.5.1 dep * fix tests * update docs * add elena use option * remove submodule of CVFusion * update doc * use auto * use throw_exception(eEntryNotFound); * update Co-authored-by: cx <cx@ubuntu20.04> Co-authored-by: miraclezqc <969226879@qq.com> * Add RKNN support. (open-mmlab#865) * save codes * support resnet and yolov3 * support yolox * fix lint * add mmseg support and a doc * add UT * update supported model list * fix ci * refine docstring * resolve comments * remote output_tensor_type * resolve comments * update readme * [Fix] Add isolated option for TorchScript SDK backend (open-mmlab#1002) * add option for TorchScript SDK backend * add doc * format * bump version to v0.8.0 (open-mmlab#1009) * fix(CI): update link checker (open-mmlab#1008) * New issue template (open-mmlab#1007) * update bug report * update issue template * update bug-report * fix mmdeploy builder on windows (open-mmlab#1018) * fix mmdeploy builder on windows * add pyyaml * fix lint * BUG P0 (open-mmlab#1044) * update api in doc (open-mmlab#1021) * fix two stage batch dynamic (open-mmlab#1046) * docs(scripts): update auto install desc (open-mmlab#1036) * Fix `RoIAlignFunction` error for CoreML backend (open-mmlab#1029) * Fixed typo for install commands for TensorRT runtime (open-mmlab#1025) * Fixed typo for install commands for TensorRT runtime * Apply typo-fix on 'cn' documentation Co-authored-by: Tümer Tosik <tumer_t@hotmail.de> * merge master@a1a19f0 documents to dev-1.x * missed ubuntu_utils.py * change benchmark reference in readme_zh-CN Co-authored-by: Ryan_Huang <44900829+DrRyanHuang@users.noreply.github.com> Co-authored-by: Chen Xin <xinchen.tju@gmail.com> Co-authored-by: q.yao <yaoqian@sensetime.com> Co-authored-by: zytx121 <592267829@qq.com> Co-authored-by: RunningLeon <mnsheng@yeah.net> Co-authored-by: Li Zhang <lzhang329@gmail.com> Co-authored-by: tripleMu <gpu@163.com> Co-authored-by: tripleMu <865626@163.com> Co-authored-by: hanrui1sensetime <83800577+hanrui1sensetime@users.noreply.github.com> Co-authored-by: Bryan Glen Suello <11388006+bgsuello@users.noreply.github.com> Co-authored-by: zambranohally <63218980+zambranohally@users.noreply.github.com> Co-authored-by: AllentDan <41138331+AllentDan@users.noreply.github.com> Co-authored-by: tpoisonooo <khj.application@aliyun.com> Co-authored-by: Hakjin Lee <nijkah@gmail.com> Co-authored-by: 孙德伟 <5899962+dwSun@users.noreply.github.com> Co-authored-by: dwSun <dwsunny@icloud.com> Co-authored-by: Chen Xin <irexyc@gmail.com> Co-authored-by: OldDreamInWind <108687632+OldDreamInWind@users.noreply.github.com> Co-authored-by: VVsssssk <88368822+VVsssssk@users.noreply.github.com> Co-authored-by: 梦阳 <49838178+liu-mengyang@users.noreply.github.com> Co-authored-by: gy77 <64619863+gy-7@users.noreply.github.com> Co-authored-by: gaoying <gaoying@xiaobaishiji.com> Co-authored-by: Hongyi Xiang <Groexhy@users.noreply.github.com> Co-authored-by: xianghongyi1 <xianghongyi1@sensetime.com> Co-authored-by: munhou <51435578+munhou@users.noreply.github.com> Co-authored-by: whhuang <whhuang@hitotek.com> Co-authored-by: grimoire <streetyao@live.com> Co-authored-by: cx <cx@ubuntu20.04> Co-authored-by: miraclezqc <969226879@qq.com> Co-authored-by: Jelle Maas <typiqally@gmail.com> Co-authored-by: ichitaka <tuemerffm@hotmail.com> Co-authored-by: Tümer Tosik <tumer_t@hotmail.de>

* [Feature] Support RoITransRoIHead * Add docs * Add mmrotate models regression test * Add a draft for test code * change the argument name * fix test code * fix minor change for not class agnostic case * fix sample for test code * fix sample for test code * Add mmrotate in requirements * Revert "Add mmrotate in requirements" This reverts commit 0434900.

nijkah added 2 commits July 6, 2022 19:45

[Feature] Support RoITransRoIHead

fd15b3a

Add docs

65a5d6c

lvhan028 requested review from RunningLeon and grimoire July 6, 2022 11:50

RunningLeon reviewed Jul 7, 2022

View reviewed changes

mmdeploy/codebase/mmrotate/models/roi_trans_roi_head.py Outdated Show resolved Hide resolved

RunningLeon reviewed Jul 7, 2022

View reviewed changes

docs/en/03-benchmark/benchmark.md Show resolved Hide resolved

nijkah added 2 commits July 8, 2022 12:14

Add mmrotate models regression test

4cb9ca3

Add a draft for test code

656079d

Merge remote-tracking branch 'origin/master' into feature/roi_trans

84d0284

RunningLeon reviewed Jul 14, 2022

View reviewed changes

mmdeploy/codebase/mmrotate/models/roi_heads/roi_trans_roi_head.py Outdated Show resolved Hide resolved

RunningLeon reviewed Jul 14, 2022

View reviewed changes

tests/test_codebase/test_mmrotate/test_mmrotate_models.py Outdated Show resolved Hide resolved

nijkah added 3 commits July 15, 2022 10:42

change the argument name

c5c003e

fix test code

1d51a98

fix minor change for not class agnostic case

1fc2642

nijkah added 2 commits July 18, 2022 14:01

fix sample for test code

e01c9f0

fix sample for test code

b82a6ba

Add mmrotate in requirements

0434900

Revert "Add mmrotate in requirements"

0b32eea

This reverts commit 0434900.

RunningLeon approved these changes Jul 20, 2022

View reviewed changes

grimoire approved these changes Jul 22, 2022

View reviewed changes

lvhan028 merged commit 36b3ca4 into open-mmlab:master Jul 22, 2022

nijkah deleted the feature/roi_trans branch July 22, 2022 07:56

Conversation

nijkah commented Jul 6, 2022 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Motivation

Modification

BC-breaking (Optional)

Use cases (Optional)

Checklist

Uh oh!

Uh oh!

Uh oh!

nijkah commented Jul 13, 2022 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

grimoire commented Jul 13, 2022

Uh oh!

RunningLeon commented Jul 14, 2022

Uh oh!

Uh oh!

Uh oh!

nijkah commented Jul 14, 2022 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

RunningLeon commented Jul 15, 2022 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

grimoire commented Jul 15, 2022

Uh oh!

nijkah commented Jul 15, 2022 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

nijkah commented Jul 18, 2022 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

nijkah commented Jul 18, 2022 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

RunningLeon commented Jul 19, 2022

Uh oh!

nijkah commented Jul 19, 2022 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

RunningLeon commented Jul 19, 2022

Uh oh!

RunningLeon left a comment

Choose a reason for hiding this comment

Uh oh!

nijkah commented Jul 20, 2022 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

RunningLeon commented Jul 20, 2022

Uh oh!

nijkah commented Jul 20, 2022 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

RunningLeon commented Jul 21, 2022 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

nijkah commented Jul 22, 2022 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

grimoire left a comment

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

nijkah commented Jul 6, 2022 •

edited

Loading

nijkah commented Jul 13, 2022 •

edited

Loading

nijkah commented Jul 14, 2022 •

edited

Loading

RunningLeon commented Jul 15, 2022 •

edited

Loading

nijkah commented Jul 15, 2022 •

edited

Loading

nijkah commented Jul 18, 2022 •

edited

Loading

nijkah commented Jul 18, 2022 •

edited

Loading

nijkah commented Jul 19, 2022 •

edited

Loading

nijkah commented Jul 20, 2022 •

edited

Loading

nijkah commented Jul 20, 2022 •

edited

Loading

RunningLeon commented Jul 21, 2022 •

edited

Loading

nijkah commented Jul 22, 2022 •

edited

Loading