Vacc Backend

[AndyLiu93]

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

Motivation

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

Modification

Please briefly describe what modification is made in this PR.

BC-breaking (Optional)

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

Use cases (Optional)

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

Checklist

1. Pre-commit or other linting tools are used to fix the potential lint issues.
2. The modification is covered by complete unit tests. If not, please add more unit tests to ensure the correctness.
3. If the modification has a dependency on downstream projects of a newer version, this PR should be tested with all supported versions of downstream projects.
4. The documentation has been modified accordingly, like docstring or example tutorials.

[CLAassistant]

All committers have signed the CLA.

[lvhan028]

Hi, @AndyLiu93
Please sign CLA before we can accept your contribution.

Please fix the lint issue. You can install pre-commit hook on your localhost like following:

pip install -U pre-commit
cd mmdeploy
pre-commit install

You can run pre-commit run --all-file to check whether there are lint errors

[lvhan028]

Do you have any plan to integrate vacc backend to mmdeploy SDK?

[lvhan028]

A github workflow or github action runner is appreciated

[AndyLiu93]

Do you have any plan to integrate vacc backend to mmdeploy SDK?

Yes, we will support vacc backend to mmdeploy SDK

[lvhan028]

The deployment of fcn in mmsegmentation failed.
The command was

python tools/deploy.py configs/mmseg/segmentation_vacc-fp16_static_512x512.py ../mmsegmentation/configs/fcn/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py ~/lvhan/checkpoint/mmseg/fcn_r50-d8_512x512_20k_voc12aug_20200617_010715-52dc5306.pth demo/resources/cityscapes.png --dump-info --work-dir ../mmdeploy_models/mmseg/fcn/fp16

The error log:

vm._ffi.base.TVMError:   File "/home/mmdeploy/tool/vaststream-1.2.5/tvm/python/tvm/_ffi/_ctypes/function.py", line 72, in cfun
    rv = local_pyfunc(*pyargs)
  File "/home/mmdeploy/tool/vaststream-1.2.5/tvm/python/tvm/relay/op/image/_image.py", line 36, in compute_resize
    return [topi.image.resize(inputs[0], size, layout, method, align_corners, out_dtype)]
  File "/home/mmdeploy/anaconda3/envs/openmmlab2.0/lib/python3.8/site-packages/decorator.py", line 232, in fun
    return caller(func, *(extras + args), **kw)
  File "/home/mmdeploy/tool/vaststream-1.2.5/tvm/python/tvm/target.py", line 382, in dispatch_func
    return dispatch_dict[k](*args, **kwargs)
  File "/home/mmdeploy/anaconda3/envs/openmmlab2.0/lib/python3.8/site-packages/decorator.py", line 232, in fun
    return caller(func, *(extras + args), **kw)
  File "/home/mmdeploy/tool/vaststream-1.2.5/tvm/python/tvm/autotvm/task/dispatcher.py", line 216, in dispatch_func
    return dispatch_dict['direct'](cfg, *args, **kwargs)
  File "/home/mmdeploy/tool/vaststream-1.2.5/tvm/python/tvm/autotvm/task/topi_integration.py", line 397, in template_call
    node = f(cfg, *args, **kwargs)
  File "/home/mmdeploy/tool/vaststream-1.2.5/tvm/vacc/python/vacc/top/vacc.py", line 919, in _declaration_vacc_resize
    assert(scale_h.value == scale_w.value), "Only support same scale factor on axis H and W"
AssertionError: Only support same scale factor on axis H and W

[AllentDan]

Looks good to me except that there is no benchmark for exported models. Is there any further plan?

[grimoire]

LGTM

[RunningLeon]

LGTM

[vansin]

@AndyLiu93 Congratulations on having your first PR merged in OpenMMLab! I am a technical operations staff member of OpenMMLab. My WeChat ID is van-sin ,please add me . I would like to invite you to join the OpenMMLab contributors WeChat group.