Skip to content
New issue

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

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

Already on GitHub? Sign in to your account

请问这个框架不支持蒸馏吗? #52

Open
ersanliqiao opened this issue Dec 4, 2022 · 5 comments
Open

请问这个框架不支持蒸馏吗? #52

ersanliqiao opened this issue Dec 4, 2022 · 5 comments

Comments

@ersanliqiao
Copy link

Traceback (most recent call last):
File "/opt/conda/lib/python3.8/runpy.py", line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/opt/conda/lib/python3.8/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/data/juicefs_hz_cv_v3/11105507/AAAI2022/united-perception2/up/main.py", line 31, in
main()
File "/data/juicefs_hz_cv_v3/11105507/AAAI2022/united-perception2/up/main.py", line 25, in main
args.run(args)
File "/data/juicefs_hz_cv_v3/11105507/AAAI2022/united-perception2/up/commands/train.py", line 161, in _main
launch(main, args.num_gpus_per_machine, args.num_machines, args=args, start_method=args.fork_method)
File "/data/juicefs_hz_cv_v3/11105507/AAAI2022/united-perception2/up/utils/env/launch.py", line 68, in launch
main_func(*(args,))
File "/data/juicefs_hz_cv_v3/11105507/AAAI2022/united-perception2/up/commands/train.py", line 140, in main
runner = RUNNER_REGISTRY.get(runner_cfg['type'])(cfg, **runner_cfg['kwargs'])
File "/data/juicefs_hz_cv_v3/11105507/AAAI2022/united-perception2/up/utils/general/registry.py", line 81, in get
assert module_name in self, '{} is not supported, avaiables are:{}'.format(module_name, self)
AssertionError: kd is not supported, avaiables are:{'base': <class 'up.runner.base_runner.BaseRunner'>}

@yqyao
Copy link

yqyao commented Dec 5, 2022

If you want to use distill, you need add tasks export DEFAULT_TASKS=cls:distill @ersanliqiao

@ersanliqiao
Copy link
Author

If you want to use distill, you need add tasks export DEFAULT_TASKS=cls:distill @ersanliqiao

多谢,改完可以跑了,另外,想问下我跑nas,导入task也改了(export DEFAULT_TASKS=cls:bignas
),但是还是报错:
no custom work to be done.

  • export DEFAULT_TASKS=cls:bignas
  • DEFAULT_TASKS=cls:bignas
  • bash scripts/dist_train.sh 1 /data/juicefs_hz_cv_v3/11105507/AAAI2022/united-perception2/configs/nas/bignas/cls/bignas_regnet_800m_train_supnet.yaml
    No module named 'petrel_client'
    init petrel failed
    No module named 'spring_aux'
    2022-12-06 17:40:51,629-rk0-normalize.py#37:import error No module named 'mqbench'; If you need Mqbench to quantize model, you should add Mqbench to this project. Or just ignore this error.
    2022-12-06 17:40:51,629-rk0-normalize.py#44:import error No module named 'msbench'; If you need Msbench to prune model, you should add Msbench to this project. Or just ignore this error.
    Traceback (most recent call last):
    File "/opt/conda/lib/python3.8/runpy.py", line 194, in _run_module_as_main
    return _run_code(code, main_globals, None,
    File "/opt/conda/lib/python3.8/runpy.py", line 87, in _run_code
    exec(code, run_globals)
    File "/data/juicefs_hz_cv_v3/11105507/AAAI2022/united-perception2/up/main.py", line 31, in
    main()
    File "/data/juicefs_hz_cv_v3/11105507/AAAI2022/united-perception2/up/main.py", line 25, in main
    args.run(args)
    File "/data/juicefs_hz_cv_v3/11105507/AAAI2022/united-perception2/up/commands/train.py", line 161, in _main
    launch(main, args.num_gpus_per_machine, args.num_machines, args=args, start_method=args.fork_method)
    File "/data/juicefs_hz_cv_v3/11105507/AAAI2022/united-perception2/up/utils/env/launch.py", line 68, in launch
    main_func(*(args,))
    File "/data/juicefs_hz_cv_v3/11105507/AAAI2022/united-perception2/up/commands/train.py", line 140, in main
    runner = RUNNER_REGISTRY.get(runner_cfg['type'])(cfg, **runner_cfg['kwargs'])
    File "/data/juicefs_hz_cv_v3/11105507/AAAI2022/united-perception2/up/utils/general/registry.py", line 81, in get
    assert module_name in self, '{} is not supported, avaiables are:{}'.format(module_name, self)
    AssertionError: bignas is not supported, avaiables are:{'base': <class 'up.runner.base_runner.BaseRunner'>}
    train <class 'up.commands.train.Train'>

@yqyao
Copy link

yqyao commented Dec 7, 2022

Maybe you need to set DEFAULT_TASKS=cls:nas @ersanliqiao

@TheWangYang
Copy link

TheWangYang commented Dec 8, 2022

Why did I add export DEFAULT_TASKS=cls:distill as you mentioned above, but I got the following error:

ImportError: cannot import name 'gpu_iou_overlap' from 'up.extensions' (/ssd3/wyy/projects/United-Perception/up/extensions/__init__.py)

This seems to be the same as the error I reported before when I did not export any tasks. How can I solve it? Looking forward to your reply? @yqyao

@yqyao
Copy link

yqyao commented Dec 8, 2022

If you want to use advanced features, maybe you need to compile extensions. following the docs @TheWangYang

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants