no model named mega_core

[SpongeBab]

(python38) F:\视频目标检测\代码\mega.pytorch>python -m torch.distributed.launch --nproc_per_node 4 tools/test_net.py --config-file configs/MEGA/vid_R_101_C4_MEGA_1x.yaml --motion-specific MODEL.WEIGHT MEGA_R_101.pth

---

Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.

---

Traceback (most recent call last): Traceback (most recent call last): Traceback (most recent call last): File "tools/test_net.py", line 4, in File "tools/test_net.py", line 4, in File "tools/test_net.py", line 4, in from mega_core.utils.env import setup_environment # noqa F401 isort:skip ModuleNotFoundError: No module named 'mega_core' from mega_core.utils.env import setup_environment # noqa F401 isort:skip ModuleNotFoundError: No module named 'mega_core' from mega_core.utils.env import setup_environment # noqa F401 isort:skip ModuleNotFoundError: No module named 'mega_core' Traceback (most recent call last): File "D:\Anaconda\envs\python38\lib\runpy.py", line 194, in _run_module_as_main Traceback (most recent call last): return _run_code(code, main_globals, None, File "tools/test_net.py", line 4, in File "D:\Anaconda\envs\python38\lib\runpy.py", line 87, in _run_code from mega_core.utils.env import setup_environment # noqa F401 isort:skip ModuleNotFoundError : No module named 'mega_core'exec(code, run_globals)

File "D:\Anaconda\envs\python38\lib\site-packages\torch\distributed\launch.py", line 261, in main() File "D:\Anaconda\envs\python38\lib\site-packages\torch\distributed\launch.py", line 256, in main raise subprocess.CalledProcessError(returncode=process.returncode, subprocess.CalledProcessError: Command '['D:\Anaconda\envs\python38\python.exe', '-u', 'tools/test_net.py', '--local_rank=3', '--config-file', 'configs/MEGA/vid_R_101_C4_MEGA_1x.yaml', '--motion-specific', 'MODEL.WEIGHT', 'MEGA_R_101.pth']' returned non-zero exit status 1.

anynoe can help me???.......

[joe660]

我遇到了同样的问题 请问你解决了吗？ 麻烦你了 谢谢

[SpongeBab]

之前配成功了。忘了怎么解决的了。不过最好是在ubuntu下安装。能避免很多问题。

发自我的iPhone

在 2021年4月8日，下午6:22，joe660 @.***> 写道：

 我遇到了同样的问题 请问你解决了吗？ 麻烦你了 谢谢

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

[joe660]

你还记得当时python是3.6还是3.7？谢谢？我就是在Ubuntu下安装，出现了错误。难受。。。。

[SpongeBab]

我是3.8。

发自我的iPhone

在 2021年4月8日，下午10:33，joe660 @.***> 写道：

 你还记得当时python是3.6还是3.7？谢谢？我就是在Ubuntu下安装，出现了错误。难受。。。。

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

[joe660]

我是3.8。 发自我的iPhone … 在 2021年4月8日，下午10:33，joe660 @.***> 写道：  你还记得当时python是3.6还是3.7？谢谢？我就是在Ubuntu下安装，出现了错误。难受。。。。 — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

作者 你跑通的模型可以发给我一份吗 不用您的数据，我的qq：2517449340 微信：z2517449340 感谢老哥！！！

[joe660]

我是3.8。 发自我的iPhone … 在 2021年4月8日，下午10:33，joe660 @.***> 写道：  你还记得当时python是3.6还是3.7？谢谢？我就是在Ubuntu下安装，出现了错误。难受。。。。 — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

在吗 为什么我运行原始模型就可以成功，但是运行MEGA就报错，我只用了部分VID的数据，没有使用DET数据集，错误如下：

[fengjingchehu]

ModuleNotFoundError: No module named 'mega_core' 我遇到了同样的问题，请问你解决了吗？

[returnlsz]

你需要在你的MEGA虚拟环境中主动导入mega_core的地址，激活虚拟环境后，使用命令export PYTHONPATH="${PYTHONPATH}:autodl-tmp/mega.pytorch/mega_core" 即可解决