Mmdetection: Training Error on Google Colab

Created on 3 Jul 2020  路  6Comments  路  Source: open-mmlab/mmdetection

I am using google colab to train model for table structure recognition. When I execute the command
!python tools/train.py {config_fname}
I got the the following error-

Traceback (most recent call last): File "tools/train.py", line 14, in <module> from mmdet.apis import set_random_seed, train_detector File "/usr/local/lib/python3.6/dist-packages/mmdet-1.2.0+0f33c08-py3.6-linux-x86_64.egg/mmdet/apis/__init__.py", line 1, in <module> from .inference import (async_inference_detector, inference_detector, File "/usr/local/lib/python3.6/dist-packages/mmdet-1.2.0+0f33c08-py3.6-linux-x86_64.egg/mmdet/apis/inference.py", line 13, in <module> from mmdet.models import build_detector File "/usr/local/lib/python3.6/dist-packages/mmdet-1.2.0+0f33c08-py3.6-linux-x86_64.egg/mmdet/models/__init__.py", line 3, in <module> from .bbox_heads import * # noqa: F401,F403 File "/usr/local/lib/python3.6/dist-packages/mmdet-1.2.0+0f33c08-py3.6-linux-x86_64.egg/mmdet/models/bbox_heads/__init__.py", line 3, in <module> from .double_bbox_head import DoubleConvFCBBoxHead File "/usr/local/lib/python3.6/dist-packages/mmdet-1.2.0+0f33c08-py3.6-linux-x86_64.egg/mmdet/models/bbox_heads/double_bbox_head.py", line 2, in <module> from mmcv.cnn.weight_init import normal_init, xavier_init ModuleNotFoundError: No module named 'mmcv.cnn.weight_init'

I am using cascade_mask_rcnn_hrnetv2p_w32_20e.py to train my model and following this link https://github.com/Tony607/mmdetection_object_detection_demo/blob/master/mmdetection_train_custom_coco_data.ipynb

Can you help me out on this?

Most helpful comment

i use colab to train cascade_rcnn , successly

I was also able to run it successfully 2 weeks ago but this time when I am runnning it after changing data files it is not working.

maybe mmcv has updated

you can pip install mmcv==0.4.3

All 6 comments

i use colab to train cascade_rcnn , successly

i use colab to train cascade_rcnn , successly

I was also able to run it successfully 2 weeks ago but this time when I am runnning it after changing data files it is not working.

i use colab to train cascade_rcnn , successly

I was also able to run it successfully 2 weeks ago but this time when I am runnning it after changing data files it is not working.

maybe mmcv has updated

i use colab to train cascade_rcnn , successly

I was also able to run it successfully 2 weeks ago but this time when I am runnning it after changing data files it is not working.

maybe mmcv has updated

you can pip install mmcv==0.4.3

Thanks. It worked :)

i use colab to train cascade_rcnn , successly

I was also able to run it successfully 2 weeks ago but this time when I am runnning it after changing data files it is not working.

maybe mmcv has updated

you can pip install mmcv==0.4.3

thks, your answer help me a lot!!!

Was this page helpful?
0 / 5 - 0 ratings