강의

N
챌린지

멘토링

N
클립

커뮤니티

BEST
AI Technology

/

Computer Vision

[Revised Edition] Deep Learning Computer Vision: The Complete Guide

This course will help you grow into a deep learning-based computer vision expert needed in the field through in-depth theoretical explanations of Object Detection and Segmentation, along with practical examples at a level that can be immediately applied in the industry.

(4.9) 165 reviews

4,028 learners

Level Intermediate

Course period Unlimited

  • dooleyz3525
Python
Python
Machine Learning(ML)
Machine Learning(ML)
Deep Learning(DL)
Deep Learning(DL)
Computer Vision(CV)
Computer Vision(CV)
Python
Python
Machine Learning(ML)
Machine Learning(ML)
Deep Learning(DL)
Deep Learning(DL)
Computer Vision(CV)
Computer Vision(CV)
News list
dooleyz3525님의 프로필 이미지
dooleyz3525

Notice on solution to error when performing train_detector using mmdetection

hello,

 

Due to recent changes in the mmdetection package, when executing train_detector(model, datasets, cfg, distributed=False, validate=True), an error similar to 'ConfigDict' object has no attribute 'device' occurs.

 

You can check the issue at https://github.com/open-mmlab/mmdetection/issues/7901.

 

To solve this, add cfg.device='cuda' to the config settings as shown below.

 

For example, in the cfg settings in the practice code, you can add cfg.device='cuda' at the very end as shown below.

 

I'm not sure if this is a bug or intentional, so I won't modify the practice code on github for now.

 

If the problem still occurs after observing for about a week, I will revise the practice code on github and notify you.

 

thank you

 

# Modify environment parameters for dataset.

cfg.dataset_type = 'PetDataset'

cfg.data_root = '/content/data/'

 

# Modify environment parameters type, data_root, ann_file, and img_prefix for train, val, and test datasets.

cfg.data.train.type = 'PetDataset'

cfg.data.train.data_root = '/content/data/'

cfg.data.train.ann_file = 'train.txt'

cfg.data.train.img_prefix = 'images'

 

.....other config settings

 

# Settings to prevent 'ConfigDict' object has no attribute 'device' error.

cfg.device='cuda'

Comment