当前位置:网站首页>Mmdetection installation problem
Mmdetection installation problem
2022-07-02 07:34:00 【chenf0】
Question 1 :Install MMDetection Report errors
pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/{
cu_version}/{
torch_version}/index.html
My environment
cu_version10.1 ( Input nvcc -V command , You can find CUDA Version number .)
torch_version1.10.2
mmcv-full is only compiled on PyTorch 1.x.0 because the compatibility
usually holds between 1.x.0 and 1.x.1. If your PyTorch version is
1.x.1, you can install mmcv-full compiled with PyTorch 1.x.0 and it usually works well.
https://github.com/open-mmlab/mmcv#installation
pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu101/torch1.10.0/index.html
There is an error 

Have a look PyTorch and CUDA Version combination , It is found that there is no corresponding version , Reduce torch edition , take 1.10.2 Reduced to 1.8.1
https://github.com/open-mmlab/mmcv/blob/master/README_zh-CN.md
The whole process :
#1.Prepare environment
conda create -n openmmlab python=3.7 -y
conda activate openmmlab
conda install pytorch=1.8.1 cudatoolkit=10.1 torchvision -c pytorch
#2.Install mmcv-full.
pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu101/torch1.8.0/index.html
#3.Install MMDetection.
git clone https://github.com/open-mmlab/mmdetection.git
cd mmdetection
pip install -r requirements/build.txt
pip install -v -e . # or "python setup.py develop"
Question two fatal: unable to access…
stay git Problems encountered while downloading items :
fatal: unable to access 'https://github.com/open-mmlab/mmdetection.git/': gnutls_handshake() failed: A TLS packet with unexpected length was received.
Solution :
take https Change it to git Re execution
git clone git://github.com/open-mmlab/mmdetection.git
Question 3 :ImportError: cannot import name ‘PILLOW_VERSION’ from ‘PIL’
Method 2. According to the prompt in the last line of the error report , open function.py file , Use from PIL import Image, ImageOps, ImageEnhance, version In the replacement file from PIL import Image, ImageOps, ImageEnhance,PILLOW_VERSION This sentence .
Reference solutions :https://blog.csdn.net/Lee_lg/article/details/103901632
When cuda 11
https://pytorch.org/get-started/previous-versions/
conda install pytorch==1.7.0 torchvision==0.8.0 torchaudio==0.7.0 cudatoolkit=11.0 -c pytorch
Mirror image problem https://blog.csdn.net/weixin_49304494/article/details/122622134
边栏推荐
- 基于pytorch的YOLOv5单张图片检测实现
- 【信息检索导论】第一章 布尔检索
- Data warehouse model fact table model design
- 【Torch】最简洁logging使用指南
- Oracle APEX 21.2 installation et déploiement en une seule touche
- SSM second hand trading website
- 【BERT,GPT+KG调研】Pretrain model融合knowledge的论文集锦
- Drawing mechanism of view (I)
- 一份Slide两张表格带你快速了解目标检测
- Determine whether the version number is continuous in PHP
猜你喜欢
随机推荐
Drawing mechanism of view (II)
SSM laboratory equipment management
Typeerror in allenlp: object of type tensor is not JSON serializable error
Oracle RMAN semi automatic recovery script restore phase
【MEDICAL】Attend to Medical Ontologies: Content Selection for Clinical Abstractive Summarization
parser.parse_args 布尔值类型将False解析为True
Pyspark build temporary report error
allennlp 中的TypeError: Object of type Tensor is not JSON serializable错误
生成模型与判别模型的区别与理解
深度学习分类优化实战
【论文介绍】R-Drop: Regularized Dropout for Neural Networks
離線數倉和bi開發的實踐和思考
PHP returns the abbreviation of the month according to the numerical month
[medical] participants to medical ontologies: Content Selection for Clinical Abstract Summarization
实现接口 Interface Iterable<T>
DNS attack details
机器学习理论学习:感知机
Module not found: Error: Can't resolve './$$_gendir/app/app.module.ngfactory'
Oracle segment advisor, how to deal with row link row migration, reduce high water level
Oracle EBS ADI development steps



![[introduction to information retrieval] Chapter II vocabulary dictionary and inverted record table](/img/3f/09f040baf11ccab82f0fc7cf1e1d20.png)




