当前位置:网站首页>Cs231n notes (bottom) - applicable to 0 Foundation
Cs231n notes (bottom) - applicable to 0 Foundation
2022-07-05 16:43:00 【Small margin, rush】
Catalog
Transfer learning and object location monitoring
Object segmentation & Semantic segmentation
Transfer learning and object location monitoring
Can target detection be regarded as a regression problem ? The bounding box of multiple objects output for different pictures , May output 4 A bounding box may also output 8 A bounding box , The number of outputs is not fixed , So it can't be regarded as a return problem .
The migration study
In practice , Because few data sets are large enough , So few people choose to train the network from scratch . The common way is : Pre train one on a very large data set CNN, Then use the pre trained network as the initialization network to fine tune 、 Or as a feature extractor .
- Convolutional neural network as a feature extractor . Use in ImageNet Pre trained CNN, Remove the last full connection layer ( namely : The last layer used for classification ), Then use the rest as a feature extractor .
- Fine-tuning CNN. Replace the input layer of the network ( data ), Continue training with new data .
Transfer learning scenarios :
- The new dataset is relatively small , And it is highly similar to the original data set . It is not recommended to CNN Conduct Fine-tune, It is recommended to use pre trained CNN As a feature extractor , Then train a linear classifier .
- The new data set is relatively large , And it is highly similar to the original data set . Because the new data set is large enough , Sure fine-tune The whole network
- The new dataset is smaller , And it is very different from the original data set . Because the data set is very small , So it is best to train a linear classifier . And because the data set is not similar to the original data set , The best way is to train a linear classifier from the shallow output of the pre training network as a feature .
- The new data set is relatively large , And it is very different from the original data set . Because the new data set is big enough , You can retrain the network .
Object positioning & testing
After labeling the picture , Also frame where the object is - In classification and positioning , The number of output boxes is known in advance , And object detection is uncertain , And classification + The difference between positioning tasks is , The number of objects to be detected in object detection is uncertain , Therefore, the regression framework cannot be used directly .
The sliding window -overfeat
Randomly select several windows of different sizes and positions
RCNN
- Pre train a CNN
- Build a training set : First apply Selective Search The algorithm selects 2000~3000 Candidate box .
- Each candidate region is preprocessed , Deliver to CNN Extract image features , Then send the image features to SVM In the classifier , Calculate the loss of label classification . At the same time, the image features are also sent to the regressor , Calculate the offset distance L2 Loss .
- Back propagation training
fast R-CNN
solve R-CNN The problem of slow training prediction , The whole image is CNN feature extraction , Then select the candidate area
- And R-CNN Same use Selective Search Method generation 2000 Multiple candidate boxes
- Input the whole picture directly CNN in , Feature extraction
- Put the 2000 Boxes map to just CNN The last layer extracted feature map On
faster R-CNN:
SSD
SSD The idea is to divide the image into many grids , Several can be derived from the center of each lattice base boxes. Use neural network to classify these grids at one time , For these baseboxes Regression .
Object segmentation & Semantic segmentation
Semantic segmentation is to classify each pixel in the image , Do not distinguish between objects , Only care about pixels , Often costly , May first The framework of undersampling and oversampling
Under sampling can use convolution layer and pooling , Over sampling adopts de pooling , Transposition convolution
There is another one called Max Unpooling Methods , This method records the previous use max pooling The index of the previous maximum values in the array , When de pooling, put the value in the index , Fill in other positions 0:
Object segmentation -Mask RCNN
What we need to do is to go further in object detection , Segment the objects from the pixel level .
Use images CNN Process as a feature , And then through a RPN Network generation candidate area , Project to the previous feature map. Here with faster RCNN equally . Then there are two branches , A branch and faster RCNN identical , Predict the classification and boundary value of the candidate box , Another branch is similar to semantic segmentation , Classify each pixel .
边栏推荐
- Data verification before and after JSON to map -- custom UDF
- 一键安装脚本实现快速部署GrayLog Server 4.2.10单机版
- Jarvis OJ Flag
- Data Lake (XIV): spark and iceberg integrated query operation
- Today's sleep quality record 79 points
- 养不起真猫,就用代码吸猫 -Unity 粒子实现画猫咪
- Mongodb getting started Tutorial Part 04 mongodb client
- 程序员如何提升自己的格局?
- tf. sequence_ Mask function explanation case
- EDI许可证和ICP经营性证有什么区别
猜你喜欢
单商户 V4.4,初心未变,实力依旧!
[61dctf]fm
How was the middle table destroyed?
新春限定丨“牛年忘烦”礼包等你来领~
Data Lake (XIV): spark and iceberg integrated query operation
Bs-xx-042 implementation of personnel management system based on SSM
【刷題篇】鹅廠文化衫問題
Today's sleep quality record 79 points
普洛斯数据中心发布DC Brain系统,科技赋能智慧化运营管理
Android privacy sandbox developer preview 3: privacy, security and personalized experience
随机推荐
【刷题篇】有效的数独
Do sqlserver have any requirements for database performance when doing CDC
【学术相关】多位博士毕业去了三四流高校,目前惨不忍睹……
Cheer yourself up
Reduce the cost by 40%! Container practice of redis multi tenant cluster
为季前卡牌游戏 MotoGP Ignition Champions 做好准备!
漫画:什么是服务熔断?
How was the middle table destroyed?
[team PK competition] the task of this week has been opened | question answering challenge to consolidate the knowledge of commodity details
Quelques réflexions cognitives
树莓派4b安装Pytorch1.11
搜索 正排索引 和 倒排索引 区别
Cartoon: what is distributed transaction?
解决CMakeList find_package找不到Qt5,找不到ECM
10 minutes to help you get ZABBIX monitoring platform alarm pushed to nail group
You should have your own persistence
Today's sleep quality record 79 points
scratch五彩糖葫芦 电子学会图形化编程scratch等级考试三级真题和答案解析2022年6月
降本40%!Redis多租户集群的容器化实践
Accès aux données - intégration du cadre d'entité