#The modified data set contains 5000 apple pictures, including 2000 rotten apples and 2000 fresh apples,Divide training set and test set by 4:1 #Choose ResNet18 for migration learning, and only fine-tune its fully connected layer (last layer), where batch_size is 4 and epoch is 6 #We get a model that is 97% accurate on the test set #if you want the apple dataset,welcome contact with me. #wechat:15109007781 #email:756534202@qq.com
-
Notifications
You must be signed in to change notification settings - Fork 0
它可以识别苹果是否腐烂,并给出详细的新鲜度分析
License
EthanZhou0826/rotten_apple_classfication
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
它可以识别苹果是否腐烂,并给出详细的新鲜度分析
Topics
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published