Skip to content

谷歌INCEPTION-RESNET-V3迁移学习实现图像二分类判断图像是否生病

Notifications You must be signed in to change notification settings

jiangyiqiao/fundus_transfer_v3_classification

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 

Repository files navigation

fundus_binary_classification

眼底图二分类——inception v3 迁移学习

参考https://blog.csdn.net/White_Idiot/article/details/78816850 tensorflow 实现谷歌INCEPTION-V3迁移学习

LEARNING_RATE = 0.01
STEPS = 10000
BATCH = 100
CHECKPOINT_EVERY = 100
NUM_CHECKPOINTS = 5
VALIDATION_PERCENTAGE = 10 
TEST_PERCENTAGE = 10 

图像对比

  • 正样本

* 负样本

Dependencies

  • tensorflow

其中,训练集正负样本各约3600

训练数据集: data/

训练:

python train.py

验证: python validation.py

result

Validation accuracy on random sampled 100 examples = 83.2%

train acc

loss

About

谷歌INCEPTION-RESNET-V3迁移学习实现图像二分类判断图像是否生病

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages