Skip to content

injemamul/BrainTumorClassification

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 

Repository files navigation

BrainTumorClassification

VGG16 97% Train acc, 98% Val acc and 100% on TestSet

Description

The Size of the dataset was 3000, It's a very small dataset that i got from kaggle.
Training Size: 2600
Val_size: 450
Test_size: 150

Trained for 50 Epochs but got the best val_loss at 14th epoch with 98% val Accuracy.
used checkpoints to get the best model.

Problems that i faced:
Image size was not equal for all. >> resized and croped for better result.

End-to-End project:

  1. Preprocessing -- done
  2. Model training -- done
  3. Front-end --
  4. Deployment --

About

VGG16 97% Train acc, 98% Val acc and 100% on TestSet

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors