Skip to content

Submission to the first Mobile AI challenge, where the target is to develop quantized deep learning-based camera scene classification solutions that can demonstrate a real-time performance on smartphones and IoT platforms

Notifications You must be signed in to change notification settings

ckyrkou/Mobile_AI_Camera_Scene_Detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 

Repository files navigation

Requirements:
Tensorflow/Keras 2.3
Albumentations
Custom ImageGenerator (Files Provided also available: https://github.com/mjkvaak/ImageDataAugmentor)

How to run:

python train_keras.py

Put training images in ./Training/ folder
Put validation images in ./Validation/ folder

Each class should have a dedicated folder with its own images with numbering starting from 00


Output:
Checkpoint files - best accuracy in an epoch
accuracy-loss curves

About

Submission to the first Mobile AI challenge, where the target is to develop quantized deep learning-based camera scene classification solutions that can demonstrate a real-time performance on smartphones and IoT platforms

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages