Skip to content

ckull/cnn_catdog

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 

Repository files navigation

CNN_CatDog

Cat And Dog classification using interception v3 model which based on convolutional neural network. This model.py is implemented by Keras and can be retrain with a new datasets (not just cat and dog).

Datasets: https://goo.gl/jGdxbE

Test result

These are the last 3 results after retrain with 10 Epoch and 25 of fine-tuning

Epoch 23/25 250/250 [==============================] - 63s - loss: 0.1122 - acc: 0.9534 - val_loss: 0.2114 - val_acc: 0.9330

Epoch 24/25 250/250 [==============================] - 62s - loss: 0.1251 - acc: 0.9539 - val_loss: 0.1822 - val_acc: 0.9395

Epoch 25/25 250/250 [==============================] - 62s - loss: 0.1120 - acc: 0.9589 - val_loss: 0.2166 - val_acc: 0.9235

Preview all the test: https://goo.gl/afrvDG

About

Cat Vs Dog CNN classification using interception v3 model (retrain and fine-tuned)

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages