Hands-On Transfer Learning with Python by Dipanjan Sarkar

Author:Dipanjan Sarkar
Language: eng
Format: epub, pdf
Tags: COM004000 - COMPUTERS / Intelligence (AI) and Semantics, COM044000 - COMPUTERS / Neural Networks, COM042000 - COMPUTERS / Natural Language Processing
Publisher: Packt Publishing
Published: 2018-08-30T13:32:01+00:00

We get a validation accuracy jump to around 82%, which is almost 4-5% better than our previous model. Also, our training accuracy is very similar to our validation accuracy, indicating our model isn't overfitting anymore. The following depict the model accuracy and loss per epoch:

While there are some spikes in the validation accuracy and loss, overall, we see that it is much closer to the training accuracy, with the loss indicating that we obtained a model that generalizes much better as compared to our previous models. Let's save this model now so we can evaluate it later on our test dataset:

model.save('cats_dogs_cnn_img_aug.h5')

We will now try and leverage the power of transfer learning to see if we can build a better model.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.