Train Xception Model after adjustments made to training data (LIME)

afislonge / deepfake-detection-project

Our project aims to develop a machine learning model to compare and contrast images sourced from Flickr, a platform with user-uploaded photographs, against those generated by ThisPersonDoesNotExist, which uses generative adversarial networks (GANs) to create lifelike human images. We'll evaluate the nuances in authenticity and quality

3 stars 1 forks source link

Train Xception Model after adjustments made to training data (LIME) #47

Open isamia1910 opened 5 months ago

isamia1910 commented 5 months ago

Training the model after adjustments were made to the training data, using the best model as base model.

isamia1910 commented 5 months ago

Model 2 generated with the following improvments:

isamia1910 commented 5 months ago

First model location: /content/drive/My Drive/checkpoints/Xception2/7/model_epoch_14_val_accuracy_0.9115.h5

Second (fine-tuned model) location: /content/drive/My Drive/checkpoints/Xception2/10/model_epoch_11_val_accuracy_0.9414.h5