rgkannan676 / Recognition-and-Classification-of-Facial-Attributes

Created a classifier that can identify and classify 41 types of facial attributes, using an ImageNet pre-trained ResNext50 model provided by PyTorch and CelebA dataset. Multiple data augmentation techniques were used along with the MSE loss function. Obtained a training accuracy of 95.7% and test accuracy of 91.8%.
10Updated 3 years ago

Related projects

Alternatives and complementary repositories for Recognition-and-Classification-of-Facial-Attributes