Gender Classification Model based on the Resnet 152 Architecture

The objective of the gender categorization job is to determine a person's gender based on the face photographs of that individual. Approaches that are based on deep learning have shown encouraging outcomes in this field in recent years. A gender categorization model that is based on the Resnet 152 architecture is one of the contributions that this work makes. It has been shown that the Resnet 152 architecture can attain state-of-the-art performance on a variety of image recognition applications. This design is a deep residual neural network. We used a huge dataset of facial photos to fine-tune the previously trained Resnet 152 model, which can determine whether a person is a male or female based on the appearance of their face. The suggested model performed much better than numerous other state-of-the-art gender categorization models, with an accuracy of 99% on the test set. Our findings suggest that applying deep learning-based techniques for gender categorization is beneficial and that the Resnet 152 architecture has the potential to be used for this job.