top of page

Classify Each Face Based On Gender Using CNNs(On Tensorflow 2.x and OpenCV): Practice Set

Problem Statement

UTKFace Dataset is a large-scale face dataset with a long age span (range from 0 to 116 years old). The objective is to classify each face based on gender using CNNs on Tensorflow 2.x and then, use OpenCV & Haar Cascade File to check the gender in real-time.

Dataset Description

UTKFace Dataset Total Images:

  • The Dataset consists of over 20,000 Face Images

  • The images cover large variations in pose, facial expression, illumination, resolution, etc. This dataset could be used on a variety of tasks, e.g., face detection, age estimation, gender detection, landmark localization, etc.

  • You will be using the Aligned & Cropped Faces Dataset from the UTKFace Dataset.

Dataset available at here

Tasks 1 to be performed

.ipynb file 1

  • Do you get the same results if you run the Notebook multiple times without changing any parameters?

  • What is the effect of adding more neurons to each Conv2D layer?

  • What happens if we manipulate the value of dropout?

  • What is the effect of adding more activation layers to the network?

  • What is the purpose of MaxPooling2D layer?

  • Does manipulating the learning rate affect the model? Justify your answer.

Tasks 2 to be performed

.ipynb file 2

  • Try improving the model and re-code the program from scratch without looking too much at this source code

  • Write up a summary explaining how your program works

Tasks 3 to be performed

.ipynb file 3

Import Required Libraries

  • Prepare the dataset for the model

  • Develop CNN model for recognizing the gender

  • Analyze the model summary

  • Fit the basic CNN model

  • Predict the Gender of the uploaded image

  • Use OpenCV and Haar Cascade File to check the gender in Real-time

Contact us or send your requirement details at get the solution of above problem with an affordable prices at:


bottom of page