International Journal of Scientific Research and Engineering Development( International Peer Reviewed Open Access Journal ) ISSN [ Online ] : 2581 - 7175 |
Performance Evaluation of Different Machine Learning Frameworks for Facial Expression Recognition
International Journal of Scientific Research and Engineering Development (IJSRED) | ||
Published Issue : Volume-4 Issue-2 | ||
Year of Publication : 2021 | ||
Unique Identification Number : IJSRED-V4I2P119 | ||
Authors : Md Asif Shahjalal, Rafi Ud Daula Refat, Rushrukh Rayan | ||
: Click Here |
Abstract :
Image processing is one of the hot topics nowadays. Machine learning frameworks like Pytorch, Keras, TensorFlow etc. all provides support for solving image processing related problems. But each framework has its own philosophy and system requirements. It is difficult for the user to choose the framework perfect for his system. The goal of this work is to provide a comparative analysis of different machine learning algorithms in terms of memory and system requirements. The whole experiment was performed on google collaboration platform, used convolutional neural network algorithm and coded in Pytorch, Keras and TensorFlow. From the experiments, most of the cases we found out that increasing the batch training size, the training time decreases in all frameworks.