Comparative Evaluation Of FP32 And INT8 Quantization For Edge Device Real-Time Indian Sign Language Recognition
Author :
Siddharth Roy, Ravish KumarJourna Name:
International Journal of Science, Engineering and Technology Volume:
14 issue:2 Year:Volume-14-issue-2 Views : 234
Abstract:
The high memory and computational requirements of standard floating-point architectures make it difficult to deploy Deep Learning models on edge devices with limited resources. The Post-Training Quantization (PTQ) methods used with a MobileNetV2 architecture for real-time Indian Sign Language (ISL) recognition are compared in this paper. We show that the baseline 32-bit floating-point (FP32) model can be converted to an 8-bit integer (INT8) format, which significantly reduces the model footprint and improves inference latency without significantly degrading accuracy. The INT8 quantized model achieves a 72.4% reduction in memory size (from 9.52 MB to 2.63 MB) and a 31.7% increase in inference speed (from 14.40 ms to 9.83 ms per frame), according to experimental results on a 27-class ISL dataset. Importantly, compared to the FP32 baseline, the quantized model maintains a strong validation accuracy of 98.60%, with an accuracy decline of less than 1%. These results confirm that INT8 quantization is effective in enabling offline, high-framerate computer vision applications on low-power edge hardware.
APA:Siddharth Roy, Ravish Kumar. (Volume-14, Issue-2 -(Year-Volume-14-issue-2)). Comparative Evaluation Of FP32 And INT8 Quantization For Edge Device Real-Time Indian Sign Language Recognition. Retrieved from https://www.ijset.in/wp-content/uploads/IJSRET_V12_issue2_475.pdf
Chicago:Siddharth Roy, Ravish Kumar. "Comparative Evaluation Of FP32 And INT8 Quantization For Edge Device Real-Time Indian Sign Language Recognition" Example, Volume-14-issue-2-Year-Volume-14-issue-2-2348-4098. https://www.ijset.in/wp-content/uploads/IJSRET_V12_issue2_475.pdf.