Downloads · 30 days
0
yolov7-pose-qat
LouisMM/yolov7-pose-qat
yolov7-pose-qat is a machine learning model from LouisMM. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Benchmark, comparing CPU/iGPU with 3 different processors:
Access
Public
Updated Sep 29, 2023
Repo size
598 MB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.bin598 MB · 98%
At a glance
- Access
- Public
- Created
- Sep 19, 2023
- Updated
- Sep 29, 2023
- SHA
- acd01664
Model card
From the Hugging Face model README
Yolov7-pose Benchmark results
Benchmark, comparing CPU/iGPU with 3 different processors:
- i5-1250pe (alder lake)
- i5-1145G7E (tiger lake)
- i7-1185G7E (tiger lake)
3 different models:
- FP16
- Partial QAT (model is quantized but the head is preserved for accuracy)
- int8 QAT (model is fully quantized)
| Device - Model | Precision | Average Latency (ms) | FPS |
|---|---|---|---|
| i5-1250pe-CPU | int8 QAT | 11.63 | 85.10 |
| i7-1185G7E CPU | int8 QAT | 13.36 | 74.50 |
| i7-1185G7E iGPU | Partial QAT | 13.51 | 73.32 |
| i7-1185G7E iGPU | int8 QAT | 13.66 | 72.53 |
| i5-1250pe-CPU | Partial QAT | 14.14 | 68.75 |
| i5-1145G7E CPU | int8 QAT | 16.32 | 61.01 |
| i7-1185G7E CPU | Partial QAT | 17.30 | 60.39 |
| i7-1185G7E iGPU | FP16 | 17.52 | 56.63 |
| i5-1145G7E iGPU | Partial QAT | 17.91 | 55.78 |
| i5-1145G7E iGPU | int8 QAT | 17.95 | 55.66 |
| i5-1250pe-iGPU | Partial QAT | 18.99 | 51.04 |
| i5-1250pe-iGPU | int8 QAT | 20.12 | 49.29 |
| i5-1145G7E CPU | Partial QAT | 20.28 | 49.14 |
| i5-1250pe-iGPU | FP16 | 21.25 | 46.71 |
| i5-1145G7E iGPU | FP16 | 23.86 | 42.73 |
| i7-1185G7E CPU | FP16 | 37.03 | 26.96 |
| i5-1250pe-CPU | FP16 | 37.83 | 26.38 |
| i5-1145G7E CPU | FP16 | 44.27 | 22.56 |
- Created
- Sep 19, 2023
- Updated
- Sep 29, 2023