Remove warning on non-calibrated INT8 model's poentially bad accuracy
Browse files
README.md
CHANGED
|
@@ -3,14 +3,15 @@ pipeline_tag: object-detection
|
|
| 3 |
datasets:
|
| 4 |
- Mai0313/coco-pose-2017
|
| 5 |
tags:
|
| 6 |
-
- TensorRT
|
| 7 |
- Pose Estimation
|
| 8 |
- YOLO-NAS-Pose
|
| 9 |
- Jetson Orin
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
We offer a TensorRT model in various precisions including int8, fp16, fp32, and mixed, converted from Deci-AI's [YOLO-NAS-Pose](https://github.com/Deci-AI/super-gradients/blob/master/YOLONAS-POSE.md) pre-trained weights in PyTorch.
|
| 13 |
-
This model is compatible with Jetson Orin Nano
|
| 14 |
|
| 15 |
~~Note that all quantization that has been introduced in the conversion is purely static, meaning that the corresponding model has potentillay bad accuracy compared to the original one.~~
|
| 16 |
|
|
|
|
| 3 |
datasets:
|
| 4 |
- Mai0313/coco-pose-2017
|
| 5 |
tags:
|
|
|
|
| 6 |
- Pose Estimation
|
| 7 |
- YOLO-NAS-Pose
|
| 8 |
- Jetson Orin
|
| 9 |
+
- JetPack 5.1.1
|
| 10 |
+
- TensorRT 8.5.2
|
| 11 |
---
|
| 12 |
|
| 13 |
We offer a TensorRT model in various precisions including int8, fp16, fp32, and mixed, converted from Deci-AI's [YOLO-NAS-Pose](https://github.com/Deci-AI/super-gradients/blob/master/YOLONAS-POSE.md) pre-trained weights in PyTorch.
|
| 14 |
+
This (TensorRT) model is compatible with JetPack 5.1.1, benchmarked and tested on Jetson Orin Nano Deveoper Kit.
|
| 15 |
|
| 16 |
~~Note that all quantization that has been introduced in the conversion is purely static, meaning that the corresponding model has potentillay bad accuracy compared to the original one.~~
|
| 17 |
|