Add benchmark graph
Browse files
README.md
CHANGED
@@ -52,3 +52,5 @@ We offer a TensorRT model in various precisions including int8, fp16, fp32, and
|
|
52 |
| yolo_nas_pose_s_fp32.onnx.int8.engine | FP32 | FP32+INT8 | 88.0719 qps |
|
53 |
| yolo_nas_pose_s_int8.onnx.best.engine | INT8 | FP32+FP16+INT8 | 80.8271 qps |
|
54 |
| yolo_nas_pose_s_int8.onnx.int8.engine | INT8 | FP32+INT8 | 74.2658 qps |
|
|
|
|
|
|
52 |
| yolo_nas_pose_s_fp32.onnx.int8.engine | FP32 | FP32+INT8 | 88.0719 qps |
|
53 |
| yolo_nas_pose_s_int8.onnx.best.engine | INT8 | FP32+FP16+INT8 | 80.8271 qps |
|
54 |
| yolo_nas_pose_s_int8.onnx.int8.engine | INT8 | FP32+INT8 | 74.2658 qps |
|
55 |
+
|
56 |
+
![alt text](benchmark.png "Benchmark")
|