Hugging Face's logo

STMicroelectronics
/
yolov11n_pose

Keypoint Detection
Model card Files
xet
Community
FBAGSTM commited on
Commit
9fc22db
·
verified ·
1 Parent(s): bdb40fd

Release AI-ModelZoo-4.0.0

Browse files
Files changed (1) hide show
  1. README.md +9 -8
README.md CHANGED
@@ -48,7 +48,7 @@ With an image resolution of NxM with K keypoints to detect :
48
  | STM32U5 | [] | [] |
49
  | STM32H7 | [] | [] |
50
  | STM32MP1 | [] | [] |
51
- | STM32MP2 | [] | [] |
52
  | STM32N6 | [x] | [x] |
53
 
54
 
@@ -64,16 +64,17 @@ Please also check the folder's README.md file for detailed information about its
64
  https://github.com/stm32-hotspot/ultralytics/blob/main/examples/YOLOv8-STEdgeAI/README.md
65
 
66
  ### Reference **NPU** memory footprint based on COCO Person dataset (see Accuracy for details on dataset)
67
- |Model | Dataset | Format | Resolution | Series | Internal RAM (KiB) | External RAM (KiB) | Weights Flash (KiB)| STM32Cube.AI version | STEdgeAI Core version |
68
- |----------|------------------|--------|-------------|------------------|------------------|---------------------|-------|----------------------|-------------------------|
69
- | [YOLOv8n pose per channel](https://github.com/stm32-hotspot/ultralytics/blob/main/examples/YOLOv8-STEdgeAI/stedgeai_models/pose_estimation/yolo11/yolo11n_256_quant_pc_uf_pose_coco-st.tflite) | COCO-Person | Int8 | 256x256x3 | STM32N6 | 742.95 | 0.0 | 3543.04 | 10.2.0 | 2.2.0 |
 
70
 
71
 
72
  ### Reference **NPU** inference time based on COCO Person dataset (see Accuracy for details on dataset)
73
- | Model | Dataset | Format | Resolution | Board | Execution Engine | Inference time (ms) | Inf / sec | STM32Cube.AI version | STEdgeAI Core version |
74
- |--------|------------------|--------|-------------|------------------|------------------|---------------------|-------|----------------------|-------------------------|
75
- | [YOLOv8n pose per channel](https://github.com/stm32-hotspot/ultralytics/blob/main/examples/YOLOv8-STEdgeAI/stedgeai_models/pose_estimation/yolo11/yolo11n_256_quant_pc_uf_pose_coco-st.tflite) | COCO-Person | Int8 | 256x256x3 | STM32N6570-DK | NPU/MCU | 37.39 | 26.74 | 10.2.0 | 2.2.0 |
76
-
77
 
78
 
79
  ## Integration in a simple example and other services support:
 
48
  | STM32U5 | [] | [] |
49
  | STM32H7 | [] | [] |
50
  | STM32MP1 | [] | [] |
51
+ | STM32MP2 | [] | [] |
52
  | STM32N6 | [x] | [x] |
53
 
54
 
 
64
  https://github.com/stm32-hotspot/ultralytics/blob/main/examples/YOLOv8-STEdgeAI/README.md
65
 
66
  ### Reference **NPU** memory footprint based on COCO Person dataset (see Accuracy for details on dataset)
67
+ |Model | Dataset | Format | Resolution | Series | Internal RAM (KiB) | External RAM (KiB) | Weights Flash (KiB) | STEdgeAI Core version |
68
+ |----------|------------------|--------|-------------|------------------|------------------|---------------------|-------|-------------------------|
69
+ | [YOLOv11n pose per channel](https://github.com/stm32-hotspot/ultralytics/blob/main/examples/YOLOv8-STEdgeAI/stedgeai_models/pose_estimation/yolo11/yolo11n_256_quant_pc_uf_pose_coco-st.tflite) | COCO-Person | Int8 | 256x256x3 | STM32N6 | 740.25 | 0.0 | 2818.16 | 3.0.0 |
70
+ | [YOLOv11n pose per channel](https://github.com/stm32-hotspot/ultralytics/blob/main/examples/YOLOv8-STEdgeAI/stedgeai_models/pose_estimation/yolo11/yolo11n_320_quant_pc_uf_pose_coco-st.tflite) | COCO-Person | Int8 | 320x320x3 | STM32N6 | 1840.85 | 0.0 | 2851.33 | 3.0.0 |
71
 
72
 
73
  ### Reference **NPU** inference time based on COCO Person dataset (see Accuracy for details on dataset)
74
+ | Model | Dataset | Format | Resolution | Board | Execution Engine | Inference time (ms) | Inf / sec | STEdgeAI Core version |
75
+ |--------|------------------|--------|-------------|------------------|------------------|---------------------|-------|-------------------------|
76
+ | [YOLOv11n pose per channel](https://github.com/stm32-hotspot/ultralytics/blob/main/examples/YOLOv8-STEdgeAI/stedgeai_models/pose_estimation/yolo11/yolo11n_256_quant_pc_uf_pose_coco-st.tflite) | COCO-Person | Int8 | 256x256x3 | STM32N6570-DK | NPU/MCU | 34.32 | 29.14 | 3.0.0 |
77
+ | [YOLOv11n pose per channel](https://github.com/stm32-hotspot/ultralytics/blob/main/examples/YOLOv8-STEdgeAI/stedgeai_models/pose_estimation/yolo11/yolo11n_320_quant_pc_uf_pose_coco-st.tflite) | COCO-Person | Int8 | 320x320x3 | STM32N6570-DK | NPU/MCU | 56.15 | 17.81 | 3.0.0 |
78
 
79
 
80
  ## Integration in a simple example and other services support: