Hugging Face's logo

STMicroelectronics
/
hand_landmarks

Keypoint Detection
Model card Files Community
FBAGSTM commited on
Commit
cbcf9c2
·
verified ·
1 Parent(s): 34a86bf

Update ST Model Zoo

Browse files
Files changed (1) hide show
  1. README.md +3 -7
README.md CHANGED
@@ -1,8 +1,3 @@
1
- ---
2
- license: apache-2.0
3
- license_name: sla0044
4
- pipeline_tag: keypoint-detection
5
- ---
6
  # Hand landmarks quantized
7
 
8
  ## **Use case** : `Pose estimation`
@@ -58,9 +53,10 @@ Measures are done with default STM32Cube.AI configuration with enabled input / o
58
  ### Reference **NPU** memory footprint based on COCO Person dataset (see Accuracy for details on dataset)
59
  |Model | Dataset | Format | Resolution | Series | Internal RAM (KiB) | External RAM (KiB) | Weights Flash (KiB) | STM32Cube.AI version | STEdgeAI Core version |
60
  |----------|------------------|--------|-------------|------------------|------------------|---------------------|-------|----------------------|-------------------------|
61
- | [hand_landmarks](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/pose_estimation/hand_landmarks/Public_pretrainedmodel_custom_dataset/custom_dataset_hands_21kpts/hand_landmarks_full_224_int8_pc.tflite) | COCO-Person | Int8 | 224x224x3 | STM32N6 | 1739.5 | 0.0 | 3283.38 | 10.0.0 | 2.0.0 |
62
 
63
  ### Reference **NPU** inference time based on COCO Person dataset (see Accuracy for details on dataset)
64
  | Model | Dataset | Format | Resolution | Board | Execution Engine | Inference time (ms) | Inf / sec | STM32Cube.AI version | STEdgeAI Core version |
65
  |--------|------------------|--------|-------------|------------------|------------------|---------------------|-------|----------------------|-------------------------|
66
- | [hand_landmarks](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/pose_estimation/hand_landmarks/Public_pretrainedmodel_custom_dataset/custom_dataset_hands_21kpts/hand_landmarks_full_224_int8_pc.tflite) | custom_dataset_hands_21kpts | Int8 | 224x224x3 | STM32N6570-DK | NPU/MCU | 20.75 | 48.19 | 10.0.0 | 2.0.0 |
 
 
 
 
 
 
 
1
  # Hand landmarks quantized
2
 
3
  ## **Use case** : `Pose estimation`
 
53
  ### Reference **NPU** memory footprint based on COCO Person dataset (see Accuracy for details on dataset)
54
  |Model | Dataset | Format | Resolution | Series | Internal RAM (KiB) | External RAM (KiB) | Weights Flash (KiB) | STM32Cube.AI version | STEdgeAI Core version |
55
  |----------|------------------|--------|-------------|------------------|------------------|---------------------|-------|----------------------|-------------------------|
56
+ | [hand_landmarks](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/pose_estimation/hand_landmarks/Public_pretrainedmodel_custom_dataset/custom_dataset_hands_21kpts/hand_landmarks_full_224_int8_pc.tflite) | COCO-Person | Int8 | 224x224x3 | STM32N6 | 1739.5 | 0.0 | 3283.38 | 10.2.0 | 2.2.0 |
57
 
58
  ### Reference **NPU** inference time based on COCO Person dataset (see Accuracy for details on dataset)
59
  | Model | Dataset | Format | Resolution | Board | Execution Engine | Inference time (ms) | Inf / sec | STM32Cube.AI version | STEdgeAI Core version |
60
  |--------|------------------|--------|-------------|------------------|------------------|---------------------|-------|----------------------|-------------------------|
61
+ | [hand_landmarks](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/pose_estimation/hand_landmarks/Public_pretrainedmodel_custom_dataset/custom_dataset_hands_21kpts/hand_landmarks_full_224_int8_pc.tflite) | custom_dataset_hands_21kpts | Int8 | 224x224x3 | STM32N6570-DK | NPU/MCU | 20.75 | 48.19 | 10.2.0 | 2.2.0 |
62
+