Hugging Face's logo

STMicroelectronics
/
IGN-HAR-model

Model card Files Community
FBAGSTM commited on
Commit
510c488
·
verified ·
1 Parent(s): 69f07d8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -8
README.md CHANGED
@@ -2,7 +2,7 @@
2
  license: other
3
  license_name: sla0044
4
  license_link: >-
5
- https://github.com/STMicroelectronics/stm32ai-modelzoo/human_activity_recognition/ign/ST_pretrainedmodel_public_dataset/LICENSE.md
6
  ---
7
  # IGN HAR model
8
 
@@ -62,8 +62,8 @@ Reference memory footprint and inference times for IGN models are given in the t
62
 
63
  | Model | Format | Input Shape | Series | Activation RAM (KiB) | Runtime RAM (KiB) | Weights Flash (KiB) | Code Flash (KiB) | Total RAM (KiB)| Total Flash (KiB) | Inference Time (msec) | STM32Cube.AI version |
64
  |:-----------------------------------------------------------------------------:|:---------:|:-----------:|:-------:|:--------------------:|:-----------------:|:-------------------:|:----------------:|:--------------:|:-----------------:|:---------------------:|:---------------------:|
65
- | [IGN wl 24](https://github.com/STMicroelectronics/stm32ai-modelzoo/human_activity_recognition/ign/ST_pretrainedmodel_public_dataset/WISDM/ign_wl_24/ign_wl_24.h5) | FLOAT32 | 24 x 3 x 1 | STM32U5 | 2.03 | 1.91 | 11.97 | 13.61 | 3.94 | 25.58 | 2.25 | 10.0.0 |
66
- | [IGN wl 48](https://github.com/STMicroelectronics/stm32ai-modelzoo/human_activity_recognition/ign/ST_pretrainedmodel_public_dataset/WISDM/ign_wl_48/ign_wl_48.h5) | FLOAT32 | 48 x 3 x 1 | STM32U5 | 4.56 | 1.91 | 38.97 | 13.61 | 6.47 | 52.58 | 8.17 | 10.0.0 |
67
 
68
 
69
 
@@ -76,12 +76,12 @@ Dataset details: A custom dataset and not publically available, Number of classe
76
 
77
  | Model | Format | Resolution | Accuracy (%)|
78
  |:--------------------------------------------------------------------------------------------:|:------:|:----------:|:-----------:|
79
- | [IGN wl 24](https://github.com/STMicroelectronics/stm32ai-modelzoo/human_activity_recognition/ign/ST_pretrainedmodel_custom_dataset/mobility_v1/ign_wl_24/ign_wl_24.h5) | FLOAT32| 24 x 3 x 1 | 94.64 |
80
- | [IGN wl 48](https://github.com/STMicroelectronics/stm32ai-modelzoo/human_activity_recognition/ign/ST_pretrainedmodel_custom_dataset/mobility_v1/ign_wl_48/ign_wl_48.h5) | FLOAT32| 48 x 3 x 1 | 95.01 |
81
 
82
  Confusion matrix for IGN wl 24 with Float32 weights for mobility_v1 dataset is given below.
83
 
84
- ![plot](https://github.com/STMicroelectronics/stm32ai-modelzoo/human_activity_recognition/ign/doc/img/mobility_v1_ign_wl_24_confusion_matrix.png)
85
 
86
 
87
  ### Accuracy with WISDM dataset
@@ -91,8 +91,8 @@ Dataset details: [link](([WISDM]("https://www.cis.fordham.edu/wisdm/dataset.php"
91
 
92
  | Model | Format | Resolution | Accuracy (%) |
93
  |:-------------------------------------------------------------------------------------:|:-------:|:----------:|:-------------:|
94
- | [IGN wl 24](https://github.com/STMicroelectronics/stm32ai-modelzoo/human_activity_recognition/ign/ST_pretrainedmodel_public_dataset/WISDM/ign_wl_24/ign_wl_24.h5) | FLOAT32 | 24 x 3 x 1 | 91.7 |
95
- | [IGN wl 48](https://github.com/STMicroelectronics/stm32ai-modelzoo/human_activity_recognition/ign/ST_pretrainedmodel_public_dataset/WISDM/ign_wl_48/ign_wl_48.h5) | FLOAT32 | 48 x 3 x 1 | 93.67 |
96
 
97
 
98
  ## Retraining and Integration in a simple example:
 
2
  license: other
3
  license_name: sla0044
4
  license_link: >-
5
+ https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/human_activity_recognition/ign/ST_pretrainedmodel_public_dataset/LICENSE.md
6
  ---
7
  # IGN HAR model
8
 
 
62
 
63
  | Model | Format | Input Shape | Series | Activation RAM (KiB) | Runtime RAM (KiB) | Weights Flash (KiB) | Code Flash (KiB) | Total RAM (KiB)| Total Flash (KiB) | Inference Time (msec) | STM32Cube.AI version |
64
  |:-----------------------------------------------------------------------------:|:---------:|:-----------:|:-------:|:--------------------:|:-----------------:|:-------------------:|:----------------:|:--------------:|:-----------------:|:---------------------:|:---------------------:|
65
+ | [IGN wl 24](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/human_activity_recognition/ign/ST_pretrainedmodel_public_dataset/WISDM/ign_wl_24/ign_wl_24.h5) | FLOAT32 | 24 x 3 x 1 | STM32U5 | 2.03 | 1.91 | 11.97 | 13.61 | 3.94 | 25.58 | 2.25 | 10.0.0 |
66
+ | [IGN wl 48](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/human_activity_recognition/ign/ST_pretrainedmodel_public_dataset/WISDM/ign_wl_48/ign_wl_48.h5) | FLOAT32 | 48 x 3 x 1 | STM32U5 | 4.56 | 1.91 | 38.97 | 13.61 | 6.47 | 52.58 | 8.17 | 10.0.0 |
67
 
68
 
69
 
 
76
 
77
  | Model | Format | Resolution | Accuracy (%)|
78
  |:--------------------------------------------------------------------------------------------:|:------:|:----------:|:-----------:|
79
+ | [IGN wl 24](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/human_activity_recognition/ign/ST_pretrainedmodel_custom_dataset/mobility_v1/ign_wl_24/ign_wl_24.h5) | FLOAT32| 24 x 3 x 1 | 94.64 |
80
+ | [IGN wl 48](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/human_activity_recognition/ign/ST_pretrainedmodel_custom_dataset/mobility_v1/ign_wl_48/ign_wl_48.h5) | FLOAT32| 48 x 3 x 1 | 95.01 |
81
 
82
  Confusion matrix for IGN wl 24 with Float32 weights for mobility_v1 dataset is given below.
83
 
84
+ ![plot](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/human_activity_recognition/ign/doc/img/mobility_v1_ign_wl_24_confusion_matrix.png)
85
 
86
 
87
  ### Accuracy with WISDM dataset
 
91
 
92
  | Model | Format | Resolution | Accuracy (%) |
93
  |:-------------------------------------------------------------------------------------:|:-------:|:----------:|:-------------:|
94
+ | [IGN wl 24](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/human_activity_recognition/ign/ST_pretrainedmodel_public_dataset/WISDM/ign_wl_24/ign_wl_24.h5) | FLOAT32 | 24 x 3 x 1 | 91.7 |
95
+ | [IGN wl 48](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/human_activity_recognition/ign/ST_pretrainedmodel_public_dataset/WISDM/ign_wl_48/ign_wl_48.h5) | FLOAT32 | 48 x 3 x 1 | 93.67 |
96
 
97
 
98
  ## Retraining and Integration in a simple example: