Release AI-ModelZoo-3.2.0:

- Support of STEdgeAI Core v2.2.0 (STM32Cube.AI v10.2.0).
- Support of X-Linux-AI v6.1.0 support for MPU.
- New use cases added: StyleTransfer and FastDepth.
- New models added: Face Detection, available in the Object Detection use case, and Face Landmarks, available in the Pose Estimation use case.
- Architecture and codebase clean-up.


Signed-off-by: khaoula boutiche <[email protected]>

Author: KBOUSTM

README.md

@@ -10,7 +10,7 @@ projects.
 - A large collection of application-oriented models ready for re-training
 - Pre-trained models on reference datasets
 
-**Scripts to easily retrain, quantize, evaluate or benchmark any model from user datasets as well as application code examples automatically generated from user AI model can be found in the  [stm32ai-modelzoo-services GitHub](https://github.com/STMicroelectronics/stm32ai-modelzoo-services)** 
+**Scripts to easily retrain, quantize, evaluate or benchmark any model from user datasets as well as application code examples automatically generated from user AI model can be found in the  [stm32ai-modelzoo-services GitHub](https://github.com/STMicroelectronics/stm32ai-modelzoo-services)**
 
 
 These models can be useful for quick deployment if you are interested in the categories that they were trained. We also provide training scripts to do transfer learning or to train your own model from scratch on your custom dataset.
@@ -19,26 +19,36 @@ The performances on reference STM32 MCU, NPU and MPU are provided for float and
 
 ## What's new in releases :
 </details>
-<details open><summary><b>3.1:</b></summary>
+<details open><summary><b>3.2:</b></summary>
+
+* Support for **STEdgeAI Core v2.2.0** (STM32Cube.AI v10.2.0).
+* Support of **X-Linux-AI v6.1.0** support for MPU.
+* New use cases added: **StyleTransfer** and **FastDepth**.
+* New models added: **Face Detection**, available in the Object Detection use case, and **Face Landmarks**, available in the Pose Estimation use case.
+* Architecture and codebase clean-up.
+</details>
+
+</details>
+<details><summary><b>3.1:</b></summary>
 
 * Included additional models support (yolo_v11, st_yolo_x variants)
 </details>
 <details><summary><b>3.0:</b></summary>
 
 * Included additional models compatible with the [STM32N6570-DK](https://www.st.com/en/evaluation-tools/stm32n6570-dk) board.
 * Expanded models in all use cases.
-* Expanded use case support to include `Instance Segmentation` and `Speech Enhancement`.
+* Expanded use case support to include **Instance Segmentation** and **Speech Enhancement**.
 * Added `Pytorch` support through the speech enhancement Use Case.
 * Model Zoo hosted on <a href="#Hugging Face">Hugging Face</a>
 </details>
 <details><summary><b>2.1:</b></summary>
 
 * Included additional models compatible with the [STM32MP257F-EV1](https://www.st.com/en/evaluation-tools/stm32mp257f-ev1) board.
-* Expanded use case support to include `Pose Estimation` and `Semantic Segmentation`.
+* Expanded use case support to include **Pose Estimation** and **Semantic Segmentation**.
 </details>
 <details><summary><b>2.0:</b></summary>
 
-* An aligned and `uniform architecture` for all the use case
+* An aligned and **uniform architecture** for all the use case
 </details>
 
 
@@ -50,6 +60,8 @@ The performances on reference STM32 MCU, NPU and MPU are provided for float and
 | [Pose Estimation](./pose_estimation/README.md)   | Detects key points on some specific objects (people, hand, face, ...).     | [STM32MP257F-EV1](https://github.com/STMicroelectronics/stm32ai-modelzoo-services/blob/main/application_code/pose_estimation/STM32MP-LINUX/STM32MP2/README.md) <br> [STM32N6570-DK](https://www.st.com/en/development-tools/stm32n6-ai.html) <br> | <div align="center" style="width:480px; margin: left;">![plot](./doc/img/output_application_pe.JPG) |
 | [Semantic Segmentation](./semantic_segmentation/README.md)   | Associates a label to every pixel in an image to recognize a collection of pixels that form distinct categories.     | [STM32MP257F-EV1](https://github.com/STMicroelectronics/stm32ai-modelzoo-services/blob/main/application_code/STM32MP-LINUX/STM32MP2/README.md) <br> [STM32N6570-DK](https://www.st.com/en/development-tools/stm32n6-ai.html) <br> | <div align="center" style="width:480px; margin: left;">![plot](./doc/img/output_application_semseg.JPG) |
 | [Instance Segmentation](./instance_segmentation/README.md)   | Associates a label to every pixel in an image to recognize a collection of pixels that form distinct categories or instances of each category.     |  [STM32N6570-DK](https://www.st.com/en/development-tools/stm32n6-ai.html) <br> | <div align="center" style="width:480px; margin: left;">![plot](./doc/img/output_application_instseg.JPG) |
+| [Depth Estimation](./depth_estimation/README.md)   | Predict the distance to objects from an image as a pixel-wise depth map.     |  [STM32N6570-DK](https://www.st.com/en/development-tools/stm32n6-ai.html) <br>  | <div align="center" style="width:480px; margin: left;">![plot](./doc/img/output_application_de.JPG) |
+| [Neural Style Transfer](./neural_style_transfer/README.md)   | applies the artistic style of one image to the content of another image.     |  [STM32N6570-DK](https://www.st.com/en/development-tools/stm32n6-ai.html) <br>  | <div align="center" style="width:480px; margin: left;">![plot](./doc/img/output_application_nst.JPG) |
 | [Audio Event Detection](./audio_event_detection/README.md)   | Detection of a specific audio events.     | [B-U585I-IOT02A ThreadX](https://github.com/STMicroelectronics/stm32ai-modelzoo-services/blob/main/application_code/sensing_thread_x/STM32U5/README.md) <br> [B-U585I-IOT02A FreeRTOS](https://github.com/STMicroelectronics/stm32ai-modelzoo-services/blob/main/application_code/sensing_free_rtos/STM32U5/README.md) <br> [STM32N6570-DK](https://www.st.com/en/development-tools/stm32n6-ai.html) <br> | <div align="center" style="width:480px; margin: left;">![plot](./doc/img/output_application_aed.JPG) |
 | [Speech Enhancement](./speech_enhancement/README.md)   | Enhancement of the audio perception in a noisy environment.     |  [STM32N6570-DK](https://www.st.com/en/development-tools/stm32n6-ai.html) <br> | <div align="center" style="width:480px; margin: left;">![plot](./doc/img/output_application_se.JPG) |
 | [Human Activity Recognition](./human_activity_recognition/README.md)   | Recognizes various activities like walking, running, ...     |  [B-U585I-IOT02A](https://github.com/STMicroelectronics/stm32ai-modelzoo-services/blob/main/application_code/sensing_thread_x/STM32U5/README.md) <br> | <div align="center" style="width:480px; margin: left;">![plot](./doc/img/output_application_har.JPG) |
@@ -88,7 +100,7 @@ Once downloaded and installed, set up Git LFS for your user account by running t
 ```sh
 git lfs install
 ```
-You should see the message `Git LFS initialized.` if the command runs successfully. 
+You should see the message `Git LFS initialized.` if the command runs successfully.
 
 **NOTE:** If you do not see the message `Git LFS initialized.`, visit the [GitHub documentation page](https://docs.github.com/en/repositories/working-with-files/managing-large-files/installing-git-large-file-storage) for more details and support.
 

audio_event_detection/miniresnet/README.md

@@ -61,17 +61,17 @@ Measures are done with default STM32Cube.AI configuration with enabled input / o
 
 | Model             | Format | Resolution | Series  | Activation RAM (KiB) | Runtime RAM (KiB)| Weights Flash (KiB) | Code Flash (KiB) | Total RAM (KiB) | Total Flash (KiB)| STM32Cube.AI version  |
 |-------------------|--------|------------|---------|----------------|-------------|---------------|------------|-------------|-------------|-----------------------|
-| [MiniResNet 1stack ](ST_pretrainedmodel_public_dataset/esc10/miniresnet_1stacks_64x50_tl/miniresnet_1stacks_64x50_tl_int8.tflite) | int8 | 64x50x1 | B-U585I-IOT02A    | 59.89 | 5.38               |   123.6       |   56.9            | 65.27 | 180.5 | 10.0.0                 |
-| [MiniResNet 2stacks ](ST_pretrainedmodel_public_dataset/esc10/miniresnet_2stacks_64x50_tl/miniresnet_2stacks_64x50_tl_int8.tflite) | int8 | 64x50x1 | B-U585I-IOT02A    | 59.89 |   8.37      |   431.1           |   63.69    | 68.26 | 494.9 | 10.0.0                | 
+| [MiniResNet 1stack ](ST_pretrainedmodel_public_dataset/esc10/miniresnet_1stacks_64x50_tl/miniresnet_1stacks_64x50_tl_int8.tflite) | int8 | 64x50x1 | B-U585I-IOT02A    | 59.89 | 5.38               |   123.6       |   55.89            | 65.27 | 179.49 | 10.2.0                 |
+| [MiniResNet 2stacks ](ST_pretrainedmodel_public_dataset/esc10/miniresnet_2stacks_64x50_tl/miniresnet_2stacks_64x50_tl_int8.tflite) | int8 | 64x50x1 | B-U585I-IOT02A    | 59.89 |   8.37      |   431.1           |   	62.68    | 68.26 | 493.78 | 10.2.0                | 
 
 
 ### Reference inference time based on ESC-10 dataset
 
 
 | Model             | Format | Resolution | Board            | Execution Engine | Frequency   | Inference time (ms) | STM32Cube.AI version  |
 |-------------------|--------|------------|------------------|------------------|-------------|-----------------|-----------------------|
-| [MiniResNet 1stacks ](ST_pretrainedmodel_public_dataset/esc10/miniresnet_1stacks_64x50_tl/miniresnet_1stacks_64x50_tl_int8.tflite) | int8 | 64x50x1 | B-U585I-IOT02A | 1 CPU | 160 MHz | 92.25 | 10.0.0                 |
-| [MiniResNet 2stacks ](ST_pretrainedmodel_public_dataset/esc10/miniresnet_2stacks_64x50_tl/miniresnet_2stacks_64x50_tl_int8.tflite) | int8 | 64x50x1 | B-U585I-IOT02A | 1 CPU | 160 MHz | 142.69 | 10.0.0               |
+| [MiniResNet 1stacks ](ST_pretrainedmodel_public_dataset/esc10/miniresnet_1stacks_64x50_tl/miniresnet_1stacks_64x50_tl_int8.tflite) | int8 | 64x50x1 | B-U585I-IOT02A | 1 CPU | 160 MHz | 91.47 | 10.2.0                 |
+| [MiniResNet 2stacks ](ST_pretrainedmodel_public_dataset/esc10/miniresnet_2stacks_64x50_tl/miniresnet_2stacks_64x50_tl_int8.tflite) | int8 | 64x50x1 | B-U585I-IOT02A | 1 CPU | 160 MHz | 141.86 | 10.2.0               |
 
 
 ### Accuracy with ESC-10 dataset

audio_event_detection/miniresnet/ST_pretrainedmodel_public_dataset/esc10/miniresnet_1stacks_64x50_tl/miniresnet_1stacks_64x50_tl_config.yaml

@@ -135,11 +135,11 @@ prediction:
 
 tools:
   stedgeai:
-    version: 10.0.0
+    version: 10.2.0
     optimization: balanced
     on_cloud: True
-    path_to_stedgeai: C:/Users/<XXXXX>/STM32Cube/Repository/Packs/STMicroelectronics/X-CUBE-AI/<*.*.*>/Utilities/windows/stedgeai.exe
-  path_to_cubeIDE: C:/ST/STM32CubeIDE_1.17.0/STM32CubeIDE/stm32cubeide.exe
+    path_to_stedgeai: C:/ST/STEdgeAI/<x.y>/Utilities/windows/stedgeai.exe
+  path_to_cubeIDE: C:/ST/STM32CubeIDE_<*.*.*>/STM32CubeIDE/stm32cubeide.exe
 
 benchmarking:
   board: B-U585I-IOT02A

audio_event_detection/miniresnet/ST_pretrainedmodel_public_dataset/esc10/miniresnet_2stacks_64x50_tl/miniresnet_2stacks_64x50_tl_config.yaml

@@ -136,11 +136,11 @@ prediction:
 
 tools:
   stedgeai:
-    version: 10.0.0
+    version: 10.2.0
     optimization: balanced
     on_cloud: True
-    path_to_stedgeai: C:/Users/<XXXXX>/STM32Cube/Repository/Packs/STMicroelectronics/X-CUBE-AI/<*.*.*>/Utilities/windows/stedgeai.exe
-  path_to_cubeIDE: C:/ST/STM32CubeIDE_1.17.0/STM32CubeIDE/stm32cubeide.exe
+    path_to_stedgeai: C:/ST/STEdgeAI/<x.y>/Utilities/windows/stedgeai.exe
+  path_to_cubeIDE: C:/ST/STM32CubeIDE_<*.*.*>/STM32CubeIDE/stm32cubeide.exe
 
 benchmarking:
   board: B-U585I-IOT02A

audio_event_detection/miniresnetv2/README.md

@@ -63,17 +63,17 @@ It outputs embedding vectors of size 2048 for the 2 stacks version, and 3548 for
 
 | Model             | Format | Resolution | Series  | Activation RAM (KiB) | Runtime RAM (KiB) | Weights Flash (KiB) | Code Flash (KiB) | Total RAM (KiB)  | Total Flash (kB) | STM32Cube.AI version  |
 |-------------------|--------|------------|---------|----------------|-------------|---------------|------------|-------------|-------------|-----------------------|
-| [miniresnet v2 1stacks ](ST_pretrainedmodel_public_dataset/esc10/miniresnetv2_1stacks_64x50_tl/miniresnetv2_1stacks_64x50_tl_int8.tflite) | int8 | 64x50x1 | B-U585I-IOT02A    | 59.89               |   7.09       |   123.98            |   61.57      | 66.98 | 185.55 | 10.0.0                 |
-| [miniresnet v2 2stacks ](ST_pretrainedmodel_public_dataset/esc10/miniresnetv2_2stacks_64x50_tl/miniresnetv2_2stacks_64x50_tl_int8.tflite) | int8 | 64x50x1 | B-U585I-IOT02A    | 59.89                |   11.28        |   431.98            |   69.86      | 71.17 | 501.84 | 10.0.0                 |
+| [miniresnet v2 1stacks ](ST_pretrainedmodel_public_dataset/esc10/miniresnetv2_1stacks_64x50_tl/miniresnetv2_1stacks_64x50_tl_int8.tflite) | int8 | 64x50x1 | B-U585I-IOT02A    | 59.89               |   7.09       |   	123.98           |   60.56	9      | 66.98| 184.54 | 10.2.0                 |
+| [miniresnet v2 2stacks ](ST_pretrainedmodel_public_dataset/esc10/miniresnetv2_2stacks_64x50_tl/miniresnetv2_2stacks_64x50_tl_int8.tflite) | int8 | 64x50x1 | B-U585I-IOT02A    | 59.89                |   	11.29        |   431.98           |   68.85      | 71.18 | 	500.83 | 10.2.0                 |
 
 
 ### Reference inference time based on ESC-10 dataset
 
 
 | Model             | Format | Resolution | Board            | Execution Engine |  Frequency   | Inference time (ms) | STM32Cube.AI version  |
 |-------------------|--------|------------|------------------|------------------|--------------|-------|-----------------------|
-| [miniresnet v2 1stacks ](ST_pretrainedmodel_public_dataset/esc10/miniresnetv2_1stacks_64x50_tl/miniresnetv2_1stacks_64x50_tl_int8.tflite) | int8 | 64x50x1 | B-U585I-IOT02A |  1 CPU | 160 | 188.36 | 10.0.0                |
-| [miniresnet v2 2stacks ](ST_pretrainedmodel_public_dataset/esc10/miniresnetv2_2stacks_64x50_tl/miniresnetv2_2stacks_64x50_tl_int8.tflite) | int8 | 64x50x1 | B-U585I-IOT02A |  1 CPU | 160 | 308.81 | 10.0.0                 |
+| [miniresnet v2 1stacks ](ST_pretrainedmodel_public_dataset/esc10/miniresnetv2_1stacks_64x50_tl/miniresnetv2_1stacks_64x50_tl_int8.tflite) | int8 | 64x50x1 | B-U585I-IOT02A |  1 CPU | 160 | 	187.21 | 10.2.0                |
+| [miniresnet v2 2stacks ](ST_pretrainedmodel_public_dataset/esc10/miniresnetv2_2stacks_64x50_tl/miniresnetv2_2stacks_64x50_tl_int8.tflite) | int8 | 64x50x1 | B-U585I-IOT02A |  1 CPU | 160 | 307.22 | 10.2.0                 |
 
 
 ### Accuracy with ESC-10 dataset

audio_event_detection/miniresnetv2/ST_pretrainedmodel_public_dataset/esc10/miniresnetv2_1stacks_64x50_tl/miniresnetv2_1stacks_64x50_tl_config.yaml

@@ -135,11 +135,11 @@ prediction:
 
 tools:
   stedgeai:
-    version: 10.0.0
+    version: 10.2.0
     optimization: balanced
     on_cloud: True
-    path_to_stedgeai: C:/Users/<XXXXX>/STM32Cube/Repository/Packs/STMicroelectronics/X-CUBE-AI/<*.*.*>/Utilities/windows/stedgeai.exe
-  path_to_cubeIDE: C:/ST/STM32CubeIDE_1.17.0/STM32CubeIDE/stm32cubeide.exe
+    path_to_stedgeai: C:/ST/STEdgeAI/<x.y>/Utilities/windows/stedgeai.exe
+  path_to_cubeIDE: C:/ST/STM32CubeIDE_<*.*.*>/STM32CubeIDE/stm32cubeide.exe
 
 benchmarking:
   board: B-U585I-IOT02A

audio_event_detection/miniresnetv2/ST_pretrainedmodel_public_dataset/esc10/miniresnetv2_2stacks_64x50_tl/miniresnetv2_2stacks_64x50_tl_config.yaml

@@ -135,11 +135,11 @@ prediction:
 
 tools:
   stedgeai:
-    version: 10.0.0
+    version: 10.2.0
     optimization: balanced
     on_cloud: True
-    path_to_stedgeai: C:/Users/<XXXXX>/STM32Cube/Repository/Packs/STMicroelectronics/X-CUBE-AI/<*.*.*>/Utilities/windows/stedgeai.exe
-  path_to_cubeIDE: C:/ST/STM32CubeIDE_1.17.0/STM32CubeIDE/stm32cubeide.exe
+    path_to_stedgeai: C:/ST/STEdgeAI/<x.y>/Utilities/windows/stedgeai.exe
+  path_to_cubeIDE: C:/ST/STM32CubeIDE_<*.*.*>/STM32CubeIDE/stm32cubeide.exe
 
 benchmarking:
   board: B-U585I-IOT02A

audio_event_detection/yamnet/README.md

@@ -79,27 +79,27 @@ For Yamnet-1024
 ### Reference **NPU** memory footprint based on ESC-10 dataset
 |Model      | Dataset       | Format   | Resolution | Series    | Internal RAM (KiB) | External RAM (KiB) | Weights Flash (KiB) | STM32Cube.AI version | STEdgeAI Core version |
 |----------|------------------|--------|-------------|------------------|------------------|---------------------|-------|----------------------|-------------------------|
-| [Yamnet 256](ST_pretrainedmodel_public_dataset/esc10/yamnet_256_64x96_tl/yamnet_256_64x96_tl_int8.tflite)  | esc-10 | Int8 | 64x96x1 | STM32N6 |                                                144 | 0.0 | 176.59 | 10.0.0 | 2.0.0 |
-| [Yamnet 1024](ST_pretrainedmodel_public_dataset/esc10/yamnet_1024_64x96_tl/yamnet_1024_64x96_tl_qdq_int8.onnx) | esc-10 | Int8 | 64x96x1 | STM32N6 |                                       144 | 0.0 | 3497.24 | 10.0.0 | 2.0.0 |
+| [Yamnet 256](ST_pretrainedmodel_public_dataset/esc10/yamnet_256_64x96_tl/yamnet_256_64x96_tl_int8.tflite)  | esc-10 | Int8 | 64x96x1 | STM32N6 |                                                144 | 0.0 | 167.7 | 10.2.0 | 2.2.0 |
+| [Yamnet 1024](ST_pretrainedmodel_public_dataset/esc10/yamnet_1024_64x96_tl/yamnet_1024_64x96_tl_qdq_int8.onnx) | esc-10 | Int8 | 64x96x1 | STM32N6 |                                       144 | 0.0 | 	3450.58 | 10.2.0 | 2.2.0 |
 
 ### Reference **NPU**  inference time  based on ESC-10 dataset
 | Model  | Dataset          | Format | Resolution  | Board            | Execution Engine | Inference time (ms) | Inf / sec   | STM32Cube.AI version  |  STEdgeAI Core version |
 |--------|------------------|--------|-------------|------------------|------------------|---------------------|-------|----------------------|-------------------------|
-| [Yamnet 256](ST_pretrainedmodel_public_dataset/esc10/yamnet_256_64x96_tl/yamnet_256_64x96_tl_int8.tflite) | esc-10      | Int8     | 64x96x1  | STM32N6570-DK   |   NPU/MCU      |              1.07      |   934.58           |       10.0.0        |     2.0.0   |
-| [Yamnet 1024](ST_pretrainedmodel_public_dataset/esc10/yamnet_1024_64x96_tl/yamnet_1024_64x96_tl_qdq_int8.onnx) | esc-10      | Int8     | 64x96x1  | STM32N6570-DK   |   NPU/MCU      |        9.88      |   101.21           |       10.0.0        |     2.0.0   |
+| [Yamnet 256](ST_pretrainedmodel_public_dataset/esc10/yamnet_256_64x96_tl/yamnet_256_64x96_tl_int8.tflite) | esc-10      | Int8     | 64x96x1  | STM32N6570-DK   |   NPU/MCU      |              1.05      |   952.38           |       10.2.0        |     2.2.0   |
+| [Yamnet 1024](ST_pretrainedmodel_public_dataset/esc10/yamnet_1024_64x96_tl/yamnet_1024_64x96_tl_qdq_int8.onnx) | esc-10      | Int8     | 64x96x1  | STM32N6570-DK   |   NPU/MCU      |        9.88      |   101.21           |       10.2.0        |     2.2.0   |
 
 
 ### Reference **MCU** memory footprint based on ESC-10 dataset
 | Model             | Format | Resolution | Series  | Activation RAM (kB) | Runtime RAM (kB) | Weights Flash (kB) | Code Flash (kB) | Total RAM (kB)  | Total Flash (kB) | STM32Cube.AI version  |
 |-------------------|--------|------------|---------|----------------|-------------|---------------|------------|-------------|-------------|-----------------------|
-|[Yamnet 256](ST_pretrainedmodel_public_dataset/esc10/yamnet_256_64x96_tl/yamnet_256_64x96_tl_int8.tflite) | Int8 | 64x96x1 | B-U585I-IOT02A    | 109.57               |   7.61        |   135.91           |   57.74   | 117.18 | 193.65 | 10.0.0 |
-|[Yamnet 1024](ST_pretrainedmodel_public_dataset/esc10/yamnet_1024_64x96_tl/yamnet_1024_64x96_tl_qdq_int8.onnx) | Int8 | 64x96x1 | STM32N6 | 108.59               |   35.41        |   3162.66           |  334.30   | 144.0 | 3496.96 | 10.0.0 |
+|[Yamnet 256](ST_pretrainedmodel_public_dataset/esc10/yamnet_256_64x96_tl/yamnet_256_64x96_tl_int8.tflite) | Int8 | 64x96x1 | B-U585I-IOT02A    | 109.57               |   7.61        |   135.91           |   56.67  | 117.18 | 192.58 | 10.2.0 |
+|[Yamnet 1024](ST_pretrainedmodel_public_dataset/esc10/yamnet_1024_64x96_tl/yamnet_1024_64x96_tl_qdq_int8.onnx) | Int8 | 64x96x1 | STM32N6 | 144.0               |   	1.67        |   3450.58          |  252.48  | 145.67 | 3703.06 | 10.2.0 |
 
 ### Reference inference time based on ESC-10 dataset
 | Model             | Format | Resolution | Board            | Execution Engine | Frequency    | Inference time  | STM32Cube.AI version  |
 |-------------------|--------|------------|------------------|------------------|--------------|-----------------|-----------------------|
-| [Yamnet 256](ST_pretrainedmodel_public_dataset/esc10/yamnet_256_64x96_tl/yamnet_256_64x96_tl_int8.tflite) | Int8 | 64x96x1 | B-U585I-IOT02A | 1 CPU | 160 MHz | 281.95 ms | 10.0.0    
-|[Yamnet 1024](ST_pretrainedmodel_public_dataset/esc10/yamnet_1024_64x96_tl/yamnet_1024_64x96_tl_qdq_int8.onnx) | Int8 | 64x96x1 | STM32N6 | 1 CPU + 1 NPU | 800MhZ/1000MhZ | 11.949 ms | 10.0.0
+| [Yamnet 256](ST_pretrainedmodel_public_dataset/esc10/yamnet_256_64x96_tl/yamnet_256_64x96_tl_int8.tflite) | Int8 | 64x96x1 | B-U585I-IOT02A | 1 CPU | 160 MHz | 279.62 ms | 10.2.0    
+|[Yamnet 1024](ST_pretrainedmodel_public_dataset/esc10/yamnet_1024_64x96_tl/yamnet_1024_64x96_tl_qdq_int8.onnx) | Int8 | 64x96x1 | STM32N6 | 1 CPU + 1 NPU | 800MhZ/1000MhZ | 9.88 ms | 10.2.0
 
 
 ### Accuracy with ESC-10 dataset