Updates:

- Enable logging trials in ClearML.
- Correct some typos.


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

Author: KBOUSTM

README.md

@@ -138,7 +138,7 @@ Object detection is used to detect, locate and estimate the occurrences probabil
 | [ST Yolo LC v1](https://github.com/STMicroelectronics/stm32ai-modelzoo/blob/master/object_detection/st_yolo_lc_v1/README.md)   |  192x192x3<br> 224x224x3<br> 256x256x3<br>  | Full OD Services      | [STM32H747I-DISCO](application_code/object_detection/STM32H7/Application/STM32H747I-DISCO) with B-CAMS-OMV camera daughter board<br>  |
 | [Tiny Yolo v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/blob/master/object_detection/tiny_yolo_v2/README.md)   |  224x224x3<br> 416x416x3<br>  | Full OD Services      | [STM32N6570-DK](https://www.st.com/en/development-tools/stm32n6-ai.html)<br>     |
 | [ST Yolo X](https://github.com/STMicroelectronics/stm32ai-modelzoo/blob/master/object_detection/st_yolo_x/README.md)   |  256x256x3<br> 416x416x3<br>  | Full OD Services      | [STM32N6570-DK](https://www.st.com/en/development-tools/stm32n6-ai.html)<br>     |
-| [Yolo v8](https://github.com/stm32-hotspot/ultralytics/tree/main/examples/YOLOv8-STEdgeAI/stedgeai_models/object_detection)   |  192x192x3<br> 256x256x3<br> 320x320x3<br> 416x416x3<br>  | Evaluation / Benchmarking / Prediction / Deployment    | [STM32N6570-DK](https://www.st.com/en/development-tools/stm32n6-ai.html)<br>     |
+| [Yolo v8](https://github.com/stm32-hotspot/ultralytics/tree/main/examples/YOLOv8-STEdgeAI/stedgeai_models/object_detection) <br> Yolo v5u  |  192x192x3<br> 256x256x3<br> 320x320x3<br> 416x416x3<br>  | Evaluation / Benchmarking / Prediction / Deployment    | [STM32N6570-DK](https://www.st.com/en/development-tools/stm32n6-ai.html)<br>     |
 
 
 [Full OD Services](object_detection/README.md) : training, evaluation, quantization, benchmarking, prediction, deployment
@@ -457,18 +457,54 @@ pip install -r requirements.txt
 
 ## Jump start with Colab
 
-In [tutorials/notebooks](tutorials/notebooks/README.md) you will find a jupyter notebook that can be easily deployed on
-Colab to exercise STM32 model zoo training scripts.
-
+In the `tutorials/notebooks` directory, you will find a Jupyter notebook that can be easily deployed on Colab to exercise STM32 model zoo training scripts.
 
 > [!IMPORTANT]
-> In this project, we are using **TensorFLow version 2.8.3** following unresolved issues with newest versions of TensorFlow, see [more](https://github.com/tensorflow/tensorflow/issues/56242).
+> In this project, we are using TensorFlow version 2.8.3 due to unresolved issues with newer versions of TensorFlow. For more details, see [this issue](https://github.com/tensorflow/tensorflow/issues/56242).
 
->[!CAUTION]
-> If there are some white spaces in the paths (for Python, STM32CubeIDE, or, STM32Cube.AI local installation) this can result in errors. So avoid having paths with white spaces in them.
+> [!CAUTION]
+> If there are any white spaces in the paths (for Python, STM32CubeIDE, or STM32Cube.AI local installation), this can result in errors. Avoid having paths with white spaces.
 
->[!TIP]
-> In this project we are using the `mlflow` library to log the results of different runs. Depending on which version of Windows OS are you using or where you place the project the output log files might have a very long path which might result in an error at the time of logging the results. As by default, Windows uses a path length limitation (MAX_PATH) of 256 characters: Naming Files, Paths, and Namespaces. To avoid this potential error, create (or edit) a variable named `LongPathsEnabled` in **Registry Editor** under **Computer/HKEY_LOCAL_MACHINE/SYSTEM/CurrentControlSet/Control/FileSystem/** and assign it a value of `1`. This will change the maximum length allowed for the file length on Windows machines and will avoid any errors resulting due to this. For more details have a look at this [link](https://knowledge.autodesk.com/support/autocad/learn-explore/caas/sfdcarticles/sfdcarticles/The-Windows-10-default-path-length-limitation-MAX-PATH-is-256-characters.html). Note that using GIT, line below may help solving long path issue : 
-```bash
-git config --system core.longpaths true
-```
+> [!TIP]
+> In this project, we are using the ClearML library to log the results of different runs.
+
+### ClearML Setup
+
+1. **Sign Up**: Sign up for free to the [ClearML Hosted Service](https://app.clear.ml). Alternatively, you can set up your own server as described [here](https://clear.ml/docs/latest/docs/deploying_clearml/).
+
+2. **Create Credentials**: Go to your ClearML workspace and create new credentials.
+
+3. **Configure ClearML**: Create a `clearml.conf` file and paste the credentials into it. If you are behind a proxy or using SSL portals, add `verify_certificate = False` to the configuration to make it work. Here is an example of what your `clearml.conf` file might look like:
+
+    ```ini
+    api {
+        web_server: https://app.clear.ml
+        api_server: https://api.clear.ml
+        files_server: https://files.clear.ml
+        # Add this line if you are behind a proxy or using SSL portals
+        verify_certificate = False
+        credentials {
+            "access_key" = "YOUR_ACCESS_KEY"
+            "secret_key" = "YOUR_SECRET_KEY"
+        }
+    }
+  
+    ```
+
+Once configured, your experiments will be logged directly and shown in the project section under the name of your project.
+
+### MLflow Setup
+
+In this project, we are also using the MLflow library to log the results of different runs.
+
+#### Windows Path Length Limitation
+
+Depending on which version of Windows OS you are using or where you place the project, the output log files might have a very long path, which might result in an error at the time of logging the results. By default, Windows uses a path length limitation (MAX_PATH) of 256 characters. To avoid this potential error, follow these steps:
+
+1. **Enable Long Paths**: Create (or edit) a variable named `LongPathsEnabled` in the Registry Editor under `Computer\HKEY_LOCAL_MACHINE\SYSTEM\CurrentControlSet\Control\FileSystem` and assign it a value of `1`. This will change the maximum length allowed for the file path on Windows machines and will avoid any errors resulting due to this. For more details, refer to [Naming Files, Paths, and Namespaces](https://docs.microsoft.com/en-us/windows/win32/fileio/naming-a-file).
+
+2. **GIT Configuration**: If you are using GIT, the line below may help solve the long path issue:
+
+    ```bash
+    git config --system core.longpaths true
+    ```

audio_event_detection/src/README.md

@@ -30,7 +30,35 @@ This directory contains the following files :
 - Several confusion matrices, as well as plots of the loss & validation accuracy curves during training are included.
 
 </details></ul>
-<ul><details open><summary><a href="#1-3">1.3 MLflow</a></summary><a id="1-3"></a>
+<ul><details open><summary><a href="#1-3">1.3 ClearML run</a></summary><a id="1-3"></a>
+
+ClearML is an open-source tool used for logging and tracking machine learning experiments. It allows you to record metrics, parameters, and results, making it easier to monitor and compare diffrent runs.
+
+Follow these steps to configurate ClearML for logging your results. This setup only needs to be done once. if you haven't set it up yet, complete the steps below. if you've already configured ClearML, your results should be automatically logged and available in your session.
+
+- Sign up for free to the [ClearML Hosted Service](https://app.clear.ml), then go to your ClearML workspace and create new credentials.
+
+- Create a `clearml.conf` file and paste the credentials into it. If you are behind a proxy or using SSL portals, add `verify_certificate = False` to the configuration to make it work. Here is an example of what your `clearml.conf` file might look like:
+
+    ```ini
+    api {
+        web_server: https://app.clear.ml
+        api_server: https://api.clear.ml
+        files_server: https://files.clear.ml
+        # Add this line if you are behind a proxy or using SSL portals
+        verify_certificate = False
+        credentials {
+            "access_key" = "YOUR_ACCESS_KEY"
+            "secret_key" = "YOUR_SECRET_KEY"
+        }
+    }
+  
+    ```
+
+Once configured, your experiments will be logged directly and shown in the project section under the name of your project.
+
+</details></ul>
+<ul><details open><summary><a href="#1-4">1.4 MLflow run</a></summary><a id="1-4"></a>
 
 MLflow is an API for logging parameters, code versions, metrics, and artifacts while running machine learning code and for visualizing results.
 The model zoo lets you use MLflow to easily visualize the results and metrics obtained in multiple trainings.

audio_event_detection/src/stm32ai_main.py

@@ -21,6 +21,8 @@
 import argparse
 import logging
 from typing import Optional
+from clearml import Task
+from clearml.backend_config.defs import get_active_config_file
 
 sys.path.append(os.path.join(os.path.dirname(__file__), '../../common'))
 sys.path.append(os.path.join(os.path.dirname(__file__), '../../common/benchmarking'))
@@ -545,6 +547,14 @@ def process_mode(mode: str = None, configs: DictConfig = None, train_ds: tf.data
     # logging the completion of the chain
     log_to_file(configs.output_dir, f'operation finished: {mode}')
 
+    # ClearML - Example how to get task's context anywhere in the file.
+    # Checks if there's a valid ClearML configuration file
+    if get_active_config_file() is not None: 
+        print(f"[INFO] : ClearML task connection")
+        task = Task.current_task()
+        task.connect(configs)
+
+
 @hydra.main(version_base=None, config_path="", config_name="user_config")
 def main(cfg: DictConfig) -> None:
     """
@@ -573,6 +583,17 @@ def main(cfg: DictConfig) -> None:
     cfg.output_dir = HydraConfig.get().run.dir
     mlflow_ini(cfg)
 
+    # Checks if there's a valid ClearML configuration file
+    print(f"[INFO] : ClearML config check")
+    if get_active_config_file() is not None:
+        print(f"[INFO] : ClearML initialization and configuration")
+        # ClearML - Initializing ClearML's Task object.
+        task = Task.init(project_name=cfg.general.project_name,
+                         task_name='aed_modelzoo_task')
+        # ClearML - Optional yaml logging 
+        task.connect_configuration(name=cfg.operation_mode, 
+                                   configuration=cfg)
+
     # Seed global seed for random generators
     seed = get_random_seed(cfg)
     print(f'[INFO] : The random seed for this simulation is {seed}')

audio_event_detection/src/utils/gen_h_file.py

@@ -140,7 +140,7 @@ def gen_h_user_file(config):
         if config.feature_extraction.to_db:
             f.write('#define CTRL_X_CUBE_AI_SPECTROGRAM_SILENCE_THR   (0) // 0 means disabled\n')
         else:
-            f.write('#define CTRL_X_CUBE_AI_SPECTROGRAM_SILENCE_THR   (3000.0F) // 0 means disabled\n')
+            f.write('#define CTRL_X_CUBE_AI_SPECTROGRAM_SILENCE_THR   (100.0F) // 0 means disabled\n')
         f.write('#define CTRL_X_CUBE_AI_SPECTROGRAM_WIN           (user_win)\n')
         f.write('#define CTRL_X_CUBE_AI_SPECTROGRAM_MEL_LUT       (user_melFiltersLut)\n')
         f.write('#define CTRL_X_CUBE_AI_SPECTROGRAM_MEL_START_IDX (user_melFiltersStartIndices)\n')

hand_posture/src/README.md

@@ -19,6 +19,7 @@ Remember that minimalistic yaml files are available [here](./config_file_example
    - [3.1 Saved results](#3-1)
    - [3.2 Run tensorboard](#3-2)
    - [3.3 Run MLFlow](#3-3)
+   - [3.4 Run ClearML](#3-4)
 
 <details open><summary><a href="#1"><b>1. Hand Posture Model Zoo introduction</b></a></summary><a id="1"></a>
 
@@ -357,7 +358,7 @@ tensorboard --logdir logs
 This will start a server and its address will be displayed. Use this address in a web browser to connect to the server. Then, using the web browser, you will be able to explore the learning curves and other training metrics.
 
 </details></ul>
-<ul><details open><summary><a href="#3-3">3.3 Run MLFlow</a></summary><a id="4-3"></a>
+<ul><details open><summary><a href="#3-3">3.3 Run MLFlow</a></summary><a id="3-3"></a>
 
 MLflow is an API that allows you to log parameters, code versions, metrics, and artifacts while running machine learning code, and provides a way to visualize the results. 
 
@@ -368,8 +369,35 @@ mlflow ui
 ```
 This will start a server and its address will be displayed. Use this address in a web browser to connect to the server. Then, using the web browser, you will be able to navigate the different experiment directories and look at the metrics that were collected. Refer to [MLflow Home](https://mlflow.org/) for more information about MLflow.
 
+
 </details></ul>
-</details>
+<ul><details open><summary><a href="#3-4">3.4 Run ClearML</a></summary><a id="3-4"></a>
+
+ClearML is an open-source tool used for logging and tracking machine learning experiments. It allows you to record metrics, parameters, and results, making it easier to monitor and compare diffrent runs.
+
+Follow these steps to configurate ClearML for logging your results. This setup only needs to be done once. if you haven't set it up yet, complete the steps below. if you've already configured ClearML, your results should be automatically logged and available in your session.
+
+- Sign up for free to the [ClearML Hosted Service](https://app.clear.ml), then go to your ClearML workspace and create new credentials.
+
+- Create a `clearml.conf` file and paste the credentials into it. If you are behind a proxy or using SSL portals, add `verify_certificate = False` to the configuration to make it work. Here is an example of what your `clearml.conf` file might look like:
+
+    ```ini
+    api {
+        web_server: https://app.clear.ml
+        api_server: https://api.clear.ml
+        files_server: https://files.clear.ml
+        # Add this line if you are behind a proxy or using SSL portals
+        verify_certificate = False
+        credentials {
+            "access_key" = "YOUR_ACCESS_KEY"
+            "secret_key" = "YOUR_SECRET_KEY"
+        }
+    }
+  
+    ```
+
+Once configured, your experiments will be logged directly and shown in the project section under the name of your project.
+
 <details open><summary><a href="#A"><b>Appendix A: YAML syntax</b></a></summary><a id="A"></a>
 
 **Example and terminology:**

hand_posture/src/stm32ai_main.py

@@ -11,14 +11,15 @@
 from hydra.core.hydra_config import HydraConfig
 import hydra
 import warnings
-
 warnings.filterwarnings("ignore")
 os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3' 
 
 import tensorflow as tf
 from omegaconf import DictConfig
 import mlflow
 import argparse
+from clearml import Task
+from clearml.backend_config.defs import get_active_config_file
 
 sys.path.append(os.path.join(os.path.dirname(__file__), '../../common'))
 sys.path.append(os.path.join(os.path.dirname(__file__), '../../common/benchmarking'))
@@ -111,6 +112,13 @@ def process_mode(mode: str = None,
     # logging the completion of the chain
     log_to_file(configs.output_dir, f'operation finished: {mode}')
 
+    # ClearML - Example how to get task's context anywhere in the file.
+    # Checks if there's a valid ClearML configuration file
+    if get_active_config_file() is not None: 
+        print(f"[INFO] : ClearML task connection")
+        task = Task.current_task()
+        task.connect(configs)
+
 
 @hydra.main(version_base=None, config_path="", config_name="user_config")
 def main(cfg: DictConfig) -> None:
@@ -140,6 +148,17 @@ def main(cfg: DictConfig) -> None:
     cfg.output_dir = HydraConfig.get().run.dir
     mlflow_ini(cfg)
 
+    # Checks if there's a valid ClearML configuration file
+    print(f"[INFO] : ClearML config check")
+    if get_active_config_file() is not None:
+        print(f"[INFO] : ClearML initialization and configuration")
+        # ClearML - Initializing ClearML's Task object.
+        task = Task.init(project_name=cfg.general.project_name,
+                         task_name='hpr_modelzoo_task')
+        # ClearML - Optional yaml logging 
+        task.connect_configuration(name=cfg.operation_mode, 
+                                   configuration=cfg)
+
     # Seed global seed for random generators
     seed = get_random_seed(cfg)
     print(f'[INFO] : The random seed for this simulation is {seed}')

hand_posture/src/user_config.yaml

@@ -54,7 +54,7 @@ training:
 
 tools:
   stedgeai:
-    version: 9.1.0
+    version: 10.0.0
     optimization: balanced
     on_cloud: True
     path_to_stedgeai: C:/Users/<XXXXX>/STM32Cube/Repository/Packs/STMicroelectronics/X-CUBE-AI/<*.*.*>/Utilities/windows/stedgeai.exe

human_activity_recognition/src/stm32ai_main.py

@@ -11,14 +11,15 @@
 from hydra.core.hydra_config import HydraConfig
 import hydra
 import warnings
-
 warnings.filterwarnings("ignore")
 os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3' 
 
 import tensorflow as tf
 from omegaconf import DictConfig
 import mlflow
 import argparse
+from clearml import Task
+from clearml.backend_config.defs import get_active_config_file
 
 sys.path.append(os.path.join(os.path.dirname(__file__), '../../common'))
 sys.path.append(os.path.join(os.path.dirname(__file__), '../../common/benchmarking'))
@@ -145,6 +146,14 @@ def process_mode(mode: str = None,
     # logging the completion of the chain
     log_to_file(configs.output_dir, f'operation finished: {mode}')
 
+    # ClearML - Example how to get task's context anywhere in the file.
+    # Checks if there's a valid ClearML configuration file
+    if get_active_config_file() is not None: 
+        print(f"[INFO] : ClearML task connection")
+        task = Task.current_task()
+        task.connect(configs)
+
+
 @hydra.main(version_base=None, config_path="", config_name="user_config")
 def main(cfg: DictConfig) -> None:
     """
@@ -172,7 +181,18 @@ def main(cfg: DictConfig) -> None:
     cfg = get_config(cfg)
     cfg.output_dir = HydraConfig.get().run.dir
     mlflow_ini(cfg)
-    
+
+    # Checks if there's a valid ClearML configuration file
+    print(f"[INFO] : ClearML config check")
+    if get_active_config_file() is not None:
+        print(f"[INFO] : ClearML initialization and configuration")
+        # ClearML - Initializing ClearML's Task object.
+        task = Task.init(project_name=cfg.general.project_name,
+                         task_name='har_modelzoo_task')
+        # ClearML - Optional yaml logging 
+        task.connect_configuration(name=cfg.operation_mode, 
+                                   configuration=cfg)
+
     # Seed global seed for random generators
     seed = get_random_seed(cfg)
     print(f'[INFO] : The random seed for this simulation is {seed}')