Before using the script, ensure you have the following prerequisites in place:
Python: Make sure you have Python installed on your system. You can download it from python.org.
Git: You'll also need Git installed on your system to run the following command. You can download it from git-scm.com.
Required Libraries: Install the required Python libraries, including the script's custom library, using the following commands:
pip install watchdog aiohttp discord.py pytz
PyPi package installation:
pip install svc-ds-webhook
Download the script to your local machine.
Open a terminal or command prompt and navigate to the directory where you've saved the script.
Run the script using the following command:
svc_ds_webhook --url YOUR_DISCORD_WEBHOOK_URL --dataset_name YOUR_DATASET_NAME --train_folder_name YOUR_TRAIN_FOLDER_NAME --epochs_to_train NUMBER_OF_EPOCHS --directory DIRECTORY_TO_MONITOR
- Replace YOUR_DISCORD_WEBHOOK_URL with the actual Discord webhook URL where you want to receive updates.
- Specify the YOUR_DATASET_NAME and YOUR_TRAIN_FOLDER_NAME
- Set NUMBER_OF_EPOCHS to the total number of epochs you want to train.
- Specify the DIRECTORY_TO_MONITOR, which is the directory where you want the script to monitor for AI training progress updates.
Once the script is running, it will monitor the specified directory for changes in the training process. When new model files (with names starting with 'G_') are created in the directory, the script will send updates to the Discord webhook. It will provide information on the percentage of training completed and the estimated completion time.
The script will continue to run until you manually stop it using Ctrl+C
in the terminal.
That's it! You now know how to use the AI training progress monitoring script to keep track of your AI model's training progress using a Discord webhook.