I'm trying to convert my model using the Luxonis Blob Converter but it's been two hours and it still says converting. Is there any way I can make this process faster? Should I be worried?
How long does it take for the blob converter to convert a pb file?
The model is only 140kb. I tried using the provided API to try to get more insight into what's happening and I got an error:
Conversion failed with status code: 500
Error message: <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2 Final//EN">
<title>500 Internal Server Error</title>
<h1>Internal Server Error</h1>
<p>The server encountered an internal error and was unable to complete your request. Either the server is overloaded or there is an error in the application.</p>
Hey! Sorry for not responding I actually decided to train a model using yolov5 and it converted easily. Now I'm trying to connect my neural network to the camera and I keep getting fatal errors. I'm not sure how to fix this issue. I attached the code for my model and the code for deploying the model below.
Here is the code for deploying the model
- Edited
Hi @Acorn,
Did you use our tools to convert your trained YoloV5s model? If not, I'd highly recommend to you to use it. It is super straightforward. You just have to upload .pt model weights, and the app will convert the model. For inference, I'd recommend to you using this demo app. All you need to do is download the code, install the dependencies, and then run the script using the generated .blob and .json config file that you can obtain from the tools using this command:
python3 main_api.py -m <model_name> --config <config_json>
Hope that helps!
Best
Jan