Hi,
I managed to train a custom detection model via jetson-inference, but I wonder, is there any possible way I can get any information or statistics for the performance of the custom model? Such as, accuracy, max fps, average confidence or etc.
I noticed the “eval_ssd.py” program inside jetson-inference, but I do not have any idea what it is for and how to use it. However, I suspect it is for trained model performance evaluation.
Thank you.
Hi,
Please check below for some details:
https://github.com/dusty-nv/jetson-inference/blob/master/docs/pytorch-ssd.md
After the training jobs, you can find some loss information on the console:
...
2020-07-10 13:19:26 - Epoch: 0, Validation Loss: 5.6730, Validation Regression Loss 1.7096, Validation Classification Loss: 3.9634
2020-07-10 13:19:26 - Saved model models/fruit/mb1-ssd-Epoch-0-Loss-5.672993580500285.pth
Then you can get some mAP score with your validation dataset by applying the inference script like run_ssd_example.py.
And if you deploy the model with live camera (streaming data), the fps will show on the window automatically.
Thanks.
Hi,
Owh, I did notice those information at the console during training. Thank you for your clarification.
Hola Faiz,
Me puedes ayudar a crear un modelo de deteccion personalizado?
Hola,
I recommend you to follow the guide provided in the link below first. Tutorials video also have been included there. I think informations there able to help you.
Thank you.
Hola Faiz muchas gracias…ya revisé los tutoriales
Actualmente el problema que tengo es que estoy generando una base de datos en labelme en la que etiqueté algunas imagenes, posteriormente la transformé a formato VOC en los que se crean archivos .xml para cada imágen, sin embargo en los ejemplos observados se tienen archivos .csv.
Actualmente tengo 3 carpetas:
Annotations: archivos de tipo.xlm
AnnotationsVisualization: archivos de tipo .jpg con las imágenes etiquetadas
JPEGImages: archivos de tipo .jpg con las imagenes originales.
