aleksajanjic99

I used yolov5n-cls.pt as base model during classification training. Image size is 128x128. I will try and reproduce a MRE, and send it.

I have trained a yolo v5 image classification model, and I used online blob converter tool http://blobconverter.luxonis.com for converting the model to blob format in order to run it on OAK camera's VPU. I have set up a NeuralNetwork node, and an input stream to which I send an image, and take the NNData from the output stream. Fetching data from the output stream takes somewhere between 400 and 600 ms, which seems to be too long. Does anyone have an idea why it is taking so long, and what could be the possible mistakes I made in the process?

Okay, sorry, I did not realise at first what you meant. Can you suggest me any other framework that I could use to train image classification model, but that has the ability to work with depthai, unlike Yolov8.

Nothing is confusing, I just mentioned that I could not use that tool for conversion because my model is trained for classification. I need a way to convert my model correctly.

I trained a custom Yolo v8 classification model on 2 classes. When i run the model on my laptop it classifies images correctly, so the problem is most likely not in the dataset. I used depthai library as interface for oak camera. I converted the model from .pt format to required blob format using http://blobconverter.luxonis.com/. When i deploy the converted model to oak camera using the depthai, the model always classifies the images as the class number 1. I guess that there is a certain loss of data or parameters in the conversion process, because classification works correctly in .pt format on my laptop as i mentioned before.
I tried using http://tools.luxonis.com/ website but it only supports detection, and not classification when it comes to Yolo v8. I also tried to use the export command that Yolo v8 offers and exported the model in the Intermediate Format(IR), and then convert it to blob format using the same tool http://blobconverter.luxonis.com/. Weirdly, the model now always classified the images as class number 2.

I wonder if there is another tool i could use, or am i doing something wrong in the conversion process?