Prateek Gupta

Try this notebook for the conversion- [https://colab.research.google.com/gist/AlexeyAB/fcb47ae544cf284eb24d8ad8e880d45c/yolov7trtlinaom.ipynb](url)

Of course, it is possible. Just annotate the face area of the apes you want to detect and do custom training. For creating the dataset and labels, you can either...

The way you are following does not work with YOLO. You must add your new class data to the existing 80 classes dataset and train the model if you want...

since you have a little time, I recommend you to use YOLOv4 [https://github.com/hank-ai/darknet](url)

Try this PR- [https://github.com/WongKinYiu/yolov7/pull/1968](url)

I tried your code on the custom yolov7-tiny model. And its size is reduced to 11.8 MB only from 11.9 MB.

> @dsbyprateekg Once reparameterization is done, you can convert directly the model to engine file, for example in int8, and the output file will be about 8.3MB. any link or...

@knowngono No, it will not work without an NVIDIA GPU.

> Is there any method to make ROI and detect object only in ROI part? Please let me know which python file and method should I add or edit. I...

> I'm trying to use wandb in yolov7, but I get an error. I looked it up and it seems like using pytorch lightning, not pytorch. How can I use...