Learn Computer Vision using AI: kevinwoodrobotics.com/product/computer-vision-using-ai/ Code and Doc: kevinwoodrobotics.com/product/small-object-detection-with-sahi-and-yolo/
I see SAHI used with YOLO. Can it be used with other lightweight object detection models like MobileNet-SSD or RetinaNet? Is there any techniques that can be used to reduce the number of slicing operations in SAHI?
Yeah I’d imagine it could work with any model but you may have to modify their source code. There should be some ways to fine tune how you want to slice it
This is super great work, Kevin! I have been haunting for a tutorial on how to fine-tune SAHI on custom dataset but couldn't find any; Is it possible? Thanks. I hoped I could first fine-tune and train the YOLOV8 model first using SAHI then do inference also on SAHI. Is this approach valid? Thanks in advance
Learn Computer Vision using AI: kevinwoodrobotics.com/product/computer-vision-using-ai/
Code and Doc: kevinwoodrobotics.com/product/small-object-detection-with-sahi-and-yolo/
Great 👍
I see SAHI used with YOLO. Can it be used with other lightweight object detection models like MobileNet-SSD or RetinaNet? Is there any techniques that can be used to reduce the number of slicing operations in SAHI?
Yeah I’d imagine it could work with any model but you may have to modify their source code. There should be some ways to fine tune how you want to slice it
This is super great work, Kevin! I have been haunting for a tutorial on how to fine-tune SAHI on custom dataset but couldn't find any; Is it possible? Thanks. I hoped I could first fine-tune and train the YOLOV8 model first using SAHI then do inference also on SAHI. Is this approach valid? Thanks in advance
Thanks! Yeah it should be possible
can this framework slice images with annotations for training models?
Might be possible