Problems with custom dataset and tensorrt8 #301
Reference in New Issue
Block a user
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Hello
i have an issue using a custom trained dataset with one class on yolov4. Everything works fine on tensorrt7 but when using tensorrt8 i get 3-4 detections around the object as it gets bigger. I tested the provided weights, both with tensorrt7 and tensorrt8 there is no problem. What could be the issue? I attached the yolo-config file.
yolov4-custom.txt