🚀 TensorRT-YOLO: Supports YOLOv3, YOLOv5, YOLOv6, YOLOv7, YOLOv8, YOLOv9, YOLOv10, and PP-YOLOE using TensorRT acceleration with EfficientNMS, CUDA Kernels and CUDA Graphs!
Encountered a problem while running the detect.py script with the YOLOv8 FP16 engine exported by python/export/yolov8/export.py. Specifically, the detection of objects is compromised, leading to anomalies in precision. Notably, the same script performs adequately when using the FP32 engine exported by the same method.
Encountered a problem while running the detect.py script with the YOLOv8 FP16 engine exported by python/export/yolov8/export.py. Specifically, the detection of objects is compromised, leading to anomalies in precision. Notably, the same script performs adequately when using the FP32 engine exported by the same method.