enazoe
enazoe
@ybc-ybc the yolov4-tiny is not yet supported, but I am working on it and support soon.
@opentld 好的，我去看下yolo-fastest的性能和效果，如果不错的话可以实现下，如果您有qq的话可以加群讨论，群号在readme
yolo3，4都是用的darknet的weights，我并没有对他进行改动，yolov5是吧pt转成了weights
checkout the release tag [yolov5-2.0](https://github.com/enazoe/yolo-tensorrt/releases/tag/yolov5-2.0) about the calibration_images.rar
@Rhee-site pull the latest calibration_images.txt
@huunhan312 https://github.com/enazoe/yolo-tensorrt/releases/download/calibration_images.txt/calibration_images.rar
remove the top space line in cfg file
https://github.com/enazoe/yolo-tensorrt/blob/5ffe5869c50868c24193d317fa0be6b9d8f8e995/modules/class_yolo_detector.hpp#L84 这里和相关的地方
@jstumpin @zhangxiaopang88 @chongzhong sorry, batch inference not support yet ,I will working on it and support soon. And welcom PR at same time.