Fix inconsistent NMS IoU value for COCO (#3934)

Evaluation of 'best' and 'last' models will use the same params as the evaluation during the training phase. This PR fixes https://github.com/ultralytics/yolov5/issues/3907

Fix inconsistent NMS IoU value for COCO (#3934)
e7888af9 · Eldar Kurtic · GitHub · 8c6f9e15 · e7888af9
--- a/train.py
+++ b/train.py
@@ -457,8 +457,6 @@ def train(hyp,  # path/to/hyp.yaml or hyp dictionary
                    results, _, _ = test.run(data_dict,
                                             batch_size=batch_size // WORLD_SIZE * 2,
                                             imgsz=imgsz_test,
-                                             conf_thres=0.001,
-                                             iou_thres=0.7,
                                             model=attempt_load(m, device).half(),
                                             single_cls=single_cls,
                                             dataloader=testloader,