盛宇清

Same problem. Two 2080TI (11GB*2) with batch_size = 6 . Here's the traceback: `Traceback (most recent call last): File "C:/Users/Admin/Desktop/EfficientDet.Pytorch-master/train.py", line 196, in train() File "C:/Users/Admin/Desktop/EfficientDet.Pytorch-master/train.py", line 141, in train...

> @AlexLuya @RayOnFire @shengyuqing > I used: > OS: Ubuntu 18.04 > GPU: 2*2080TI(11GB) > When training, I set batch_size 32 for EffficientDet-D0(~20000MB cuda), and batch_size 16 for EfficientDet-Do(~20000MB cuda)....

@toandaominh1997 I used Windows10

> You can handle high-resolution images directly by setting the `imgsz` parameter to your desired resolution (3840x2160) during inference or training. However, processing such high-resolution images can be computationally expensive,...

@glenn-jocher Thank you very much for your reply. What I used for training before was model.train(data='data/train_Normal.yaml', epochs=epochs, workers=0,save=True,device=gpus,imgsz=500,batch=batch,close_mosaic=1) This line of code, how to change“ imgsz=500 ”to “imgsz=3840,2160”？