pytorch-YOLOv4

pytorch-YOLOv4 copied to clipboard

Move to YOLOV7 or YOLOX project unmaintained

4

-deleted-

ghsanti

Use YoloX

1

ghsanti

COCO eval results boost by changing NMS function

1

Hi @Tianxiaomo , I just ported your Yolov4 to Pytorch Lightning. I get the following results evaluating with `pycocotools`   | [email protected] | [email protected]:0.95 -- | -- | -- TianXiaomo(pycocotools evaluation)...

mikel-brostrom

Just go to YoloV7 or YoloX, those run at least.

ghsanti

RuntimeError: view size is not compatible with input tensor's size and stride

1

Got this error: ```python File "train.py", line 211, in build_target pred_ious = bboxes_iou(pred[b].view(-1, 4), truth_box, xyxy=False) RuntimeError: view size is not compatible with input tensor's size and stride (at least...

mikel-brostrom

Inference Issue

1

Hi Team, I am trying to run inference script on my own data. I have weights file which is converted to torch weights file and config file is also give,...

KVSAkhilesh

Hope this maybe help you ,the way to solve issues：AssertionError: results do not correspond to current coco set,

2

lizhimll

How to post process the output of yolov4 on onnx runtime in c++. I have created the onnx runtime engine and got the predictions but didn't able to get any...

codewithAshray

When I introduce random noise to the input loss.item() decreases. Part of the code for training is included here. ``` for epoch in range(epochs): # model.train() epoch_loss = 0 epoch_step...

Shah-imran

jack657166