kpt, yolov7-w6-pose.pt, Can't call numpy() on Tensor that requires grad. Use tensor.detach().numpy() instead.

[xinsuinizhuan]

Traceback (most recent call last): File "E:\Item\Item_done\yolo\yolo5\yolov7\yolov7-main\pose.py", line 27, in output = output_to_keypoint(output) File "E:\Item\Item_done\yolo\yolo5\yolov7\yolov7-main\utils\plots.py", line 443, in output_to_keypoint targets.append([i, cls, *list(*xyxy2xywh(np.array(box)[None])), conf, *list(kpts.cpu().numpy()[index])]) RuntimeError: Can't call numpy() on Tensor that requires grad. Use tensor.detach().numpy() instead.

[WongKinYiu]

kpts.cpu().numpy() -> kpts.detach().cpu().numpy()

[mkhoshbin72]

I added PR #333 to solve this problem.

[xinsuinizhuan]

I added PR #333 to solve this problem.

how to export the to onnx?

[mkhoshbin72]

use export.py

[xinsuinizhuan]

use export.py

no, i export it, but the onnx model not right: how to export it as:

[mkhoshbin72]

Do you use the latest YOLOv7 code? Take a look at #319

[xinsuinizhuan]

Do you use the latest YOLOv7 code? Take a look at #319

Yes。The latest yolov7 code.But it was the yolov7-w6-pose.pt model.

[xinsuinizhuan]

Do you use the latest YOLOv7 code? Take a look at #319

when i use: python3 export.py --weights best.pt --grid --end2end --simplify --topk-all 100 --iou-thres 0.65 --img-size 1280 1280 --conf-thres 0.35 --max-wh 1280 error:

[xinsuinizhuan]

when i export the tiny model with nms, but the output have no nms: exported with command: python export.py --weights yolov7-tiny.pt --grid --end2end --simplify --topk-all 100 --iou-thres 0.65 --conf-thres 0.35 --img-size 640 640 --max-wh 640

it shoud be nms result, as const char *OUTPUT_COUNTS = "count"; const char *OUTPUT_BOXES = "box"; const char *OUTPUT_SCORES = "score"; const char *OUTPUT_CLASSES = "class";

[mkhoshbin72]

It's OK. Output of onnx model has shape of (number_of_detections, 7). Second part consists of (batch_id,x0,y0,x1,y1,cls_id,score)

[xinsuinizhuan]

It's OK. Output of onnx model has shape of (number_of_detections, 7). Second part consists of (batch_id,x0,y0,x1,y1,cls_id,score)

OK。Thank you very much.