你好，我在训练出错 about yolodet-pytorch HOT 4 OPEN

已解决但是出现了新的问题。

from yolodet-pytorch.

           Class      Images     Targets           P           R      [email protected]  [email protected]:.95:   0%|                                                                                                        | 0/11 [00:00<?, ?it/s]/home/tongyu/develop-project/yolodet-pytorch-master/yolodet/models/heads/base.py:330: UserWarning: This overload of nonzero is deprecated:
    nonzero()

Consider using one of the following signatures instead:
nonzero(*, bool as_tuple) (Triggered internally at /opt/conda/conda-bld/pytorch_1595629431274/work/torch/csrc/utils/python_arg_parser.cpp:766.)
i, j = (x[:, 5:] > conf_thres).nonzero().t()
Class Images Targets P R [email protected] [email protected]:.95: 0%| | 0/11 [00:00<?, ?it/s]
Traceback (most recent call last):
File "tools/train.py", line 144, in
main()
File "tools/train.py", line 140, in main
train_detector(model,datasets,cfg,validate=args.validate,timestamp=timestamp,meta=meta)
File "/home/tongyu/develop-project/yolodet-pytorch-master/yolodet/apis/train.py", line 161, in train_detector
runner.run(data_loaders, cfg.workflow, cfg.total_epochs)
File "/home/tongyu/develop-project/yolodet-pytorch-master/yolodet/apis/runner.py", line 331, in run
epoch_runner(data_loaders[i], **kwargs)
File "/home/tongyu/develop-project/yolodet-pytorch-master/yolodet/apis/runner.py", line 230, in train
self.call_hook('after_train_epoch')
File "/home/tongyu/develop-project/yolodet-pytorch-master/yolodet/apis/runner.py", line 205, in call_hook
getattr(hook, fn_name)(self)
File "/home/tongyu/develop-project/yolodet-pytorch-master/yolodet/models/hooks/eval_hook.py", line 52, in after_train_epoch
results = single_gpu_test(model, self.dataloader)
File "/home/tongyu/develop-project/yolodet-pytorch-master/yolodet/apis/test.py", line 93, in single_gpu_test
output = non_max_suppression(inf_out, conf_thres=conf_thres, iou_thres=iou_thres, merge=merge)
File "/home/tongyu/develop-project/yolodet-pytorch-master/yolodet/models/heads/base.py", line 355, in non_max_suppression
i = torchvision.ops.boxes.nms(boxes, scores, iou_thres)
File "/home/tongyu/.conda/envs/yolodet/lib/python3.6/site-packages/torchvision/ops/boxes.py", line 40, in nms
return torch.ops.torchvision.nms(boxes, scores, iou_threshold)
RuntimeError: Trying to create tensor with negative dimension -349300680: [-349300680]

from yolodet-pytorch.

你好，我也遇到了同样的问题，请问你现在解决了吗？

from yolodet-pytorch.

我找到了，确实是yolov4_coco_100e.py中bbox那行的上一句的None后面没有逗号的原因。

from yolodet-pytorch.