optimización del algoritmo de detección de peatones yoloair

https://gitee.com/leeguandong/yoloair https://gitee.com/leeguandong/yoloair 1.yolov5

300 轮: métrica/precisión: 0,83757, métrica/recuperación: 0,749, mapa_0,5:0,84328, mapa_0,5:0,95:0,56934

2.investigación/yolov5s-bifpn

RuntimeError: Expected to have finished reduction in the prior iteration before starting a new one. This error indicates that your module has parameters that were not used in producing loss. You can enable unused parameter detection by (1) passing the keyword argument `find_unused_parameters=True` to `torch.nn.parallel.DistributedDataParallel`; (2) making sure all `forward` function outputs participate in calculating loss. If you already have done the above two steps, then the distributed data parallel module wasn't able to locate the output tensors in the return value of your module's `forward` function. Please include the loss function and the structure of the return value of `forward` of your module when reporting this issue (e.g. list, dict, iterable)

Línea 261 en tren.py:

    if cuda and RANK != -1:
        model = DDP(model, device_ids=[LOCAL_RANK], output_device=LOCAL_RANK,find_unused_parameters=True)

python -m torch.distributed.launch --nproc_per_node=8 --nnodes=1 --node_rank=0 --master_addr=localhost --master_port=22222 train.py