RuntimeError: Unable to find a valid cuDNN algorithm to run convolution

一、报错代码

# 报错代码

Traceback (most recent call last):
  File "train_plate.py", line 691, in <module>
    main(opt)
  File "train_plate.py", line 588, in main
    train(opt.hyp, opt, device, callbacks)
  File "train_plate.py", line 382, in train
    pred = model(imgs, headi = headi)  # forward
  File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/jovyan/wqg/code/YOLO/yolov5_v6_plate_heading/models/yolo_plate.py", line 155, in forward
    return self._forward_once(x, profile, visualize)  # single-scale inference, train
  File "/home/jovyan/wqg/code/YOLO/yolov5_v6_plate_heading/models/yolo_plate.py", line 193, in _forward_once
    x = m(x)  # run
  File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/jovyan/wqg/code/YOLO/yolov5_v6_plate_heading/models/common.py", line 57, in forward
    return self.act(self.bn(self.conv(x)))
  File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 423, in forward
    return self._conv_forward(input, self.weight)
  File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 419, in _conv_forward
    return F.conv2d(input, weight, self.bias, self.stride,
RuntimeError: Unable to find a valid cuDNN algorithm to run convolution

二 、解决方案

• 降低batch_size
• 增加显卡数量

我使用的第二个方案：

可以顺利训练。