when I train with widerface,error occured

[futureflsl]

Traceback (most recent call last):
File "train.py", line 513, in
train(hyp, opt, device, tb_writer, wandb)
File "train.py", line 299, in train
scaler.step(optimizer) # optimizer.step
File "/home/fut/miniconda3/lib/python3.8/site-packages/torch/cuda/amp/grad_scaler.py", line 321, in step
retval = optimizer.step(*args, **kwargs)
File "/home/fut/miniconda3/lib/python3.8/site-packages/torch/optim/lr_scheduler.py", line 67, in wrapper
return wrapped(*args, **kwargs)
File "/home/fut/miniconda3/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 26, in decorate_context
return func(*args, **kwargs)
File "/home/fut/miniconda3/lib/python3.8/site-packages/torch/optim/sgd.py", line 106, in step
buf.mul_(momentum).add_(d_p, alpha=1 - dampening)
RuntimeError: The size of tensor a (32) must match the size of tensor b (24) at non-singleton dimension 0

[Bohrhh]

+1

[yongjingli]

@derronqi same question

[ssmy199]

+1

[ssmy199]

Change yolov5s-face.pt to yolov5 official file>>yolov5s.pt，this is my solution