1.AttributeError: 'FreeTypeFont' object has no attribute 'getsize'

降低pillow版本，把pillow10之后的降级为9.5

pip install pillow==9.5

2.IndexError: list index out of range

在val.py里的NMS前添加：

        with dt[2]:
            preds = preds[0][1] if isinstance(preds[0], list) else preds[0]  # add

3.libiomp5md.dll already initialized

OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized. 

找到libiomp5md.dll，把重复的删一个就行

4.Arial.ttf无法下载

想办法下载，开代理翻墙

5.添加模块时运行报错

RuntimeError:adaptive_max_pool2d_backward_cuda does not have a deterministic implementation, but you set 'torch.use_deterministic_algorithms(True)'. You can turn off determinism just for this operation, or you can use the 'warn_only=True' option, if that's acceptable for your application. You can also file an issue at https://github.com/pytorch/pytorch/issues to help us prioritize adding deterministic support for this operation.

在train.py找到scaler.scale，在此位置前添加torch.use_deterministic_algorithms(False)

            # Backward
            torch.use_deterministic_algorithms(False)
            scaler.scale(loss).backward()