I am trying to use the fastai library to build a machine learning model for object detection. I'm not an expert in machine learning, so I searched online and found this tutorial at object detection tutorial
but when I used Google colab to run it, I got error saying:
TypeError: no implementation found for 'torch.nn.functional.smooth_l1_loss' on types that implement torch_function: [<class 'fastai.torch_core.TensorImage'>, <class 'fastai.vision.core.TensorBBox'>]
And I've also tried a 2018 version of the same tutorial before but ran into the same problem. Does anyone know what's going on?
我正在尝试使用FAST AI库来构建一个用于目标检测的机器学习模型。我不是机器学习方面的专家,所以我在网上搜索并在对象检测教程中找到了这个教程,但当我使用Google CoLab运行它时,我得到的错误是:TypeError:在实现Torch_Function的类型上找不到‘torch.nn.unctional.Smooth_L1_Loss’的实现:[
,
,我以前也尝试过同一教程的2018版,但遇到了同样的问题。有人知道这是怎么回事吗?
更多回答
Sounds like a problem with environment setup. What steps did you follow to install fastai and other required packages, and what version of packages are you using?
听起来像是环境设置有问题。您按照什么步骤安装Fastai和其他必需的程序包?您使用的是什么版本的程序包?
优秀答案推荐
The repository you referred to in your question is outdated a/c to their README here.
你在问题中提到的储存库在他们的自述文件中已经过时了。
You can find instructions to go to the latest versions of notebooks there.
您可以在那里找到转到最新版本笔记本的说明。
更多回答
我是一名优秀的程序员,十分优秀!