本实战项目是一个CIFAR-10的图像分类任务,基于CIFAR10的数据集和【PyTorch】,通过在云脑环境调试和训练模型,最终评估模型的准确率。
《Case1》文件夹,是基于云脑1算力资源(CPU/GPU)进行任务调试与训练的代码文件
《Case2》文件夹,是基于云脑2算力资源(Ascend NPU)进行任务调试与训练的代码文件
《教程》文件夹,是本次项目实战的详细教程
CIFAR.zip,是本次项目使用的数据集
ls
#(相应代码放在/code下,相应数据集放在/dataset下)
cd /code/case1
python main.py
#克隆代码,在代码页的HTTPS点击复制链接,在此处!git clone后面粘贴链接
!git clone
#解压数据集
!unzip cifar.zip
#运行代码
!python OpenI_test/case2/train.py --dataset_path ./cifar-10-batches-bin/
在新建训练任务中,输入指定文件为“case2/train.py”,数据集指定为cifar.zip,点击提交即可
Model | Acc. |
---|---|
VGG16 | 92.64% |
DLA | 95.47% |
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》