Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

关于在paddlex 3.0 中 CocoDetection API的问题 #2656

Open
4 tasks
fatsheep2020 opened this issue Dec 14, 2024 · 5 comments
Open
4 tasks

关于在paddlex 3.0 中 CocoDetection API的问题 #2656

fatsheep2020 opened this issue Dec 14, 2024 · 5 comments
Assignees

Comments

@fatsheep2020
Copy link

Checklist:

描述问题

在paddlex 2.1中的API paddlex.datasets.CocoDetection() 在3.0中没有了 那这个函数如何在3.0中实现呢?要自己手写吗?

urgent, thanks!

复现

example:

定义训练和验证所用的数据集

API说明:https://github.com/PaddlePaddle/PaddleX/blob/develop/paddlex/cv/datasets/coco.py#L26

train_dataset = pdx.datasets.CocoDetection(
data_dir='./train/images',
ann_file='./instances_train.json',
transforms=train_transforms,
shuffle=True)
eval_dataset = pdx.datasets.CocoDetection(
data_dir='./test/images',
ann_file='./instances_val.json',
transforms=eval_transforms)

  1. 您是否已经正常运行我们提供的教程

  2. 您是否在教程的基础上修改代码内容?还请您提供运行的代码

  3. 您使用的数据集是?

  4. 请提供您出现的报错信息及相关log

环境

  1. 请提供您使用的PaddlePaddle和PaddleX的版本号
    3.0

  2. 请提供您使用的操作系统信息,如Linux/Windows/MacOS
    ubuntu

  3. 请问您使用的Python版本是?

  4. 请问您使用的CUDA/cuDNN的版本号是?

@TingquanGao TingquanGao self-assigned this Dec 14, 2024
@TingquanGao
Copy link
Collaborator

3.0升级改动较大,和2.0的使用逻辑不同。是有什么具体的需求呢?可以先参考下新的文档:https://github.com/PaddlePaddle/PaddleX/blob/release/3.0-beta2/docs/module_usage/tutorials/cv_modules/object_detection.md#41-%E6%95%B0%E6%8D%AE%E5%87%86%E5%A4%87

@fatsheep2020
Copy link
Author

i have descripted my question above, can we still use this API in 3.0? paddlex.datasets.CocoDetection()
@TingquanGao thanks!

@TingquanGao
Copy link
Collaborator

这个接口在3.0不支持了

@wangwenqi567
Copy link

小白想请教一下,离线下载模型之后,create_model还是会从网址上下载模型,应该怎么解决

@TingquanGao
Copy link
Collaborator

小白想请教一下,离线下载模型之后,create_model还是会从网址上下载模型,应该怎么解决

这个问题到新的issue跟进吧 #2715

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants