PaddleSeg icon indicating copy to clipboard operation
PaddleSeg copied to clipboard

Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image Mat...

Results 373 PaddleSeg issues
Sort by recently updated
recently updated
newest added

Thanks for your issue. To help us solve the issue better, please provide following information: 1. PaddleSeg version: (please specify the branch as well,e.g. PaddleSeg release/2.3) 2. PaddlePaddle version: (e.g....

question

我在推理的时候,输出的预测结果shape不对,按理说应该是(64,128,128),结果却是(1,64,128,128),错误的npy大小约为正常预测结果的两倍。这是什么原因? --- 欢迎您反馈PaddleSeg使用问题,辛苦您提供以下信息,方便我们快速定位和解决问题: 1. PaddleSeg版本:(PaddleSeg release/2.3) 2. PaddlePaddle版本:(PaddlePaddle 2.3.0) 3. 操作系统信息:(Linux) 4. Python版本号:(python3.7) 5. CUDA/cuDNN版本:( CUDA10.2) 6. 其他内容: (增加其他与问题相关的内容)

question

When I use eiseg annotation, I get the following error,how to solve it please ![2022-08-17 13-05-38屏幕截图](https://user-images.githubusercontent.com/86768013/185039116-5aa7136f-edb0-4360-a0d8-2b29cc3699cb.png) ![2022-08-17 13-06-01屏幕截图](https://user-images.githubusercontent.com/86768013/185039205-3ad7a0c0-312d-4a8d-b683-29a4292b9ba2.png)

question

请问是否又方法将cityscapes数据集中的验证集中的label改变下可视化效果。 原: ![1a354a0f8d956f8f0e5b5a260f4109a](https://user-images.githubusercontent.com/71338215/184588048-b557244e-1cb4-4d68-beea-16d28f3376ea.png) 想修改成与预测(predict.py)出来结果相类似的这种: ![4d060a84470e6467ed212b77479927d](https://user-images.githubusercontent.com/71338215/184588121-8784a41f-baf1-47cf-93dc-74c38525c651.png) 另外还想请教,如何获取得到cityscapes数据集中test集的label,便于对自己修改后的模型用测试集进行评估,目前只能用验证集评估。

question

负样本损失权重也就是背景权重,在那个地方可以设置,因为要分割的类别像素相比于背景像素要少很多,我想将负样本损失权重增大,用于减少像素误分割的,请问我需要在yml文件中的那个位置进行设置。

question

Thanks for your issue. To help us solve the issue better, please provide following information: 1. PaddleSeg version: (please specify the branch as well,e.g. PaddleSeg release/2.3) 2. PaddlePaddle version: (e.g....

question

### 问题确认 Search before asking - [X] 我已经搜索过问题,但是没有找到解答。I have searched the question and found no related answer. ### 请提出你的问题 Please ask your question 如题,对人像分割模型精度不是很满意,手里没有足够的分割数据集,有matting数据集(alpha值从0-255),如何科学使用这些数据集进行优化微调呢?有没有建议,感谢

question

### 问题确认 Search before asking - [X] 我已经查询[历史issue](https://github.com/PaddlePaddle/PaddleSeg/issues)(包括open与closed),没有发现相似的bug。I have searched the [open and closed issues](https://github.com/PaddlePaddle/PaddleSeg/issues) and found no similar bug report. ### Bug描述 Describe the Bug In Google Colab Quick...

bug