Semantic segmentation, predicting how to crop pictures

[monkeycc]

Identified object

To crop

Height and width depend on the size of the object

Background translucent

[xiexinch]

Hi @monkeycc, Could you describe your problem or requirements in detail(Datasets, usage scenarios, etc.)? According to the current description, we do not implement such a model, data augmentation method, or post-processing methods.

[monkeycc]

DeepLabV3 模型 COCO数据集

语义分割检测之后

需要后处理方法

如何进行这样的裁剪 @xiexinch

[xiexinch]

I think there are many ways to implement this method, but because of the lack of developers, we do not yet have plans to support this post-processing. You might try to implement this method yourself, and welcome to create a PR for this method. :)