using text promp to get masks for all same classes not one mask

[limmax]

使用text prompt模式时我希望能够分割出图像中所有指定类别的物体，比如我的提示词是“dog“时，我希望能够分割出图像中所有的dog，而fastsam只分割出其中一条狗，即使我更换提示词为”all dogs“时也不起作用。 When using the text prompt mode, I hope to be able to segment all objects of the specified category in the image. For example, when my prompt word is "dog", I hope to segment all the dogs in the image, while fastsam only segments one of them. Even if I change the prompt word to "all dogs", it doesn't work.