Extract the mask of the entire image
Opened this issue · 4 comments
Hello Xingyu, may I ask how to extract the mask of the entire image based on the pre trained model you provided?
The pre trained model you provided does not have transient embedded MLP weights
Yes, the pre-trained model does not include transient embedded MLP weights, but they can be easily obtained by training using our provided training code.
是的，预训练模型不包括瞬态嵌入式 MLP 权重，但可以使用我们提供的训练代码轻松获得它们。
Can I load the pre trained model you provided in the test code to obtain the mask of the entire image?
Or can I only load the pre trained model you provided in the training code to obtain the mask of the entire image? Do I also need to reinitialize the transient embedded network, as the pre trained model does not have MLP weights