The file cls_labels.npy saves the class label of each image, format like {'filename' : '1, 0, 1, ..., 0'}. For simplicity, you can use the label from the x_mask, I think the program may seems like

JaveyWang / Pyramid-Attention-Networks-pytorch

Implementation of Pyramid Attention Networks for Semantic Segmentation.

GNU General Public License v3.0

235 stars 55 forks source link

The file cls_labels.npy saves the class label of each image, format like {'filename' : '1, 0, 1, ..., 0'}. For simplicity, you can use the label from the x_mask, I think the program may seems like #5

Open chezhizhong opened 5 years ago

chezhizhong commented 5 years ago

could you share the cls_labels.npy? thank you

Chenfeng1271 commented 5 years ago

It could be got by the hint the writer provided. It's easy, but as he says the result doesn't get a higher accuracy but it can converge faster.

zhudahui commented 4 years ago

name 'multi_hot' is not defined,what should I do.

nazim1021 commented 4 years ago

Hi, @JaveyWang

Is this possible to recreate cls_labels.npy, ? I tired with muli-hot encoder (assuming it is one hot encoding), it doesn't work. May you please help if there is any other way to get that cls_labels