CGNet
CGNet copied to clipboard
CGNet: A Light-weight Context Guided Network for Semantic Segmentation [IEEE Transactions on Image Processing 2020]
Hello, could you please teach me to solve this problem? Thank you!
gtFine/train/cologne/cologne_000000_000019_gtFine_labelTrainIds.png 文本cityscapes_train_list.txt的文件和数据集不对应啊,数据集中图片是对的 但是标签没有对应上
Set the gpu_nums even if the device_count is 1 or less. This line has to be there when training on a single gpu.
Can anyone help me in downloading the weights from baidu's site ?
what is the format of ''cityscapes_train_list.txt''?
For Camvid dataset, there are 0-11, 12 classes, isn't it? If the number of label is less, the confusion matrix seems not to be correct.