load cityscapes dataset

[LYJvincent]

1)Could you tell me how to load my dataset to the fast scnn network? 2) how to use the self._key = np.array([-1, -1, -1, -1, -1, -1, -1, -1, 0, 1, -1, -1, 2, 3, 4, -1, -1, -1, 5, -1, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, -1, -1, 16, 17, 18]) , the self._key come from the cityscapes.py

[Tramac]

1)Please describe your dataset in more detail. 2)The key map is used to correct the index value of cityscapes dataset.

[LYJvincent]

Thank you very much for your reply！ My dataset contains more than two categories ,just like background and defect.if i use the cityscapes.py how should i modify the cityscapes.py or the key map? thank you!!!

------------------ 原始邮件 ------------------ 发件人: "Tramac"notifications@github.com; 发送时间: 2019年7月31日(星期三) 晚上8:15 收件人: "Tramac/awesome-semantic-segmentation-pytorch"awesome-semantic-segmentation-pytorch@noreply.github.com; 抄送: "沉静的奢华"781658795@qq.com;"Author"author@noreply.github.com; 主题: Re: [Tramac/awesome-semantic-segmentation-pytorch] load cityscapesdataset (#52)

1)Please describe your dataset in more detail. 2)The key map is used to correct the index value of cityscapes dataset.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or mute the thread.

[Tramac]

Maybe refer to the pascal_voc.py better.

[LYJvincent]

ok. thank you!!!