GaoZebin

Same problem, I got 75.98 mIOU in VOC without other data. In the Paper they use additional data to train, this is link to datasets [http://home.bharathh.info/pubs/codes/SBD/download.html](url).

@JamesChuanggg hello, same question to me,did you have disort it? i found a comment in this video link,"Ubuntu 16.04 set Apache2 is a little different from Ubuntu 12.04： "/var/www/" vs...

> @hanfeng0409 您好，请问您是在多大规模的数据集上跑了多少epoch后达到收敛呢 感谢您的回复。 大概3000个 数据上，现在是设置了1200个epoch，实际跑到了200个epoch，前30个epoch的loss很快从0.8降到了 0.2左右 后100个epoch loss在0.18附近震荡。