AstarLight / Satellite-Segmentation

615 stars 233 forks source link

请问如何进行预处理啊?作者的gen_dataset就是预处理么? #34

Open GusRoth opened 5 years ago

GusRoth commented 5 years ago

还是有其他的方法先对原始数据进行处理?

MichealRay commented 5 years ago

我是直接用gen_dataset生成数据unet和segnet所需的数据的,其实就是做了简单的增强

Ophelia20444 commented 5 years ago

我是直接用gen_dataset生成数据unet和segnet所需的数据的,其实就是做了简单的增强

求助!我想借用gen_dataset.py对我下载的ISPRS的训练影像和label进行分割,但是我把图像读取的路径改了之后运行结果报错了: runfile('/media/usser/新加卷/HSS/Satellite-Segmentation-master/segnet/rawimg/gen_dataset.py', wdir='/media/usser/新加卷/HSS/Satellite-Segmentation-master/segnet/rawimg')

0%| | 0/33 [00:00<?, ?it/s]creating dataset...

3%|▎ | 1/33 [00:12<06:28, 12.13s/it]Traceback (most recent call last):

File "", line 1, in runfile('/media/usser/新加卷/HSS/Satellite-Segmentation-master/segnet/rawimg/gen_dataset.py', wdir='/media/usser/新加卷/HSS/Satellite-Segmentation-master/segnet/rawimg')

File "/opt/Anaconda3/lib/python3.7/site-packages/spyder_kernels/customize/spydercustomize.py", line 704, in runfile execfile(filename, namespace)

File "/opt/Anaconda3/lib/python3.7/site-packages/spyder_kernels/customize/spydercustomize.py", line 108, in execfile exec(compile(f.read(), filename, 'exec'), namespace)

File "/media/usser/新加卷/HSS/Satellite-Segmentation-master/segnet/rawimg/gen_dataset.py", line 104, in creat_dataset(mode='augment')

File "/media/usser/新加卷/HSS/Satellite-Segmentation-master/segnet/rawimg/gen_dataset.py", line 86, in creat_dataset label_roi = label_img[random_height: random_height + img_h, random_width: random_width + img_w]

TypeError: 'NoneType' object is not subscriptable

求助这个问题该怎么解决啊?

MichealRay commented 5 years ago

hi,Ophelia20444 . 你试试runfile(r'/media/usser/新加卷/HSS/Satellite-Segmentation-master/segnet/rawimg/gen_dataset.py', wdir=r'/media/usser/新加卷/HSS/Satellite-Segmentation-master/segnet/rawimg')

Ophelia20444 commented 5 years ago

谢谢,我还在继续尝试!

------------------ 原始邮件 ------------------ 发件人: "ZKL"notifications@github.com; 发送时间: 2019年4月22日(星期一) 上午8:32 收件人: "AstarLight/Satellite-Segmentation"Satellite-Segmentation@noreply.github.com; 抄送: "蝴蝶骨"shanshan_han@foxmail.com; "Comment"comment@noreply.github.com; 主题: Re: [AstarLight/Satellite-Segmentation] 请问如何进行预处理啊?作者的gen_dataset就是预处理么? (#34)

hi,Ophelia20444 . 你试试runfile(r'/media/usser/新加卷/HSS/Satellite-Segmentation-master/segnet/rawimg/gen_dataset.py', wdir=r'/media/usser/新加卷/HSS/Satellite-Segmentation-master/segnet/rawimg')

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

xyh-qz commented 5 years ago

谢谢,我还在继续尝试! ------------------ 原始邮件 ------------------ 发件人: "ZKL"notifications@github.com; 发送时间: 2019年4月22日(星期一) 上午8:32 收件人: "AstarLight/Satellite-Segmentation"Satellite-Segmentation@noreply.github.com; 抄送: "蝴蝶骨"shanshan_han@foxmail.com; "Comment"comment@noreply.github.com; 主题: Re: [AstarLight/Satellite-Segmentation] 请问如何进行预处理啊?作者的gen_dataset就是预处理么? (#34) hi,Ophelia20444 . 你试试runfile(r'/media/usser/新加卷/HSS/Satellite-Segmentation-master/segnet/rawimg/gen_dataset.py', wdir=r'/media/usser/新加卷/HSS/Satellite-Segmentation-master/segnet/rawimg') — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or mute the thread.

你好,我也遇到了这个问题,请问你是怎么解决的

Ophelia20444 commented 5 years ago

谢谢,我还在继续尝试! ------------------ 原始邮件 ------------------ 发件人: "ZKL"notifications@github.com; 发送时间: 2019年4月22日(星期一) 上午8:32 收件人: "AstarLight/Satellite-Segmentation"Satellite-Segmentation@noreply.github.com; 抄送: "蝴蝶骨"shanshan_han@foxmail.com; "Comment"comment@noreply.github.com; 主题: Re: [AstarLight/Satellite-Segmentation] 请问如何进行预处理啊?作者的gen_dataset就是预处理么? (#34) hi,Ophelia20444 . 你试试runfile(r'/media/usser/新加卷/HSS/Satellite-Segmentation-master/segnet/rawimg/gen_dataset.py', wdir=r'/media/usser/新加卷/HSS/Satellite-Segmentation-master/segnet/rawimg') — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or mute the thread.

你好,我也遇到了这个问题,请问你是怎么解决的

嗯……我是把所有用cv2的命令都改为pillow调用……因为还没找到原因

8023AiCGZ commented 4 years ago

gen_dataset切割后的label和src没有了坐标系,打开后label1和src1、label2和src2、label3和src3、、、、、、、都不是一一对应的,这个对结果没有影响吗