segmentation_pytorch icon indicating copy to clipboard operation
segmentation_pytorch copied to clipboard

semantic segmentation pytorch 语义分割

Results 6 segmentation_pytorch issues
Sort by recently updated
recently updated
newest added

![image](https://user-images.githubusercontent.com/40490367/177684462-1c80e95f-a4c7-4493-8bfa-250928f7d89f.png) ![f5a0c2838c2cd1b57c1dc8c9d2c6f38](https://user-images.githubusercontent.com/40490367/177684522-db45f3fa-3a0e-46a5-a016-f0e3c3eacb9e.png) loss回传时突然从tensor转成地址了

您好,我做的是二值的语义分割,0为背景(黑色),1为标签(白色),您在图像增强脚本里说对于旋转,偏移等操作,会引入黑边(均为0值),将引入的黑边 视为1类,标签值默认为0,真实标签从1开始,引入的黑边为1类,导致我分割出的图全为白色,请问这个问题怎么修改呢

我用了您的代码跑了您的data里的几张图片 发现会在for step, data in enumerate(data_loader['train'])这步报错,原因是 Traceback (most recent call last): File "D:/cc/segmentation_pytorch-master/main.py", line 80, in main(args) File "D:/cc/segmentation_pytorch-master/main.py", line 66, in main train(data_loader, model, optimizer, scheduler, tb_writer, param_dict, continue_epoch)...

老哥,你遇到过这个问题吗,我看了一下rotate这个函数确实是有fill参数的,为啥还会报这个错呢