awesome-semantic-segmentation-pytorch
awesome-semantic-segmentation-pytorch copied to clipboard
Tramac
Semantic Segmentation on PyTorch (include FCN, PSPNet, Deeplabv3, Deeplabv3+, DANet, DenseASPP, BiSeNet, EncNet, DUNet, ICNet, ENet, OCNet, CCNet, PSANet, CGNet, ESPNet, LEDNet, DFANet)
Hi, Could you please provide the way your dataset is arranged/ structured in your directory (i.e. train data, validation data and test data). I tried running the downloading script to...
选择了deeplabv3_resnet50_pascal_voc从头训练了一个权重，在使用demo.py测试的时候发现输出的pred值全为0。不确定是因为自己训练的权重问题还是其它原因。想用预训练权重测试下这个问题但没找到下载链接，求预训练权重deeplabv3_resnet50_pascal_voc.pth的下载地址？
DeepLabV3+, the backbone can only use Xception, and other backbones cannot be selected 
I want to use this model on my own dataset,but I don't know how to modify the part of loading dataset,may I ask you some questions? thank you very much.
ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 256, 1, 1])
运行到url下载的时候报错说ssl连接有问题访问不到那个网站，把网址名在浏览器搜索后也找不到这个网站，有大佬有解决的办法吗
