awesome-semantic-segmentation-pytorch
awesome-semantic-segmentation-pytorch copied to clipboard
Semantic Segmentation on PyTorch (include FCN, PSPNet, Deeplabv3, Deeplabv3+, DANet, DenseASPP, BiSeNet, EncNet, DUNet, ICNet, ENet, OCNet, CCNet, PSANet, CGNet, ESPNet, LEDNet, DFANet)
Hi, I want to directly eval model. Do you provice complete 'fcn' pretrained model? I cannot find it any where.
I face the same performance gap between pytorch and tensorflow and have no ideas to fix the problem. Ho did you solve the problem ?
how can i get the pretrained weights for biseNet, not for ResNet?
When I tried to train the deeplabv3 model by: python train.py --model deeplabv3_plus --backbone resnet50 --dataset ade20k --lr 0.0001 --epochs 50 it reports that: model = Xception65(**kwargs) TypeError: __init__() got...
please add pretrain xception base model ~~ tks
请问一下有没有用自己数据集训练的,分割结果好差,有没有什么改进的方法
Hi, "`python3 demo.py --model fcn32s_vgg16_voc --input-pic ./datasets/test.png`" running. Error Code: ``` Traceback (most recent call last): File "demo.py", line 58, in demo(args) File "demo.py", line 44, in demo model =...
from core.nn import_C ImportError:libcudart.so.9.0: cannot open shared object file :No such file or directory. 请问这是什么错误?
进行改进实验
in the paper of fcn(Fully convolutional networks for semantic segmentation),the authors report that they can get 62.2 mIOU(fcn-8s) on VOC2012 test. But your result of fcn can not reach that...