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)
I meet errors during installation when building syncbn Is this module necessary? According to the documents ,pytorch now have the syncbn. How should I solve this problem? Thanks > `G:/anaconda/lib/site-packages/torch/include\torch/csrc/jit/script/module.h(467):...
I found that many models did not seem to achieve the results in the original paper. Not enough epoch?
There is a tiny bug in the function validation() within train.py. save_checkpoint() should just be implemented when save_to_disk is True.
![image](https://user-images.githubusercontent.com/44438364/60708264-3a848f00-9f40-11e9-83df-4d0cefe8c2fb.png)
我换成了我的灰度图的数据集之后,然后一直报错,改了又错,错了又改,主要问题有维度参数,通道数,我改了,最后报错指向环境包文件,试了各种方法。最终还是没有解决。主要涉及文件dataloader里面的自己数据文件.py,segbase.py,train,py。 想问作者,换成[1,512,512]的灰度图后,需要改哪些地方?
Hello Sir, I saw test-case of your code. (core/models/model_zoo.py) ''' _models = { 'fcn32s_vgg16_voc': get_fcn32s_vgg16_voc, 'fcn16s_vgg16_voc': get_fcn16s_vgg16_voc, 'fcn8s_vgg16_voc': get_fcn8s_vgg16_voc, 'fcn_resnet50_voc': get_fcn_resnet50_voc, 'fcn_resnet101_voc': get_fcn_resnet101_voc, 'fcn_resnet152_voc': get_fcn_resnet152_voc, 'psp_resnet50_voc': get_psp_resnet50_voc, 'psp_resnet50_ade': get_psp_resnet50_ade, 'psp_resnet101_voc':...
Hi there, I'm getting this error "undefined symbol: _ZN3c1011CPUTensorIdEv". Although I have followed setup instructions correctly, and it installs everything without any error or warning. But when I'm trying to...
Hi, I just had a question about the dataset classes. In some of the classes like the cityscapes dataset, the labels are being mapped to negative keys. Why is that...
``` (torchpy3) chiot@chiot-AI:~/Desktop/SemSeg/awesome-semantic-segmentation-pytorch/scripts$ python train.py --model psp --backbone resnet50 --dataset pascal_voc --lr 0.0001 --epochs 50 2020-03-02 17:38:57,152 semantic_segmentation INFO: Using 1 GPUs 2020-03-02 17:38:57,152 semantic_segmentation INFO: Namespace(aux=False, aux_weight=0.4, backbone='resnet50', base_size=520,...
Thanks for your nice work! How to measure mIOU in the test set of cityscapes?