pytorch-semseg
pytorch-semseg copied to clipboard
meetps
Semantic Segmentation Architectures Implemented in PyTorch
Hi, I am trying to reproduce the results in the [PAMI version of the FCN paper](https://arxiv.org/pdf/1605.06211.pdf), training fcn8s on Pascal VOC with the default setting. In the paper (Table 4),...
Hi, I got validation result of ~ 78% for mIoU on cityscapes with pspnet model, but when I try to finetune this model on the training set of cityscapes, after...
Hi thanks for your work! I'm using the provided pspnet_101_pascalvoc.pth file for validating. The IoU is, however , below 5%. On Cityscapes everything works fine. Someone has a hint?
I am trying to get the labelled output using the trained model. The test.py only provides the RGB output. Is there an easy way to get the labelled outputs of...
Just wondering if you have any available config file to use the unet. The current config file for fcn8 throws an error in the unetUp because the two outputs differ...
I am having trouble loader the ADE20K data. Can anyone provide an example of how to load the ADE20K data? Thanks.
i trained with a iteration of 100000,and i use the pkl to test a img,but the result is like this,what's going on? 
hi, thank you for your excellent work, but I want to know that what is the performace corresponding to all models.
If I use the SenNet, do I need to compute the classweighting mentioned in the paper?
