HRNet-Semantic-Segmentation
HRNet-Semantic-Segmentation copied to clipboard
HRNet
The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919
How do I generate segmentation visualizations the 'test' block keeps getting errors all the time.  which dataset can visualize?
There is an image size parameter and a base size parameter in the experiment documentation. What's the difference?
I am inputting 512*512 image but getting out 128*128 with cityscapes/seg_hrnet_w18_small_v2_512x1024_sgd_lr1e-2_wd5e-4_bs_12_epoch484.yaml. Am i doing something wrong? I just load the config file in the model. How to get full-resolution?
Lite-HRNet's paper says that It simply reduces the depth andthe width of the original HRNet.But I don't know what the specific structure of small HRnet or HRNetw16 is.How many times...
I train the model HRNet-W48+OCR with the configuration seg_hrnet_ocr_w48_473x473_sgd_lr7e-3_wd5e-4_bs_40_epoch150, but finally only get 52% mIoU on the dataset LIP. How to deal with it? Or are there any train tips...
I had a question that arose while conducting an experiment. I would appreciate it if you could answer.
Im grateful for your free code and your job in tech! And in tools/test.py , i got a function named testval and then i got test_dataset.multi_scale_inference(). so i wanna know...
What is the reason for the fluctuation in the results after using random seeds
I was wondering if the authors experimented with LayerNorm instead of BatchNorm and if they noticed any differences? From what I've read is that BatchNorm is heavily dependent on batch...
I am searching for the onnx file of your model, but it seems that there is no ready-made one, can you provide it?
