ydhong_hit

Anyone reproduced the results of resnet101-ocr on pascal context or ade20k dataset? 54.8%mIoU and 45.3%mIoU

Can I directly submit the output results of test.py to cityscapes official server for evaluation?

from __future__ import absolute_import from __future__ import division from __future__ import print_function import os import logging import functools import numpy as np import torch import torch.nn as nn import torch._utils...

The shell raises the error that " FileNotFoundError: [Errno 2] No such file or directory: './VOC2007/test/Annotations/' ". How can I solve this problem?

Could you release the results of BEiT-B+UperNet on cocostuff-10k and pascal context?

Could you provide some results to demonstrate the performance gain when adding the OCR module on semantic segmentation tasks? Due to the wide usage of self-attention in backbone, is it...

Could you share the codes for feature visualization in your paper?

The training resolution of ade20k

1

For the results of resnest on ade20k, what is the base-size and crop-size? Thanks for your reply!

Does anyone run this code based on mmsegmentation? How about the performance?