Visual-Attention-Network/SegNeXt
Official Pytorch implementations for "SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation" (NeurIPS 2022)
PythonApache-2.0
Issues
- 1
- 0
- 0
Config file for the i-SAID dataset
#62 opened by giuseppemartino26 - 0
How to stop shuffle for test.py
#61 opened by matz23 - 0
Evaluation Result on Cityscapes
#60 opened by 554773162 - 0
- 0
The paddlepaddle version of SegNeXt
#50 opened by Asthestarsfalll - 1
MACs, not FLOPs
#49 opened by 3maoyap - 0
about AttentionModule
#58 opened by qiaoqiangPro - 0
- 1
ImportError: cannot import name 'revert_sync_batchnorm' from 'mmcv.cnn.utils'
#56 opened by GraceGuoo - 1
Comparison with SegFormer-B5
#55 opened by ArlenCHEN - 0
- 1
How to start training?
#53 opened by sdpscnc - 3
- 0
Welcome update to OpenMMLab 2.0
#51 opened by vansin - 3
Config for Pascal VOC
#30 opened by jun0kim - 1
- 1
Random seeds variance
#48 opened by BaiZec - 2
Is it possible to export SegNeXt as ONNX or tensorrt model to speedup inferencing?
#25 opened by chenxinfeng4 - 0
when I set the "--gpu-id", default=2, I meet this problem. only "--gpu-id", default=0. I can train the model.
#47 opened by zoufeng2416 - 1
the result of SegNeXt training on ADE20k
#39 opened by jiawen1929 - 2
Weights for the COCOStuff dataset
#45 opened by edwardyehuang - 0
a question about your paper
#44 opened by massica17 - 0
- 0
有没有不包含mmseg的版本?
#42 opened by lindadamama - 0
- 0
pad bug, when use pad,iou is error
#41 opened by yeyan00 - 3
- 8
problem about train.py
#38 opened by jiawen1929 - 3
Cannot reproduce your results
#36 opened by il1um - 1
- 3
ImageNet pretrainning configurations
#33 opened by rayleizhu - 3
Learning Rate and Batch Size
#32 opened by FabianSchuetze - 0
About the training process's error
#34 opened by Onehundred0906 - 7
about train?
#29 opened by Onehundred0906 - 0
hi ,please help me
#31 opened by wudizuixiaosa - 1
About multi-scale branch
#28 opened by go-ahead-maker - 1
- 1
about the inference speed
#27 opened by Onehundred0906 - 4
Why are the results of Mit's Params not consistent with the results presented in the paper, Segformer?
#24 opened by HuCaoFighting - 1
- 5
Contribute to mmsegmentation
#18 opened by FabianSchuetze - 1
how can i do distributed training ?
#20 opened by Yaoxingtian - 1
- 2
about the test command(only one gpu)
#21 opened by Onehundred0906 - 3
- 2
Are params really exact?
#17 opened by Monkey0806 - 0
how to get mscan_t.pth?
#16 opened by AnRanbel - 4
Hello, can you support binary segmentation dataset? 0 or 255(eg: Medical Image Segmentation)
#15 opened by zwb170010