lucidrains segformer-pytorch issues - Githubissues

lucidrains / segformer-pytorch

Implementation of Segformer, Attention + MLP neural network for segmentation, in Pytorch

MIT License

342 stars 43 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

where are the pre-training weights？

#14 TheWangYang opened 7 months ago
0
pretrain weight

#13 Philos01 opened 12 months ago
0
how to use pre_trained weights?

#12 dmndxld opened 1 year ago
0
Create 1.py

#11 Smartzzh opened 1 year ago
0
batchNorm or layerNorm？

#10 Napier7 opened 2 years ago
0
how 2 ouput origin h w size？

#9 York1996OutLook opened 3 years ago
2
Something is wrong with your implementation.

#8 camlaedtke opened 3 years ago
0
Why you use InstanceNorm instead of LayerNorm?

#7 takfate closed 3 years ago
1
patch size not used

#6 isega24 closed 3 years ago
1
Models weights + model output HxW

#5 isega24 opened 3 years ago
2
The model configurations for all the SegFormer B0 ~ B5

#4 rose-jinyang opened 3 years ago
5
a question about kv reshape in Efficient Self-Attention

#3 masszhou opened 3 years ago
1
i find the decoder which in your implementation is conv2d,and it is different with MPLDecoder which used in segformer paper ?

#2 AncientRemember opened 3 years ago
7
are the imgsize parameter of MixVisionTransformer is necessary？

#1 AncientRemember closed 3 years ago
1