[segformer] missing keys in source state_dict

[Mizbauddin]

Hi,

I run this command to test the segformer model: python3 demo/image_demo.py demo/demo.png configs/segformer/segformer_mit-b3_8x1_1024x1024_160k_cityscapes.py pretrained/mit_b0_20220624-7e0fe6dd.pth --device cuda:0 --palette cityscapes

but I get this error:
the model and loaded state dict do not match exactly

I have seen the same issue with STDC #1303 #1418

I downloaded the pretrained weights specified in the config file. Can someone help me with this issue?

This is my system configuration:
model: jetson orin
jetpack: 5.0.2
CUDA: 8.4.1
mmseg: 0.30.0
mmcv: 1.7.0