-
hi, when i try to reproduce your work for retraining on cityscapes dataset. It seems like I still miss one checkpoint. Can you help me to tackle this problem? thank you!
-
### Describe the bug
A clear and concise description of what the bug is.
When I ran the script pruning/get_channel_units.py, I got this error: TypeError: expected Tensor as element 0 in argument…
-
您好，请问一下您的mmseg的版本是多少呀，因为在导入预训练模型的时候提示没有安装mmseg，但是安装了以后不知道为什么导不了from mmseg.models.builder import build_backbone as seg_BACKBONES这个，麻烦您有空解答一下谢谢
-
Thanks for your great work!
In segmention/mmseg/models/deformable_head_with_time.py, the input augments are "query","key","value","time" , etc in self.encoder function, line 119. But, in mmcv packa…
-
我想用Vmaba作为Backbone做分割，请问您注释掉的MMSEG_VSSM相对于MMDET_VSSM，有何改变呢。
-
Same as the title.
Ako-r updated
5 months ago
-
### Describe the question you meet
Can autoslim be used on mmsegmentation models like [pspnet](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/pspnet) or [segformer](https://github.c…
-
I'm sorry to ask you something, but when running the "train.py" file, the last sentence "runner.run(data_loaders, cfg.workflow)" in the function "train" gives the following error:
- mmseg - INF…
-
Hi, when I train SegFormer-B1 on cityscapes:
预训练模型路径：
./SegFormer/pretrained/mit_b1.pth
执行脚本：
cd SegFormer
python tools/train.py local_configs/segformer/B1/segformer.b1.1024x1024.city.160k.py
…
znshi updated
8 months ago
-
Hi,
I didn't find any information about how to train on a new dataset. I tried created a new dataset file to mmseg/datasets with @DATASETS.register_module() call and I updated the mmseg/datasets/__in…