-
(1)I have installed mmcv=1.4.1 and mmcv-full=1.4.0 versions, but I still encounter errors. I have tried multiple versions, but the errors persist. I would like to ask you about the specific version yo…
-
I use local_configs/segformer/B5/segformer.b5.1024x1024.city.160k.py to train a model, but the mIoU is low even after 63950 iterations:
+---------------+-------+-------+
| Class | IoU | Ac…
-
In codes,
inputs = torch.cat(inputs, dim=1)
https://github.com/Visual-Attention-Network/SegNeXt/blob/c87bcaef22ed2ad72ed3decb3727e5f879343516/mmseg/models/decode_heads/ham_head.py#L233
In…
-
I ran the b0 model on ade160k with mmseg, but the mIoU result is slightly lower than reported(36.8% and the reported result is 37.4%), I wonder if that is a normal fluctuation.
-
你好。因为你没有留邮件，只好给你发一个ticket了。
我自己也实现了一个纯Js的mmseg分词，并且API的设计也适应于Node的异步回调方式。
https://github.com/mountain/nseg
我对你的包和我的实现做了一个测试，切分一个长文本一百次：
https://github.com/mountain/nseg/blob/master/perfs/perftest.j…
-
In mmseg.distillation.losses.cwd.ChannelWiseDivergence the student softmax output is not used (also self.name):
`softmax_pred_S = F.softmax(preds_S.view(-1,W*H)/self.tau, dim=1)`
Intended or a bug?
-
Bug:
Traceback (most recent call last):
File "D:/Desktop/脚本/Adam-2训练&结果/加载3个模型/mmpose_predict_img.py", line 48, in
result = inference_model(model, img_bgr)
File "d:\desktop\science\model…
-
FileNotFoundError: [Errno 2] No such file or directory: '../open-cd/model-index.yml'
-
### Prerequisite
- [X] I have searched [Issues](https://github.com/open-mmlab/mmdetection3d/issues) and [Discussions](https://github.com/open-mmlab/mmdetection3d/discussions) but cannot get the expec…
-
## Background
Cityspace dataset에서 좋은 성능을 보이고 있는 Lawin Transformer를 mmseg 기반으로 학습시켜 보고자…