-
why can not i replace the loss_decode?
loss_decode=[dict(type='CrossEntropyLoss',loss_weight=1.0),dict(type='DiceLoss', loss_weight=3.0)],#####
replace
loss_decode=dict(type='CrossEntropyLoss', use…
-
I add some custom analyzer in elasticsearch like Chinese words.
and I add them in inquisitor 's config js and I can see new add analyzer in /_plugin/inquisitor/#/analyzers tab. but it always 500 erro…
-
If my dataset is for multi-label change detection, and the labels contain values that are no longer just (0 1) or (0 255), but rather like (0 1 2 3 4 5 6) for the labels, does your code still support …
-
## ❓ Question
I was preparing to export a TRT model for Mask2Former using the command **optimized_model = torch_tensorrt.compile(model, inputs=imgs, enabled_precisions={torch.half})**, where mode…
-
Hi,
If you have experience with these, can you update a minimal code for training a custom data set, say on just 1 dummy image for 1 epoch.
For example if I want to train `SWIN-B` (or any other *…
-
Hi, I'm a big fan of **mmseg**.
I'd like to
1) **add some module(s)** based on the pre-trained model
and
2) train the model **while freezing the pre-trained weights** (except for the…
-
```
hi,
我想让分词器碰到《传奇3》、“传奇3”等这种词的时候，《
》内部的就不继续分词，而是让内部作为一个词语。
请问这在哪里可以修改一下？
```
Original issue reported on code.google.com by `sling...@gmail.com` on 17 Dec 2013 at 5:37
-
```
hi,
我想让分词器碰到《传奇3》、“传奇3”等这种词的时候，《
》内部的就不继续分词，而是让内部作为一个词语。
请问这在哪里可以修改一下？
```
Original issue reported on code.google.com by `sling...@gmail.com` on 17 Dec 2013 at 5:37
-
Your algorithm proposed in the paper is a fantastic idea. However, I have a few questions to ask you. When I use the ChangeCLIP_best_weights you provided to visualize the inference results of images i…
-
I'm trying to fine-tune a pre-trained Mask2former model on a custom dataset and I've been getting this error.
[This](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/mask2former/mask2…