-
Dear authors:
Congratulations on your excellent results on DiNAT.
However, I think the idea of this paper is similar as [VAN](https://arxiv.org/abs/2202.09741), [Code](https://github.com/Visual-…
-
Hi,
Thank you for the work and sharing code!
I find it very helpful :)
I have one question though,
I am trying to reproduce your result on ResNet50 + Potsdam dataset (Semantic segmentation), so …
-
Dear Sir or Madam,
i am training a PointNet++ architecture now for many weeks. However training does not converge at all. The datset contains 100 unique pointclouds (pc_size: 2000 or 20.000) and wi…
-
### What happened + What you expected to happen
My pytorch ray training program is crashing with segfault in dataloader workers after 2 - 3 minutes. It works when num_workers = 0. I have stripped …
-
Hi,
I used your default config to train the model. After about 40 epochs, overfitting began to occur. After 100 epochs, the best reslut of it still cannot achieve the metrics of pratrained model, an…
-
## 📚 Documentation
For now I have used ResUnet for my line segment part in table reconstruct project. The input image size for training is 256x256. When I pass an image (with original size is 535x269…
-
I wish to train HRNetV2-W18-Small-v2 on a custom dataset with just person class from scratch. How to achieve this?
My dataset would be similar to [Supervisely Person Dataset](https://supervise.ly/e…
-
Example: https://mila.quebec/en/publications/
It would be nice to reuse the same code as in the Mila website. Not sure if that's 'easily' possible via RTD
-
Hi, the CVAT team!
I really love the features in CVAT and how intuitive they are, great job!
For my project, I already generated some auto labels using a simple neural network model. But I would…
-
I've been working on applying Hamburger to other detection models (to be specific, Mask2Former & SparseInst), mainly by inserting Hamburger after the neck to align the multi-scale features, but the tr…