BayMax

Results 7 issues of BayMax

I attempted to test the NYU dataset using the provided weight file and obtained a result that was consistent with 85.17 in the paper. But when I tried to train...

After setting up the environment, I used NYU dataset for training, but the training results were very strange. The loss function converged slowly, rmse kept increasing, and delta kept decreasing.

### Prerequisite - [X] I have searched [Issues](https://github.com/open-mmlab/mmengine/issues) and [Discussions](https://github.com/open-mmlab/mmengine/discussions) but cannot get the expected help. - [X] The bug has not been fixed in the latest version(https://github.com/open-mmlab/mmengine). ### Environment...

bug

### What is the feature? The config file is really nice in python format, making the config file easy to view. I also use multiple config merges frequently. The experiment-config...

### What is the feature? In the training process, commonly used to save the file structure: config dump -> workdir log.txt -> _log_dir(workdir+tempstemp) checkpoint(best) -> workdir checkpoint(iter、epoch)and txt -> workdir...

### Description The existing markdown titles differ very little between different levels, and if you can customize the color, or other distinctions, it helps to enrich the performance of the...

story

### Description ![image](https://github.com/user-attachments/assets/de20e172-75cd-47ef-9a11-209b2541ddce) Can the editing method of EquationBlock be as wide as that of CodeBlock? When editing is finished, a button can be set to express editing completion and...

story