谢昕辰

> @xiexinch solution provided for converting labels, could you review this PR? > > reference: https://github.com/navganti/kitti_scripts/blob/master/semantics/devkit/kitti_relabel.py Thanks for updating this PR, we'll review it asap. :)

Hi @FranzEricSchneider Sorry for the late reply. It seems like the data type of tensor is not matching with the module weights' data type causes this error. I think you...

Hi @TimoK93 Sorry for the late reply. I think the modifications you want are somewhat similar to the [BiSeNetV1](https://github.com/open-mmlab/mmsegmentation/blob/master/mmseg/models/backbones/bisenetv1.py) and [ICNet](https://github.com/open-mmlab/mmsegmentation/blob/master/mmseg/models/backbones/icnet.py), this is indeed a convenient solution. https://github.com/open-mmlab/mmsegmentation/blob/85569442b659fa59a51a88449689b2aa1603e4ba/mmseg/models/backbones/bisenetv1.py#L274 https://github.com/open-mmlab/mmsegmentation/blob/85569442b659fa59a51a88449689b2aa1603e4ba/mmseg/models/backbones/icnet.py#L20

Hi @FranzEricSchneider Sorry for the late reply. Your requirement is similar to the visualization feature in MMGeneration. https://github.com/open-mmlab/mmgeneration/blob/master/mmgen/core/hooks/visualize_training_samples.py#L12 I'll try to test this feature in MMSegmentation, if it works, I'll...

Hi @FranzEricSchneider We just need to make a little modification to the visualization hook implemented in MMGeneration. ```python # Modify after_train_iter to before_train_iter @master_only def before_train_iter(self, runner): """The behavior before...

Hi @cheul0518, Just like `MMSegWandbHook `, write your own hook class then register it by `HOOK`, thus the runner might find your custom hook. https://github.com/open-mmlab/mmsegmentation/blob/7a0f45ebe0c4f55c5a177a2f9b6641d0a4c044e3/mmseg/core/hook/wandblogger_hook.py#L14

Might try to use [MMSegWandbHook](https://github.com/open-mmlab/mmsegmentation/blob/c5259a0d83f7b12e5d4d50ff155b872818b3204a/mmseg/core/hook/wandblogger_hook.py#L15), you can find more info in thePR #1603 that added this feature.

Hi @lorinczszabolcs Thanks for your nice PR! Since the official [repo](https://github.com/facebookresearch/HRViT) doesn't release the pretrained weights, facebookresearch/HRViT#3, after discussion, we are considering to temporarily pending this PR. But we will...

Hi @lorinczszabolcs, sorry for the late reply. When you have finished your draft version, might create a pull request to this repository and attach this issue, we'll review it ASAP....

Hi @sherwincn We'll checkout the problem and feedback to you asap!