baibizhe comments

Results 17 comments of


                                            baibizhe

Question on extreme result of my own data

> 哈喽你可以加我微信我发你语音方便一点 byl95899589

callback_get_label no longer works as described

Same

Does val_dataset need balanced sampler?

No.

add support for UNET++

> Thank you for the information, @ericspod. Hello .I would really like to do contibution on this issues. Is there anything that I could do about this issue? I am...

add support for UNET++

> Hi @baibizhe, thanks for your interest here. There's a basic UNet implementation in MONAI, the goal was to create an easy-to-understand baseline but with some price in flexibility >...

GPU memory of ZeroDepth

> I'm seeing this same issue > > Have you found a solution? Not yet

Please update documentation with more details on training the other midas backbones

> scenes = [u''.join(chr(c[0]) for c in h5_file[obj_ref][:]) for obj_ref in h5_file['sceneTypes'][0]] Thanks!

[Fix/Train] `image_processor` is missing in `get_mimicit_dataset`

But [get_mimicit_dataset](https://github.com/Luodian/Otter/blob/main/pipeline/train/data.py#L607) haven't used the image processor . Is that right?

[Fix/Train] `image_processor` is missing in `get_mimicit_dataset`

Thanks

[Fix/Train] `image_processor` is missing in `get_mimicit_dataset`

So.If mimict_dataset does not use clip image processor. However , in [otter_video.py](https://github.com/Luodian/Otter/blob/main/pipeline/demo/otter_video.py) .It do use a clip image processor. Why is this?