Marigold

Marigold copied to clipboard

Why the inference sometimes outputs a depth map and sometimes outputs a parallax map?

1

zzcml

About Recovering the Depth with Metirc.

1

Thank you for your outstanding work! It is very impressive to deploy a diffusion pipeline into monocular depth estimation. As stated in the paper, the model works for affine-invariance depth...

Magicboomliu

pass invariance flag through model_index.json support scale-invariant mode

markkua

noob questions about code understanding.

3

I've been studying the train.py code and I can't figure out this: If we continue resume training from a checkpoint, then we need to retrieve wandb_id from the WAND_ID file...

YacineDeghaies

Questions about LCM model training

1

Hi! I'm trying to train the LCM model. However, the model I trained is worse than the LCM model you released. Could you give more training details about LCM distillation...

luochunfen

Dear Authors, Thank you for presenting this model. It is indeed a good model for downstream tasks. I have used your model for 3D reconstruction on my own data, and...

shiliu0111

I am getting the following error in the validation step: AssertionError: Wrong input shape torch.Size([3, 768, 1024]), expected [1, rgb, H, W] In marigold_trainer.py function validate_single_dataset(), the input image is...

Keivin98

Data cannot be read during training

1

I just used the vkitti dataset, RGB data path for autodl - TMP/Marigold - main/vkitti/vkitti tar/vkitti/RGB, The depth data path for autodl - TMP/Marigold - main/vkitti/vkitti tar/vkitti/the depth.When I run...

dongyyyy

How to train this code on multi-GPUs?

Smarome

About some problems that arise during training

9

 My system is Ubantu 20.04.1, and the training environment is GeForce RTX3090, python 3.10, CUDA=11.7. I used the command ```python train.py--config config/train_marigold.yaml --no_wandb ```to start the project and it...

water221