Instructions to use zeyuren2002/EvalMDE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use zeyuren2002/EvalMDE with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("zeyuren2002/EvalMDE", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
| """ data sample | |
| """ | |
| class Sample(): | |
| def __init__(self, img=None, | |
| depth=None, depth_mask=None, | |
| normal=None, normal_mask=None, | |
| intrins=None, flipped=False, | |
| dataset_name='dataset', scene_name='scene', img_name='img', | |
| info={}): | |
| self.img = img # input image | |
| self.depth = depth # depth - GT | |
| self.depth_mask = depth_mask # depth - valid_mask | |
| self.normal = normal # surface normals - GT | |
| self.normal_mask = normal_mask # surface normals - valid_mask | |
| self.intrins = intrins # camera intrinsics | |
| self.flipped = flipped # True when the image is flipped during augmentation | |
| self.dataset_name = dataset_name | |
| self.scene_name = scene_name | |
| self.img_name = img_name | |
| # other info (this is a dict containing any additional information) | |
| self.info = info |