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
| from evalmde.utils.depth import load_data | |
| # gt_depth, gt_intr, gt_valid = load_data('sample_data/gt_depth.npz') | |
| # pr_depth, pr_intr, pr_valid = load_data('sample_data/curv_low_freq__0.200_10.0.npz') | |
| gt_depth, gt_intr, gt_valid = load_data('sample_data_2/gt_depth.npz') | |
| pr_depth, pr_intr, pr_valid = load_data('sample_data_2/depthpro_gt_focal.npz') | |
| from evalmde.metrics.rel_normal import compute_rel_normal | |
| from evalmde.metrics.sawa_h import compute_sawa_h | |
| sawa_h = compute_sawa_h(pr_depth, pr_intr, pr_valid, gt_depth, gt_intr, gt_valid) | |
| rel_normal = compute_rel_normal(pr_depth, pr_intr, pr_valid, gt_depth, gt_intr, gt_valid) | |
| print(f'{sawa_h=}, {rel_normal=}') | |