[bake] downloading inputs [bake] frames: ['eq_000122.jpg', 'eq_000358.jpg'] [gt] pano_camera00/eq_000122.jpg: 427 sparse obs [gt] pano_camera05/eq_000122.jpg: 682 sparse obs [gt] pano_camera06/eq_000122.jpg: 25 sparse obs [gt] pano_camera10/eq_000122.jpg: 28 sparse obs [gt] pano_camera00/eq_000358.jpg: 931 sparse obs [gt] pano_camera05/eq_000358.jpg: 391 sparse obs [gt] pano_camera06/eq_000358.jpg: 16 sparse obs [gt] pano_camera10/eq_000358.jpg: 3 sparse obs Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`. Device set to use cuda:0 /tmp/bakeoff_pod.py:184: DeprecationWarning: __array__ implementation doesn't accept a copy keyword, so passing copy=False failed. __array__ must implement 'dtype' and 'copy' keyword arguments. To learn more, see the migration guide https://numpy.org/devdocs/numpy_2_0_migration_guide.html#adapting-to-changes-in-the-copy-keyword disp = np.array(pred["predicted_depth"]) /usr/local/lib/python3.11/dist-packages/torch/hub.py:295: UserWarning: You are about to download and run code from an untrusted repository. In a future release, this won't be allowed. To add the repository to your trusted list, change the command to {calling_fn}(..., trust_repo=False) and a command prompt will appear asking for an explicit confirmation of trust, or load(..., trust_repo=True), which will assume that the prompt is to be answered with 'yes'. You can also use load(..., trust_repo='check') which will only prompt for confirmation if the repo is not already trusted. This will eventually be the default behaviour warnings.warn( Downloading: "https://github.com/yvanyin/metric3d/zipball/main" to /root/.cache/torch/hub/main.zip /usr/local/lib/python3.11/dist-packages/timm/models/layers/__init__.py:49: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.layers", FutureWarning) /usr/local/lib/python3.11/dist-packages/timm/models/registry.py:4: FutureWarning: Importing from timm.models.registry is deprecated, please import via timm.models warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.models", FutureWarning) xFormers not available xFormers not available xFormers not available xFormers not available Downloading: "https://huggingface.co/JUGGHM/Metric3D/resolve/main/metric_depth_vit_small_800k.pth" to /root/.cache/torch/hub/checkpoints/metric_depth_vit_small_800k.pth 0%| | 0.00/143M [00:00