| --- |
| pipeline_tag: depth-estimation |
| license: cc-by-nc-4.0 |
| base_model: depth-anything/Depth-Anything-V2-Base-hf |
| library_name: zeromodels |
| tags: |
| - keras |
| - zeromodels |
| - depth-anything-v2 |
| - depth-estimation |
| - arxiv:2406.09414 |
| - pytorch |
| - jax |
| - tf |
| --- |
| |
| ## ***See [our collection](https://huggingface.co/collections/zeromodels/depth-anything-v1-and-v2-6a8eaf5352197613b1655ac5) for all versions of Depth Anything V2.*** |
|
|
| # Run Depth Anything V2 with Keras 3: JAX, PyTorch, or TensorFlow |
|
|
| [](https://github.com/IMvision12/ZeroModels) [](https://imvision12.github.io/ZeroModels/depth_anything_v2/) [](https://huggingface.co/collections/zeromodels/depth-anything-v1-and-v2-6a8eaf5352197613b1655ac5) |
|
|
| # zeromodels/depth_anything_v2_base |
| |
| Paper: [Depth Anything V2 (arXiv:2406.09414)](https://arxiv.org/abs/2406.09414) · [HF Papers](https://huggingface.co/papers/2406.09414) |
| |
| Depth Anything V2 keeps V1's architecture and improves data (synthetic labels plus large-scale pseudo-labeling). Relative heads return unitless inverse depth; metric indoor/outdoor heads return metres. |
| |
| For more details on the model, please go to the upstream [model card](https://huggingface.co/depth-anything/Depth-Anything-V2-Base-hf). |
| |
| Pure-**Keras 3** conversion of [`depth-anything/Depth-Anything-V2-Base-hf`](https://huggingface.co/depth-anything/Depth-Anything-V2-Base-hf) for [zeromodels](https://github.com/IMvision12/ZeroModels). One implementation runs unmodified on **TensorFlow / Torch / JAX**. |
| |
| This is a **monocular depth** checkpoint (`DepthAnythingV2DepthEstimation`, relative). |
| |
| ## ✨ Quick start |
| |
| ```python |
| import os |
| os.environ["KERAS_BACKEND"] = "torch" # or "jax" / "tensorflow" |
|
|
| from PIL import Image |
| from zeromodels.models.depth_anything_v2 import DepthAnythingV2DepthEstimation, DepthAnythingV2ImageProcessor |
|
|
| model = DepthAnythingV2DepthEstimation.from_weights("zeromodels/depth_anything_v2_base") |
| processor = DepthAnythingV2ImageProcessor.from_weights("zeromodels/depth_anything_v2_base") |
|
|
| image = Image.open("your_image.jpg").convert("RGB") |
| output = model(processor(image)["pixel_values"], training=False) |
| depth = processor.post_process_depth_estimation( |
| output, original_size=(image.height, image.width) |
| ) |
| print(depth.shape) |
| ``` |
| |
| Load any Depth Anything V2 variant the same way with `from_weights("zeromodels/<variant>")`: |
| |
| | Variant | Hub | Output | |
| |---|---|---| |
| | `depth_anything_v2_small` | [`zeromodels/depth_anything_v2_small`](https://huggingface.co/zeromodels/depth_anything_v2_small) | relative | |
| | `depth_anything_v2_base` | [`zeromodels/depth_anything_v2_base`](https://huggingface.co/zeromodels/depth_anything_v2_base) | relative | |
| | `depth_anything_v2_large` | [`zeromodels/depth_anything_v2_large`](https://huggingface.co/zeromodels/depth_anything_v2_large) | relative | |
| | `depth_anything_v2_metric_indoor_small` | [`zeromodels/depth_anything_v2_metric_indoor_small`](https://huggingface.co/zeromodels/depth_anything_v2_metric_indoor_small) | metric indoor | |
| | `depth_anything_v2_metric_indoor_base` | [`zeromodels/depth_anything_v2_metric_indoor_base`](https://huggingface.co/zeromodels/depth_anything_v2_metric_indoor_base) | metric indoor | |
| | `depth_anything_v2_metric_indoor_large` | [`zeromodels/depth_anything_v2_metric_indoor_large`](https://huggingface.co/zeromodels/depth_anything_v2_metric_indoor_large) | metric indoor | |
| | `depth_anything_v2_metric_outdoor_small` | [`zeromodels/depth_anything_v2_metric_outdoor_small`](https://huggingface.co/zeromodels/depth_anything_v2_metric_outdoor_small) | metric outdoor | |
| | `depth_anything_v2_metric_outdoor_base` | [`zeromodels/depth_anything_v2_metric_outdoor_base`](https://huggingface.co/zeromodels/depth_anything_v2_metric_outdoor_base) | metric outdoor | |
| | `depth_anything_v2_metric_outdoor_large` | [`zeromodels/depth_anything_v2_metric_outdoor_large`](https://huggingface.co/zeromodels/depth_anything_v2_metric_outdoor_large) | metric outdoor | |
| |
| ## Tips |
| |
| - Set `KERAS_BACKEND` **before** importing Keras / zeromodels. |
| - Indoor and outdoor metric heads are not interchangeable. |
| - See [Depth Anything V2 docs]({DOCS_URL}) and [Loading Weights](https://imvision12.github.io/ZeroModels/loading_weights/). |
| - Community / upstream weights: `DepthAnythingV2DepthEstimation.from_weights("hf:depth-anything/Depth-Anything-V2-Base-hf")`. |
| |
| ## Special Thanks |
| |
| A huge thank you to the Depth Anything authors for creating and releasing these models. |
| |
| License: Apache 2.0. |
| |
