Depth Anything V1 and V2
Collection
12 items • Updated
See our collection for all versions of Depth Anything V2.
Run Depth Anything V2 with Keras 3: JAX, PyTorch, or TensorFlow
kerasformers/depth_anything_v2_base
Paper: Depth Anything V2 (arXiv:2406.09414) · HF Papers
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.
Pure-Keras 3 conversion of depth-anything/Depth-Anything-V2-Base-hf for kerasformers. One implementation runs unmodified on TensorFlow / Torch / JAX.
This is a monocular depth checkpoint (DepthAnythingV2DepthEstimation, relative).
✨ Quick start
import os
os.environ["KERAS_BACKEND"] = "torch" # or "jax" / "tensorflow"
from PIL import Image
from kerasformers.models.depth_anything_v2 import DepthAnythingV2DepthEstimation, DepthAnythingV2ImageProcessor
model = DepthAnythingV2DepthEstimation.from_weights("kerasformers/depth_anything_v2_base")
processor = DepthAnythingV2ImageProcessor.from_weights("kerasformers/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("kerasformers/<variant>"):
| Variant | Hub | Output |
|---|---|---|
depth_anything_v2_small |
kerasformers/depth_anything_v2_small |
relative |
depth_anything_v2_base |
kerasformers/depth_anything_v2_base |
relative |
depth_anything_v2_large |
kerasformers/depth_anything_v2_large |
relative |
depth_anything_v2_metric_indoor_small |
kerasformers/depth_anything_v2_metric_indoor_small |
metric indoor |
depth_anything_v2_metric_indoor_base |
kerasformers/depth_anything_v2_metric_indoor_base |
metric indoor |
depth_anything_v2_metric_indoor_large |
kerasformers/depth_anything_v2_metric_indoor_large |
metric indoor |
depth_anything_v2_metric_outdoor_small |
kerasformers/depth_anything_v2_metric_outdoor_small |
metric outdoor |
depth_anything_v2_metric_outdoor_base |
kerasformers/depth_anything_v2_metric_outdoor_base |
metric outdoor |
depth_anything_v2_metric_outdoor_large |
kerasformers/depth_anything_v2_metric_outdoor_large |
metric outdoor |
Tips
- Set
KERAS_BACKENDbefore importing Keras / kerasformers. - Indoor and outdoor metric heads are not interchangeable.
- See Depth Anything V2 docs and 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.
- Downloads last month
- 588
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for zeromodels/depth_anything_v2_base
Base model
depth-anything/Depth-Anything-V2-Base-hf
# Install from https://github.com/DepthAnything/Depth-Anything-V2 # Load the model and infer depth from an image import cv2 import torch from depth_anything_v2.dpt import DepthAnythingV2 # instantiate the model model = DepthAnythingV2(encoder="<ENCODER>", features=<NUMBER_OF_FEATURES>, out_channels=<OUT_CHANNELS>) # load the weights filepath = hf_hub_download(repo_id="zeromodels/depth_anything_v2_base", filename="depth_anything_v2_<ENCODER>.pth", repo_type="model") state_dict = torch.load(filepath, map_location="cpu") model.load_state_dict(state_dict).eval() raw_img = cv2.imread("your/image/path") depth = model.infer_image(raw_img) # HxW raw depth map in numpy