Views
No views yet
depth-anything/Depth-Anything-V2-Metric-Hypersim-Small
(indoor metric depth, max_depth = 20 m). Exported so it can run on
onnxruntime (CPU/Node) without a PyTorch dependency.depth_anything_v2_metric_hypersim_vits.pth.torch.onnx.export, opset 17, static input 1 × 3 × 518 × 518, constant-folded.< 1e-3.pixel_values: 1 × 3 × 518 × 518, RGB, ImageNet-normalized
(mean [0.485, 0.456, 0.406], std [0.229, 0.224, 0.225]).predicted_depth: 1 × 518 × 518, metric depth in metres,
range (0, 20); larger = farther.1import onnxruntime as ort, numpy as np
2sess = ort.InferenceSession("model.onnx", providers=["CPUExecutionProvider"])
3depth = sess.run(None, {"pixel_values": x})[0] # x: 1x3x518x518 float321@article{depth_anything_v2,
2 title={Depth Anything V2},
3 author={Yang, Lihe and Kang, Bingyi and Huang, Zilong and Zhao, Zhen and Xu, Xiaogang and Feng, Jiashi and Zhao, Hengshuang},
4 journal={arXiv:2406.09414},
5 year={2024}
6}