zeromodels / tipsv2-b14-dpt

huggingface.co
Total runs: 37
24-hour runs: 0
7-day runs: 2
30-day runs: 29
Model's Last Updated: August 27 2026
depth-estimation

Introduction of tipsv2-b14-dpt

Model Details of tipsv2-b14-dpt

See our collection for all versions of TIPSv2-DPT.

Run TIPSv2-DPT with Keras 3: JAX, PyTorch, or TensorFlow

GitHub Collection

zeromodels/tipsv2-b14-dpt

Paper: TIPSv2 (arXiv:2604.12012)

TIPSv2-DPT stacks DPT (Dense Prediction Transformer) heads on the TIPSv2 vision backbone. This single checkpoint serves three task classes: monocular depth estimation and semantic segmentation, or both at once.

For more details on the model, please go to the upstream model card .

Pure- Keras 3 conversion of google/tipsv2-b14-dpt for zeromodels . One implementation runs unmodified on TensorFlow / Torch / JAX .

✨ Quick start
import os
os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"

from PIL import Image
import numpy as np
import keras
from zeromodels.models.tipsv2_dpt import (
    Tipsv2DptDensePredict,        # depth + segmentation
    Tipsv2DptDepthEstimation,     # depth only
    Tipsv2DptSemanticSegment,     # segmentation only
    Tipsv2DptImageProcessor,
)

# all three load from the SAME repo
model = Tipsv2DptDensePredict.from_weights("zeromodels/tipsv2-b14-dpt")
proc = Tipsv2DptImageProcessor(image_resolution=448)

image = Image.open("your_image.jpg").convert("RGB")
pixel_values = proc(np.array(image))["pixel_values"]
out = model(pixel_values)
depth = keras.ops.convert_to_numpy(out["predicted_depth"])          # (1, H', W')
seg = keras.ops.convert_to_numpy(out["segmentation_logits"])        # (1, H', W', num_labels)

# single-task variants (same weights, one output each)
depth_model = Tipsv2DptDepthEstimation.from_weights("zeromodels/tipsv2-b14-dpt")
seg_model = Tipsv2DptSemanticSegment.from_weights("zeromodels/tipsv2-b14-dpt")

Variants:

Tips
  • Set KERAS_BACKEND before importing Keras / zeromodels.
  • The image processor rescales to [0, 1] (no mean/std normalization); input resolution is 448.
  • Outputs are at the DPT feature resolution; resize to the input size for visualization.
  • Upstream checkpoint: Tipsv2DptDensePredict.from_weights("hf:google/tipsv2-b14-dpt") .
Special Thanks

A huge thank you to the TIPSv2 authors (Google DeepMind) and the HF community.

License: Apache-2.0 (matches the upstream google/tipsv2-b14-dpt checkpoint).

Runs of zeromodels tipsv2-b14-dpt on huggingface.co

37
Total runs
0
24-hour runs
1
3-day runs
2
7-day runs
29
30-day runs

More Information About tipsv2-b14-dpt huggingface.co Model

More tipsv2-b14-dpt license Visit here:

https://choosealicense.com/licenses/apache-2.0

tipsv2-b14-dpt huggingface.co

tipsv2-b14-dpt huggingface.co is an AI model on huggingface.co that provides tipsv2-b14-dpt's model effect (), which can be used instantly with this zeromodels tipsv2-b14-dpt model. huggingface.co supports a free trial of the tipsv2-b14-dpt model, and also provides paid use of the tipsv2-b14-dpt. Support call tipsv2-b14-dpt model through api, including Node.js, Python, http.

zeromodels tipsv2-b14-dpt online free

tipsv2-b14-dpt huggingface.co is an online trial and call api platform, which integrates tipsv2-b14-dpt's modeling effects, including api services, and provides a free online trial of tipsv2-b14-dpt, you can try tipsv2-b14-dpt online for free by clicking the link below.

zeromodels tipsv2-b14-dpt online free url in huggingface.co:

https://huggingface.co/zeromodels/tipsv2-b14-dpt

tipsv2-b14-dpt install

tipsv2-b14-dpt is an open source model from GitHub that offers a free installation service, and any user can find tipsv2-b14-dpt on GitHub to install. At the same time, huggingface.co provides the effect of tipsv2-b14-dpt install, users can directly use tipsv2-b14-dpt installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

tipsv2-b14-dpt install url in huggingface.co:

https://huggingface.co/zeromodels/tipsv2-b14-dpt

Url of tipsv2-b14-dpt

tipsv2-b14-dpt huggingface.co Url

Provider of tipsv2-b14-dpt huggingface.co

zeromodels
ORGANIZATIONS

Other API from zeromodels