zeromodels / mobilevitv2_100_cvnets_in1k

huggingface.co
Total runs: 28
24-hour runs: -11
7-day runs: -18
30-day runs: -4
Model's Last Updated: August 30 2026
image-classification

Introduction of mobilevitv2_100_cvnets_in1k

Model Details of mobilevitv2_100_cvnets_in1k

See our collection for all versions of MobileViT-V2.

Run MobileViT-V2 with Keras 3: JAX, PyTorch, or TensorFlow

GitHub Docs Collection

zeromodels/mobilevitv2_100_cvnets_in1k

Paper: Separable Self-attention for Mobile Vision Transformers (arXiv:2206.02680) · HF Papers

MobileViTV2 replaces MHSA with separable self-attention (O(k)) and scales width via a single multiplier. Classification at 256/384; DeepLabV3 segmentation is a separate script/collection.

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

Pure- Keras 3 conversion of timm/mobilevitv2_100.cvnets_in1k for zeromodels . One implementation runs unmodified on TensorFlow / Torch / JAX .

This is an image-classification / backbone checkpoint ( MobileViTV2ImageClassify / MobileViTV2Model ).

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

from PIL import Image
from zeromodels.models.mobilevitv2 import (
    MobileViTV2ImageClassify,
    MobileViTV2Model,
    MobileViTV2ImageProcessor,
)

model = MobileViTV2ImageClassify.from_weights("zeromodels/mobilevitv2_100_cvnets_in1k")
processor = MobileViTV2ImageProcessor.from_weights("zeromodels/mobilevitv2_100_cvnets_in1k")

image = Image.open("your_image.jpg").convert("RGB")
logits = model(processor(image)["pixel_values"], training=False)
print(logits.shape)  # (1, num_classes)

backbone = MobileViTV2Model.from_weights(
    "zeromodels/mobilevitv2_100_cvnets_in1k", as_backbone=True
)
feats = backbone(processor(image)["pixel_values"], training=False)
print(len(feats), [tuple(f.shape) for f in feats])

Load any MobileViT-V2 variant the same way with from_weights("zeromodels/<variant>") :

Variant Hub
mobilevitv2_050_cvnets_in1k zeromodels/mobilevitv2_050_cvnets_in1k
mobilevitv2_075_cvnets_in1k zeromodels/mobilevitv2_075_cvnets_in1k
mobilevitv2_100_cvnets_in1k zeromodels/mobilevitv2_100_cvnets_in1k
mobilevitv2_125_cvnets_in1k zeromodels/mobilevitv2_125_cvnets_in1k
mobilevitv2_150_cvnets_in1k zeromodels/mobilevitv2_150_cvnets_in1k
mobilevitv2_150_cvnets_in22k_ft_in1k zeromodels/mobilevitv2_150_cvnets_in22k_ft_in1k
mobilevitv2_150_cvnets_in22k_ft_in1k_384 zeromodels/mobilevitv2_150_cvnets_in22k_ft_in1k_384
mobilevitv2_175_cvnets_in1k zeromodels/mobilevitv2_175_cvnets_in1k
mobilevitv2_175_cvnets_in22k_ft_in1k zeromodels/mobilevitv2_175_cvnets_in22k_ft_in1k
mobilevitv2_175_cvnets_in22k_ft_in1k_384 zeromodels/mobilevitv2_175_cvnets_in22k_ft_in1k_384
mobilevitv2_200_cvnets_in1k zeromodels/mobilevitv2_200_cvnets_in1k
mobilevitv2_200_cvnets_in22k_ft_in1k zeromodels/mobilevitv2_200_cvnets_in22k_ft_in1k
mobilevitv2_200_cvnets_in22k_ft_in1k_384 zeromodels/mobilevitv2_200_cvnets_in22k_ft_in1k_384
Tips
  • Set KERAS_BACKEND before importing Keras / zeromodels.
  • MobileViTV2ImageClassify returns class logits; MobileViTV2Model returns features ( as_backbone=True for multi-scale stages).
  • See docs and Loading Weights .
  • Upstream / timm checkpoints: MobileViTV2ImageClassify.from_weights("hf:timm/mobilevitv2_100.cvnets_in1k") .
Special Thanks

A huge thank you to the MobileViT-V2 authors and the timm / Hub communities for creating and releasing these models.

License: see YAML license (usually matches the upstream checkpoint).

Runs of zeromodels mobilevitv2_100_cvnets_in1k on huggingface.co

28
Total runs
-11
24-hour runs
-9
3-day runs
-18
7-day runs
-4
30-day runs

More Information About mobilevitv2_100_cvnets_in1k huggingface.co Model

More mobilevitv2_100_cvnets_in1k license Visit here:

https://choosealicense.com/licenses/other

mobilevitv2_100_cvnets_in1k huggingface.co

mobilevitv2_100_cvnets_in1k huggingface.co is an AI model on huggingface.co that provides mobilevitv2_100_cvnets_in1k's model effect (), which can be used instantly with this zeromodels mobilevitv2_100_cvnets_in1k model. huggingface.co supports a free trial of the mobilevitv2_100_cvnets_in1k model, and also provides paid use of the mobilevitv2_100_cvnets_in1k. Support call mobilevitv2_100_cvnets_in1k model through api, including Node.js, Python, http.

mobilevitv2_100_cvnets_in1k huggingface.co Url

https://huggingface.co/zeromodels/mobilevitv2_100_cvnets_in1k

zeromodels mobilevitv2_100_cvnets_in1k online free

mobilevitv2_100_cvnets_in1k huggingface.co is an online trial and call api platform, which integrates mobilevitv2_100_cvnets_in1k's modeling effects, including api services, and provides a free online trial of mobilevitv2_100_cvnets_in1k, you can try mobilevitv2_100_cvnets_in1k online for free by clicking the link below.

zeromodels mobilevitv2_100_cvnets_in1k online free url in huggingface.co:

https://huggingface.co/zeromodels/mobilevitv2_100_cvnets_in1k

mobilevitv2_100_cvnets_in1k install

mobilevitv2_100_cvnets_in1k is an open source model from GitHub that offers a free installation service, and any user can find mobilevitv2_100_cvnets_in1k on GitHub to install. At the same time, huggingface.co provides the effect of mobilevitv2_100_cvnets_in1k install, users can directly use mobilevitv2_100_cvnets_in1k installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

mobilevitv2_100_cvnets_in1k install url in huggingface.co:

https://huggingface.co/zeromodels/mobilevitv2_100_cvnets_in1k

Url of mobilevitv2_100_cvnets_in1k

mobilevitv2_100_cvnets_in1k huggingface.co Url

Provider of mobilevitv2_100_cvnets_in1k huggingface.co

zeromodels
ORGANIZATIONS

Other API from zeromodels