zeromodels / convnextv2_tiny_fcmae_ft_in1k

huggingface.co
Total runs: 42
24-hour runs: 2
7-day runs: 9
30-day runs: 8
Model's Last Updated: August 30 2026
image-classification

Introduction of convnextv2_tiny_fcmae_ft_in1k

Model Details of convnextv2_tiny_fcmae_ft_in1k

See our collection for all versions of ConvNeXt-V2.

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

GitHub Docs Collection

zeromodels/convnextv2_tiny_fcmae_ft_in1k

Paper: ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders (arXiv:2301.00808) · HF Papers

ConvNeXt V2 adds Global Response Normalization and FCMAE pretraining. Same classifier / backbone split as ConvNeXt.

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

Pure- Keras 3 conversion of timm/convnextv2_tiny.fcmae_ft_in1k for zeromodels . One implementation runs unmodified on TensorFlow / Torch / JAX .

This is an image-classification / backbone checkpoint ( ConvNeXtV2ImageClassify / ConvNeXtV2Model ).

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

from PIL import Image
import numpy as np
from zeromodels.models.convnextv2 import ConvNeXtV2ImageClassify, ConvNeXtV2Model

model = ConvNeXtV2ImageClassify.from_weights("zeromodels/convnextv2_tiny_fcmae_ft_in1k")
backbone = ConvNeXtV2Model.from_weights(
    "zeromodels/convnextv2_tiny_fcmae_ft_in1k", as_backbone=True
)

image = Image.open("your_image.jpg").convert("RGB")
image = image.resize((224, 224))
x = np.asarray(image, dtype="float32")[None]  # (1, H, W, 3)
print(model(x).shape)  # (1, num_classes)
feats = backbone(x)
print(len(feats), [tuple(f.shape) for f in feats])

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

Variant Hub
convnextv2_atto_fcmae_ft_in1k zeromodels/convnextv2_atto_fcmae_ft_in1k
convnextv2_base_fcmae_ft_in1k zeromodels/convnextv2_base_fcmae_ft_in1k
convnextv2_base_fcmae_ft_in22k_in1k zeromodels/convnextv2_base_fcmae_ft_in22k_in1k
convnextv2_base_fcmae_ft_in22k_in1k_384 zeromodels/convnextv2_base_fcmae_ft_in22k_in1k_384
convnextv2_femto_fcmae_ft_in1k zeromodels/convnextv2_femto_fcmae_ft_in1k
convnextv2_huge_fcmae_ft_in1k zeromodels/convnextv2_huge_fcmae_ft_in1k
convnextv2_huge_fcmae_ft_in22k_in1k_384 zeromodels/convnextv2_huge_fcmae_ft_in22k_in1k_384
convnextv2_huge_fcmae_ft_in22k_in1k_512 zeromodels/convnextv2_huge_fcmae_ft_in22k_in1k_512
convnextv2_large_fcmae_ft_in1k zeromodels/convnextv2_large_fcmae_ft_in1k
convnextv2_large_fcmae_ft_in22k_in1k zeromodels/convnextv2_large_fcmae_ft_in22k_in1k
convnextv2_large_fcmae_ft_in22k_in1k_384 zeromodels/convnextv2_large_fcmae_ft_in22k_in1k_384
convnextv2_nano_fcmae_ft_in1k zeromodels/convnextv2_nano_fcmae_ft_in1k
convnextv2_nano_fcmae_ft_in22k_in1k zeromodels/convnextv2_nano_fcmae_ft_in22k_in1k
convnextv2_nano_fcmae_ft_in22k_in1k_384 zeromodels/convnextv2_nano_fcmae_ft_in22k_in1k_384
convnextv2_pico_fcmae_ft_in1k zeromodels/convnextv2_pico_fcmae_ft_in1k
convnextv2_tiny_fcmae_ft_in1k zeromodels/convnextv2_tiny_fcmae_ft_in1k
convnextv2_tiny_fcmae_ft_in22k_in1k zeromodels/convnextv2_tiny_fcmae_ft_in22k_in1k
convnextv2_tiny_fcmae_ft_in22k_in1k_384 zeromodels/convnextv2_tiny_fcmae_ft_in22k_in1k_384
Tips
  • Set KERAS_BACKEND before importing Keras / zeromodels.
  • ConvNeXtV2ImageClassify returns class logits; ConvNeXtV2Model returns features ( as_backbone=True for multi-scale stages).
  • See docs and Loading Weights .
  • Upstream / timm checkpoints: ConvNeXtV2ImageClassify.from_weights("hf:timm/convnextv2_tiny.fcmae_ft_in1k") .
Special Thanks

A huge thank you to the ConvNeXt-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 convnextv2_tiny_fcmae_ft_in1k on huggingface.co

42
Total runs
2
24-hour runs
3
3-day runs
9
7-day runs
8
30-day runs

More Information About convnextv2_tiny_fcmae_ft_in1k huggingface.co Model

More convnextv2_tiny_fcmae_ft_in1k license Visit here:

https://choosealicense.com/licenses/cc-by-nc-4.0

convnextv2_tiny_fcmae_ft_in1k huggingface.co

convnextv2_tiny_fcmae_ft_in1k huggingface.co is an AI model on huggingface.co that provides convnextv2_tiny_fcmae_ft_in1k's model effect (), which can be used instantly with this zeromodels convnextv2_tiny_fcmae_ft_in1k model. huggingface.co supports a free trial of the convnextv2_tiny_fcmae_ft_in1k model, and also provides paid use of the convnextv2_tiny_fcmae_ft_in1k. Support call convnextv2_tiny_fcmae_ft_in1k model through api, including Node.js, Python, http.

convnextv2_tiny_fcmae_ft_in1k huggingface.co Url

https://huggingface.co/zeromodels/convnextv2_tiny_fcmae_ft_in1k

zeromodels convnextv2_tiny_fcmae_ft_in1k online free

convnextv2_tiny_fcmae_ft_in1k huggingface.co is an online trial and call api platform, which integrates convnextv2_tiny_fcmae_ft_in1k's modeling effects, including api services, and provides a free online trial of convnextv2_tiny_fcmae_ft_in1k, you can try convnextv2_tiny_fcmae_ft_in1k online for free by clicking the link below.

zeromodels convnextv2_tiny_fcmae_ft_in1k online free url in huggingface.co:

https://huggingface.co/zeromodels/convnextv2_tiny_fcmae_ft_in1k

convnextv2_tiny_fcmae_ft_in1k install

convnextv2_tiny_fcmae_ft_in1k is an open source model from GitHub that offers a free installation service, and any user can find convnextv2_tiny_fcmae_ft_in1k on GitHub to install. At the same time, huggingface.co provides the effect of convnextv2_tiny_fcmae_ft_in1k install, users can directly use convnextv2_tiny_fcmae_ft_in1k installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

convnextv2_tiny_fcmae_ft_in1k install url in huggingface.co:

https://huggingface.co/zeromodels/convnextv2_tiny_fcmae_ft_in1k

Url of convnextv2_tiny_fcmae_ft_in1k

convnextv2_tiny_fcmae_ft_in1k huggingface.co Url

Provider of convnextv2_tiny_fcmae_ft_in1k huggingface.co

zeromodels
ORGANIZATIONS

Other API from zeromodels