zeromodels / tf_efficientnet_b6_ns_jft_in1k

huggingface.co
Total runs: 251
24-hour runs: 0
7-day runs: -18
30-day runs: -18
Model's Last Updated: August 30 2026
image-classification

Introduction of tf_efficientnet_b6_ns_jft_in1k

Model Details of tf_efficientnet_b6_ns_jft_in1k

See our collection for all versions of EfficientNet.

Run EfficientNet with Keras 3: JAX, PyTorch, or TensorFlow

GitHub Docs Collection

zeromodels/tf_efficientnet_b6_ns_jft_in1k

Paper: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (arXiv:1905.11946) · HF Papers

EfficientNet compound-scales depth/width/resolution for strong accuracy/efficiency. Classifier or multi-scale MBConv backbone.

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

Pure- Keras 3 conversion of timm/tf_efficientnet_b6.ns_jft_in1k for zeromodels . One implementation runs unmodified on TensorFlow / Torch / JAX .

This is an image-classification / backbone checkpoint ( EfficientNetImageClassify / EfficientNetModel ).

✨ Quick start
import os

os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"

from PIL import Image
from zeromodels.models.efficientnet import EfficientNetImageClassify, EfficientNetModel, EfficientNetImageProcessor

model = EfficientNetImageClassify.from_weights("zeromodels/tf_efficientnet_b6_ns_jft_in1k")
processor = EfficientNetImageProcessor.from_weights("zeromodels/tf_efficientnet_b6_ns_jft_in1k")

image = Image.open("your_image.jpg").convert("RGB")
pixels = processor(image)  # resize + normalize (normalization lives in the processor)
logits = model(pixels, training=False)
print(logits.shape)  # (1, num_classes)

# Feature extraction: the backbone without the classifier head
backbone = EfficientNetModel.from_weights("zeromodels/tf_efficientnet_b6_ns_jft_in1k", as_backbone=True)
features = backbone(pixels, training=False)

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

Variant Hub
tf_efficientnet_b0_aa_in1k zeromodels/tf_efficientnet_b0_aa_in1k
tf_efficientnet_b0_ap_in1k zeromodels/tf_efficientnet_b0_ap_in1k
tf_efficientnet_b0_in1k zeromodels/tf_efficientnet_b0_in1k
tf_efficientnet_b0_ns_jft_in1k zeromodels/tf_efficientnet_b0_ns_jft_in1k
tf_efficientnet_b1_aa_in1k zeromodels/tf_efficientnet_b1_aa_in1k
tf_efficientnet_b1_ap_in1k zeromodels/tf_efficientnet_b1_ap_in1k
tf_efficientnet_b1_in1k zeromodels/tf_efficientnet_b1_in1k
tf_efficientnet_b1_ns_jft_in1k zeromodels/tf_efficientnet_b1_ns_jft_in1k
tf_efficientnet_b2_aa_in1k zeromodels/tf_efficientnet_b2_aa_in1k
tf_efficientnet_b2_ap_in1k zeromodels/tf_efficientnet_b2_ap_in1k
tf_efficientnet_b2_in1k zeromodels/tf_efficientnet_b2_in1k
tf_efficientnet_b2_ns_jft_in1k zeromodels/tf_efficientnet_b2_ns_jft_in1k
tf_efficientnet_b3_aa_in1k zeromodels/tf_efficientnet_b3_aa_in1k
tf_efficientnet_b3_ap_in1k zeromodels/tf_efficientnet_b3_ap_in1k
tf_efficientnet_b3_in1k zeromodels/tf_efficientnet_b3_in1k
tf_efficientnet_b3_ns_jft_in1k zeromodels/tf_efficientnet_b3_ns_jft_in1k
tf_efficientnet_b4_aa_in1k zeromodels/tf_efficientnet_b4_aa_in1k
tf_efficientnet_b4_ap_in1k zeromodels/tf_efficientnet_b4_ap_in1k
tf_efficientnet_b4_in1k zeromodels/tf_efficientnet_b4_in1k
tf_efficientnet_b4_ns_jft_in1k zeromodels/tf_efficientnet_b4_ns_jft_in1k
tf_efficientnet_b5_aa_in1k zeromodels/tf_efficientnet_b5_aa_in1k
tf_efficientnet_b5_ap_in1k zeromodels/tf_efficientnet_b5_ap_in1k
tf_efficientnet_b5_in1k zeromodels/tf_efficientnet_b5_in1k
tf_efficientnet_b5_ns_jft_in1k zeromodels/tf_efficientnet_b5_ns_jft_in1k
tf_efficientnet_b6_aa_in1k zeromodels/tf_efficientnet_b6_aa_in1k
tf_efficientnet_b6_ap_in1k zeromodels/tf_efficientnet_b6_ap_in1k
tf_efficientnet_b6_ns_jft_in1k zeromodels/tf_efficientnet_b6_ns_jft_in1k
tf_efficientnet_b7_aa_in1k zeromodels/tf_efficientnet_b7_aa_in1k
tf_efficientnet_b7_ap_in1k zeromodels/tf_efficientnet_b7_ap_in1k
tf_efficientnet_b7_ns_jft_in1k zeromodels/tf_efficientnet_b7_ns_jft_in1k
tf_efficientnet_b8_ap_in1k zeromodels/tf_efficientnet_b8_ap_in1k
tf_efficientnet_l2_ns_jft_in1k zeromodels/tf_efficientnet_l2_ns_jft_in1k
tf_efficientnet_l2_ns_jft_in1k_475 zeromodels/tf_efficientnet_l2_ns_jft_in1k_475
Tips
  • Set KERAS_BACKEND before importing Keras / zeromodels.
  • EfficientNetImageClassify returns class logits; EfficientNetModel returns features ( as_backbone=True for multi-scale stages).
  • See docs and Loading Weights .
  • Upstream / timm checkpoints: EfficientNetImageClassify.from_weights("hf:timm/tf_efficientnet_b6.ns_jft_in1k") .
Special Thanks

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

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

Runs of zeromodels tf_efficientnet_b6_ns_jft_in1k on huggingface.co

251
Total runs
0
24-hour runs
0
3-day runs
-18
7-day runs
-18
30-day runs

More Information About tf_efficientnet_b6_ns_jft_in1k huggingface.co Model

More tf_efficientnet_b6_ns_jft_in1k license Visit here:

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

tf_efficientnet_b6_ns_jft_in1k huggingface.co

tf_efficientnet_b6_ns_jft_in1k huggingface.co is an AI model on huggingface.co that provides tf_efficientnet_b6_ns_jft_in1k's model effect (), which can be used instantly with this zeromodels tf_efficientnet_b6_ns_jft_in1k model. huggingface.co supports a free trial of the tf_efficientnet_b6_ns_jft_in1k model, and also provides paid use of the tf_efficientnet_b6_ns_jft_in1k. Support call tf_efficientnet_b6_ns_jft_in1k model through api, including Node.js, Python, http.

tf_efficientnet_b6_ns_jft_in1k huggingface.co Url

https://huggingface.co/zeromodels/tf_efficientnet_b6_ns_jft_in1k

zeromodels tf_efficientnet_b6_ns_jft_in1k online free

tf_efficientnet_b6_ns_jft_in1k huggingface.co is an online trial and call api platform, which integrates tf_efficientnet_b6_ns_jft_in1k's modeling effects, including api services, and provides a free online trial of tf_efficientnet_b6_ns_jft_in1k, you can try tf_efficientnet_b6_ns_jft_in1k online for free by clicking the link below.

zeromodels tf_efficientnet_b6_ns_jft_in1k online free url in huggingface.co:

https://huggingface.co/zeromodels/tf_efficientnet_b6_ns_jft_in1k

tf_efficientnet_b6_ns_jft_in1k install

tf_efficientnet_b6_ns_jft_in1k is an open source model from GitHub that offers a free installation service, and any user can find tf_efficientnet_b6_ns_jft_in1k on GitHub to install. At the same time, huggingface.co provides the effect of tf_efficientnet_b6_ns_jft_in1k install, users can directly use tf_efficientnet_b6_ns_jft_in1k installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

tf_efficientnet_b6_ns_jft_in1k install url in huggingface.co:

https://huggingface.co/zeromodels/tf_efficientnet_b6_ns_jft_in1k

Url of tf_efficientnet_b6_ns_jft_in1k

tf_efficientnet_b6_ns_jft_in1k huggingface.co Url

Provider of tf_efficientnet_b6_ns_jft_in1k huggingface.co

zeromodels
ORGANIZATIONS

Other API from zeromodels