zeromodels/inception_next_tiny_sail_in1k

See our collection for all versions of InceptionNeXt.

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

zeromodels/inception_next_tiny_sail_in1k

Paper: InceptionNeXt: When Inception Meets ConvNeXt (arXiv:2303.16900) · HF Papers

InceptionNeXt blends Inception-style token mixing with a ConvNeXt meta-architecture for efficient ImageNet classification.

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

Pure-Keras 3 conversion of timm/inception_next_tiny.sail_in1k for zeromodels. One implementation runs unmodified on TensorFlow / Torch / JAX.

This is an image-classification / backbone checkpoint (InceptionNextImageClassify / InceptionNextModel).

✨ Quick start

import os

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

from PIL import Image
from zeromodels.models.inception_next import InceptionNextImageClassify, InceptionNextModel, InceptionNextImageProcessor

model = InceptionNextImageClassify.from_weights("zeromodels/inception_next_tiny_sail_in1k")
processor = InceptionNextImageProcessor.from_weights("zeromodels/inception_next_tiny_sail_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 = InceptionNextModel.from_weights("zeromodels/inception_next_tiny_sail_in1k", as_backbone=True)
features = backbone(pixels, training=False)

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

Variant	Hub
inception_next_atto_sail_in1k	zeromodels/inception_next_atto_sail_in1k
inception_next_base_sail_in1k	zeromodels/inception_next_base_sail_in1k
inception_next_base_sail_in1k_384	zeromodels/inception_next_base_sail_in1k_384
inception_next_small_sail_in1k	zeromodels/inception_next_small_sail_in1k
inception_next_tiny_sail_in1k	zeromodels/inception_next_tiny_sail_in1k

Tips

• Set KERAS_BACKEND before importing Keras / zeromodels.
• InceptionNextImageClassify returns class logits; InceptionNextModel returns features (as_backbone=True for multi-scale stages).
• See docs and Loading Weights.
• Upstream / timm checkpoints: InceptionNextImageClassify.from_weights("hf:timm/inception_next_tiny.sail_in1k").

Special Thanks

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

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