kerasformers/inception_next_base_sail_in1k_384

See our collection for all versions of InceptionNeXt.

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

kerasformers/inception_next_base_sail_in1k_384

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_base.sail_in1k_384 for kerasformers. 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
import numpy as np
from kerasformers.models.inception_next import InceptionNextImageClassify, InceptionNextModel

model = InceptionNextImageClassify.from_weights("kerasformers/inception_next_base_sail_in1k_384")
backbone = InceptionNextModel.from_weights(
    "kerasformers/inception_next_base_sail_in1k_384", 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 InceptionNeXt variant the same way with from_weights("kerasformers/<variant>"):

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

Tips

• Set KERAS_BACKEND before importing Keras / kerasformers.
• 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_base.sail_in1k_384").

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).