fix readme.md

README.md

@@ -7,21 +7,74 @@ tags:
 - keras
 - kerasformers
 - image-classification
-- inception_next
-- tf
-- jax
+- inception-next
+- backbone
+- arxiv:2303.16900
 - pytorch
+- jax
+- tf
 ---
 
-# inception_next_base_sail_in1k
+## ***See [our collection](https://huggingface.co/collections/kerasformers/inceptionnext-6a6bd6ca50fbbd33b18604db) for all versions of InceptionNeXt.***
+
+# Run InceptionNeXt with Keras 3: JAX, PyTorch, or TensorFlow
+
+[![GitHub](https://img.shields.io/badge/GitHub-KerasFormers-black?logo=github)](https://github.com/IMvision12/KerasFormers) [![Docs](https://img.shields.io/badge/Docs-InceptionNeXt-blue)](https://imvision12.github.io/KerasFormers/classification_backbones/) [![Collection](https://img.shields.io/badge/HF-InceptionNeXt%20collection-yellow)](https://huggingface.co/collections/kerasformers/inceptionnext-6a6bd6ca50fbbd33b18604db)
+
+# kerasformers/inception_next_base_sail_in1k
+
+Paper: [InceptionNeXt: When Inception Meets ConvNeXt (arXiv:2303.16900)](https://arxiv.org/abs/2303.16900) · [HF Papers](https://huggingface.co/papers/2303.16900)
+
+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](https://huggingface.co/timm/inception_next_base.sail_in1k).
 
-Pure-Keras 3 image-classification weight for [kerasformers](https://github.com/IMvision12/KerasFormers), converted from [timm/inception_next_base.sail_in1k](https://huggingface.co/timm/inception_next_base.sail_in1k).
+Pure-**Keras 3** conversion of [`timm/inception_next_base.sail_in1k`](https://huggingface.co/timm/inception_next_base.sail_in1k) for [kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
 
-## Usage
+This is an **image-classification / backbone** checkpoint (`InceptionNextImageClassify` / `InceptionNextModel`).
+
+## ✨ Quick start
 
 ```python
-from kerasformers.models.inception_next import InceptionNextImageClassify
-model = InceptionNextImageClassify.from_weights("inception_next_base_sail_in1k")
+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")
+backbone = InceptionNextModel.from_weights(
+    "kerasformers/inception_next_base_sail_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])
 ```
 
-License: **apache-2.0**, inherited from the upstream source.
+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`](https://huggingface.co/kerasformers/inception_next_atto_sail_in1k) |
+| `inception_next_base_sail_in1k` | [`kerasformers/inception_next_base_sail_in1k`](https://huggingface.co/kerasformers/inception_next_base_sail_in1k) |
+| `inception_next_base_sail_in1k_384` | [`kerasformers/inception_next_base_sail_in1k_384`](https://huggingface.co/kerasformers/inception_next_base_sail_in1k_384) |
+| `inception_next_small_sail_in1k` | [`kerasformers/inception_next_small_sail_in1k`](https://huggingface.co/kerasformers/inception_next_small_sail_in1k) |
+| `inception_next_tiny_sail_in1k` | [`kerasformers/inception_next_tiny_sail_in1k`](https://huggingface.co/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](https://imvision12.github.io/KerasFormers/classification_backbones/) and [Loading Weights](https://imvision12.github.io/KerasFormers/loading_weights/).
+- Upstream / timm checkpoints: `InceptionNextImageClassify.from_weights("hf:timm/inception_next_base.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).