fix readme.md

README.md

@@ -7,21 +7,74 @@ tags:
 - keras
 - kerasformers
 - image-classification
-- efficientnet_lite
+- efficientnet-lite
+- backbone
+- arxiv:1905.11946
 - pytorch
 - jax
 - tf
 ---
 
-# tf_efficientnet_lite2_in1k
+## ***See [our collection](https://huggingface.co/collections/kerasformers/efficientnet-lite-6a6d117aa2e14494d3aa6a58) for all versions of EfficientNet-Lite.***
 
-Pure-Keras 3 image-classification weight for [kerasformers](https://github.com/IMvision12/KerasFormers), converted from [timm/tf_efficientnet_lite2.in1k](https://huggingface.co/timm/tf_efficientnet_lite2.in1k).
+# Run EfficientNet-Lite with Keras 3: JAX, PyTorch, or TensorFlow
 
-## Usage
+[![GitHub](https://img.shields.io/badge/GitHub-KerasFormers-black?logo=github)](https://github.com/IMvision12/KerasFormers) [![Docs](https://img.shields.io/badge/Docs-EfficientNet--Lite-blue)](https://imvision12.github.io/KerasFormers/classification_backbones/) [![Collection](https://img.shields.io/badge/HF-EfficientNet--Lite%20collection-yellow)](https://huggingface.co/collections/kerasformers/efficientnet-lite-6a6d117aa2e14494d3aa6a58)
+
+# kerasformers/tf_efficientnet_lite2_in1k
+
+Paper: [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (arXiv:1905.11946)](https://arxiv.org/abs/1905.11946) · [HF Papers](https://huggingface.co/papers/1905.11946)
+
+EfficientNet-Lite is the mobile/EdgeTPU-friendly EfficientNet family (no squeeze-excite, ReLU6). Classifier or backbone.
+
+For more details on the model, please go to the upstream [model card](https://huggingface.co/timm/tf_efficientnet_lite2.in1k).
+
+Pure-**Keras 3** conversion of [`timm/tf_efficientnet_lite2.in1k`](https://huggingface.co/timm/tf_efficientnet_lite2.in1k) for [kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
+
+This is an **image-classification / backbone** checkpoint (`EfficientNetLiteImageClassify` / `EfficientNetLiteModel`).
+
+## ✨ Quick start
 
 ```python
-from kerasformers.models.efficientnet_lite import EfficientNetLiteImageClassify
-model = EfficientNetLiteImageClassify.from_weights("tf_efficientnet_lite2_in1k")
+import os
+os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
+
+from PIL import Image
+import numpy as np
+from kerasformers.models.efficientnet_lite import EfficientNetLiteImageClassify, EfficientNetLiteModel
+
+model = EfficientNetLiteImageClassify.from_weights("kerasformers/tf_efficientnet_lite2_in1k")
+backbone = EfficientNetLiteModel.from_weights(
+    "kerasformers/tf_efficientnet_lite2_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 EfficientNet-Lite variant the same way with `from_weights("kerasformers/<variant>")`:
+
+| Variant | Hub |
+|---|---|
+| `tf_efficientnet_lite0_in1k` | [`kerasformers/tf_efficientnet_lite0_in1k`](https://huggingface.co/kerasformers/tf_efficientnet_lite0_in1k) |
+| `tf_efficientnet_lite1_in1k` | [`kerasformers/tf_efficientnet_lite1_in1k`](https://huggingface.co/kerasformers/tf_efficientnet_lite1_in1k) |
+| `tf_efficientnet_lite2_in1k` | [`kerasformers/tf_efficientnet_lite2_in1k`](https://huggingface.co/kerasformers/tf_efficientnet_lite2_in1k) |
+| `tf_efficientnet_lite3_in1k` | [`kerasformers/tf_efficientnet_lite3_in1k`](https://huggingface.co/kerasformers/tf_efficientnet_lite3_in1k) |
+| `tf_efficientnet_lite4_in1k` | [`kerasformers/tf_efficientnet_lite4_in1k`](https://huggingface.co/kerasformers/tf_efficientnet_lite4_in1k) |
+
+## Tips
+
+- Set `KERAS_BACKEND` **before** importing Keras / kerasformers.
+- `EfficientNetLiteImageClassify` returns class logits; `EfficientNetLiteModel` 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: `EfficientNetLiteImageClassify.from_weights("hf:timm/tf_efficientnet_lite2.in1k")`.
+
+## Special Thanks
+
+A huge thank you to the EfficientNet-Lite authors and the timm / Hub communities for creating and releasing these models.
+
+License: see YAML `license` (usually matches the upstream checkpoint).