Upload README.md with huggingface_hub

README.md

@@ -1,80 +1,80 @@
----
-pipeline_tag: image-classification
-license: apache-2.0
-base_model: timm/tf_efficientnet_lite1.in1k
-library_name: zeromodels
-tags:
-- keras
-- zeromodels
-- image-classification
-- efficientnet-lite
-- backbone
-- arxiv:1905.11946
-- pytorch
-- jax
-- tf
----
-
-## ***See [our collection](https://huggingface.co/collections/zeromodels/efficientnet-lite-6a8eae80388ae9631ea12c91) for all versions of EfficientNet-Lite.***
-
-# Run EfficientNet-Lite with Keras 3: JAX, PyTorch, or TensorFlow
-
-[![GitHub](https://img.shields.io/badge/GitHub-ZeroModels-black?logo=github)](https://github.com/IMvision12/ZeroModels) [![Docs](https://img.shields.io/badge/Docs-EfficientNet--Lite-blue)](https://imvision12.github.io/ZeroModels/classification_backbones/) [![Collection](https://img.shields.io/badge/HF-EfficientNet--Lite%20collection-yellow)](https://huggingface.co/collections/zeromodels/efficientnet-lite-6a8eae80388ae9631ea12c91)
-
-# zeromodels/tf_efficientnet_lite1_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_lite1.in1k).
-
-Pure-**Keras 3** conversion of [`timm/tf_efficientnet_lite1.in1k`](https://huggingface.co/timm/tf_efficientnet_lite1.in1k) for [zeromodels](https://github.com/IMvision12/ZeroModels). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
-
-This is an **image-classification / backbone** checkpoint (`EfficientNetLiteImageClassify` / `EfficientNetLiteModel`).
-
-## ✨ Quick start
-
-```python
-import os
-os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
-
-from PIL import Image
-import numpy as np
-from zeromodels.models.efficientnet_lite import EfficientNetLiteImageClassify, EfficientNetLiteModel
-
-model = EfficientNetLiteImageClassify.from_weights("zeromodels/tf_efficientnet_lite1_in1k")
-backbone = EfficientNetLiteModel.from_weights(
-    "zeromodels/tf_efficientnet_lite1_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])
-```
-
-Load any EfficientNet-Lite variant the same way with `from_weights("zeromodels/<variant>")`:
-
-| Variant | Hub |
-|---|---|
-| `tf_efficientnet_lite0_in1k` | [`zeromodels/tf_efficientnet_lite0_in1k`](https://huggingface.co/zeromodels/tf_efficientnet_lite0_in1k) |
-| `tf_efficientnet_lite1_in1k` | [`zeromodels/tf_efficientnet_lite1_in1k`](https://huggingface.co/zeromodels/tf_efficientnet_lite1_in1k) |
-| `tf_efficientnet_lite2_in1k` | [`zeromodels/tf_efficientnet_lite2_in1k`](https://huggingface.co/zeromodels/tf_efficientnet_lite2_in1k) |
-| `tf_efficientnet_lite3_in1k` | [`zeromodels/tf_efficientnet_lite3_in1k`](https://huggingface.co/zeromodels/tf_efficientnet_lite3_in1k) |
-| `tf_efficientnet_lite4_in1k` | [`zeromodels/tf_efficientnet_lite4_in1k`](https://huggingface.co/zeromodels/tf_efficientnet_lite4_in1k) |
-
-## Tips
-
-- Set `KERAS_BACKEND` **before** importing Keras / zeromodels.
-- `EfficientNetLiteImageClassify` returns class logits; `EfficientNetLiteModel` returns features (`as_backbone=True` for multi-scale stages).
-- See [docs](https://imvision12.github.io/ZeroModels/classification_backbones/) and [Loading Weights](https://imvision12.github.io/ZeroModels/loading_weights/).
-- Upstream / timm checkpoints: `EfficientNetLiteImageClassify.from_weights("hf:timm/tf_efficientnet_lite1.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).
+---
+pipeline_tag: image-classification
+license: apache-2.0
+base_model: timm/tf_efficientnet_lite1.in1k
+library_name: zeromodels
+tags:
+- keras
+- zeromodels
+- image-classification
+- efficientnet-lite
+- backbone
+- arxiv:1905.11946
+- pytorch
+- jax
+- tf
+---
+
+## ***See [our collection](https://huggingface.co/collections/zeromodels/efficientnet-lite-6a8eae80388ae9631ea12c91) for all versions of EfficientNet-Lite.***
+
+# Run EfficientNet-Lite with Keras 3: JAX, PyTorch, or TensorFlow
+
+[![GitHub](https://img.shields.io/badge/GitHub-ZeroModels-black?logo=github)](https://github.com/IMvision12/ZeroModels) [![Docs](https://img.shields.io/badge/Docs-EfficientNet--Lite-blue)](https://imvision12.github.io/ZeroModels/classification_backbones/) [![Collection](https://img.shields.io/badge/HF-EfficientNet--Lite%20collection-yellow)](https://huggingface.co/collections/zeromodels/efficientnet-lite-6a8eae80388ae9631ea12c91)
+
+# zeromodels/tf_efficientnet_lite1_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_lite1.in1k).
+
+Pure-**Keras 3** conversion of [`timm/tf_efficientnet_lite1.in1k`](https://huggingface.co/timm/tf_efficientnet_lite1.in1k) for [zeromodels](https://github.com/IMvision12/ZeroModels). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
+
+This is an **image-classification / backbone** checkpoint (`EfficientNetLiteImageClassify` / `EfficientNetLiteModel`).
+
+## ✨ Quick start
+
+```python
+import os
+
+os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
+
+from PIL import Image
+from zeromodels.models.efficientnet_lite import EfficientNetLiteImageClassify, EfficientNetLiteModel, EfficientNetLiteImageProcessor
+
+model = EfficientNetLiteImageClassify.from_weights("zeromodels/tf_efficientnet_lite1_in1k")
+processor = EfficientNetLiteImageProcessor.from_weights("zeromodels/tf_efficientnet_lite1_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 = EfficientNetLiteModel.from_weights("zeromodels/tf_efficientnet_lite1_in1k", as_backbone=True)
+features = backbone(pixels, training=False)
+```
+
+Load any EfficientNet-Lite variant the same way with `from_weights("zeromodels/<variant>")`:
+
+| Variant | Hub |
+|---|---|
+| `tf_efficientnet_lite0_in1k` | [`zeromodels/tf_efficientnet_lite0_in1k`](https://huggingface.co/zeromodels/tf_efficientnet_lite0_in1k) |
+| `tf_efficientnet_lite1_in1k` | [`zeromodels/tf_efficientnet_lite1_in1k`](https://huggingface.co/zeromodels/tf_efficientnet_lite1_in1k) |
+| `tf_efficientnet_lite2_in1k` | [`zeromodels/tf_efficientnet_lite2_in1k`](https://huggingface.co/zeromodels/tf_efficientnet_lite2_in1k) |
+| `tf_efficientnet_lite3_in1k` | [`zeromodels/tf_efficientnet_lite3_in1k`](https://huggingface.co/zeromodels/tf_efficientnet_lite3_in1k) |
+| `tf_efficientnet_lite4_in1k` | [`zeromodels/tf_efficientnet_lite4_in1k`](https://huggingface.co/zeromodels/tf_efficientnet_lite4_in1k) |
+
+## Tips
+
+- Set `KERAS_BACKEND` **before** importing Keras / zeromodels.
+- `EfficientNetLiteImageClassify` returns class logits; `EfficientNetLiteModel` returns features (`as_backbone=True` for multi-scale stages).
+- See [docs](https://imvision12.github.io/ZeroModels/classification_backbones/) and [Loading Weights](https://imvision12.github.io/ZeroModels/loading_weights/).
+- Upstream / timm checkpoints: `EfficientNetLiteImageClassify.from_weights("hf:timm/tf_efficientnet_lite1.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).