Add kf_preprocessor.json; load processor via from_weights

README.md

@@ -1,72 +1,75 @@
----
-pipeline_tag: image-feature-extraction
-license: apache-2.0
-base_model: facebook/dinov2-large
-library_name: kerasformers
-tags:
-- keras
-- kerasformers
-- dinov2
-- feature-extraction
-- vision
-- arxiv:2304.07193
-- pytorch
-- jax
-- tf
----
-
-## ***See [our collection](https://huggingface.co/collections/kerasformers/dino-v1-v2-v3-6a6a94f8281a2f373f70e769) for all versions of DINOv2.***
-
-# Run DINOv2 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-DINOv2-blue)](https://imvision12.github.io/KerasFormers/dinov2/) [![Collection](https://img.shields.io/badge/HF-DINOv2%20collection-yellow)](https://huggingface.co/collections/kerasformers/dino-v1-v2-v3-6a6a94f8281a2f373f70e769)
-
-# kerasformers/dinov2_vitl14
-
-Paper: [DINOv2: Learning Robust Visual Features without Supervision (arXiv:2304.07193)](https://arxiv.org/abs/2304.07193) · [HF Papers](https://huggingface.co/papers/2304.07193)
-
-DINOv2 scales self-supervised ViT pretraining for strong transferable visual features without labels. These checkpoints are backbones that return patch tokens for downstream heads.
-
-For more details on the model, please go to the upstream [model card](https://huggingface.co/facebook/dinov2-large).
-
-Pure-**Keras 3** conversion of [`facebook/dinov2-large`](https://huggingface.co/facebook/dinov2-large) for [kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
-
-This is a **self-supervised backbone** (`DinoV2Model`), not a task head.
-
-## ✨ Quick start
-
-```python
-import os
-os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
-
-import numpy as np
-from PIL import Image
-from kerasformers.models.dino_v2 import DinoV2Model
-
-model = DinoV2Model.from_weights("kerasformers/dinov2_vitl14", image_size=448)
-image = Image.open("your_image.jpg").convert("RGB")
-x = np.asarray(image.resize((448, 448)))[None].astype("float32")
-tokens = model(x, training=False)
-print(tokens.shape)
-```
-
-Load any DINOv2 variant the same way with `from_weights("kerasformers/<variant>")`:
-
-| Variant | Hub | Backbone |
-|---|---|---|
-| `dinov2_vits14` | [`kerasformers/dinov2_vits14`](https://huggingface.co/kerasformers/dinov2_vits14) | ViT-S/14 |
-| `dinov2_vitb14` | [`kerasformers/dinov2_vitb14`](https://huggingface.co/kerasformers/dinov2_vitb14) | ViT-B/14 |
-| `dinov2_vitl14` | [`kerasformers/dinov2_vitl14`](https://huggingface.co/kerasformers/dinov2_vitl14) | ViT-L/14 |
-
-## Tips
-
-- Set `KERAS_BACKEND` **before** importing Keras / kerasformers.
-- Feed raw `[0, 255]` pixels; normalization happens inside by default.
-- See [DINOv2 docs]({DOCS_URL}) and [Loading Weights](https://imvision12.github.io/KerasFormers/loading_weights/).
-- Community / upstream weights: `DinoV2Model.from_weights("hf:facebook/dinov2-large")`.
-
-## Special Thanks
-
-A huge thank you to the Facebook AI Research DINOv2 authors for creating and releasing these models.
-
-License: Apache 2.0.
+---
+pipeline_tag: image-feature-extraction
+license: apache-2.0
+base_model: facebook/dinov2-large
+library_name: kerasformers
+tags:
+- keras
+- kerasformers
+- dinov2
+- feature-extraction
+- vision
+- arxiv:2304.07193
+- pytorch
+- jax
+- tf
+---
+
+## ***See [our collection](https://huggingface.co/collections/kerasformers/dino-v1-v2-v3-6a6a94f8281a2f373f70e769) for all versions of DINOv2.***
+
+# Run DINOv2 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-DINOv2-blue)](https://imvision12.github.io/KerasFormers/dinov2/) [![Collection](https://img.shields.io/badge/HF-DINOv2%20collection-yellow)](https://huggingface.co/collections/kerasformers/dino-v1-v2-v3-6a6a94f8281a2f373f70e769)
+
+# kerasformers/dinov2_vitl14
+
+Paper: [DINOv2: Learning Robust Visual Features without Supervision (arXiv:2304.07193)](https://arxiv.org/abs/2304.07193) · [HF Papers](https://huggingface.co/papers/2304.07193)
+
+DINOv2 scales self-supervised ViT pretraining for strong transferable visual features without labels. These checkpoints are backbones that return patch tokens for downstream heads.
+
+For more details on the model, please go to the upstream [model card](https://huggingface.co/facebook/dinov2-large).
+
+Pure-**Keras 3** conversion of [`facebook/dinov2-large`](https://huggingface.co/facebook/dinov2-large) for [kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
+
+This is a **self-supervised backbone** (`DinoV2Model`), not a task head.
+
+## ✨ Quick start
+
+```python
+import os
+os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
+
+from kerasformers.models.dino_v2 import DinoV2Model, DinoV2ImageProcessor
+
+# The processor resizes + ImageNet-normalizes, so build the model with
+# include_normalization=False (it would otherwise normalize a second time).
+model = DinoV2Model.from_weights(
+    "kerasformers/dinov2_vitl14", include_normalization=False
+)
+processor = DinoV2ImageProcessor.from_weights("kerasformers/dinov2_vitl14")
+
+pixel_values = processor("your_image.jpg")["pixel_values"]
+features = model(pixel_values, training=False)
+print(pixel_values.shape, features.shape)
+```
+
+Load any DINOv2 variant the same way with `from_weights("kerasformers/<variant>")`:
+
+| Variant | Hub | Backbone |
+|---|---|---|
+| `dinov2_vits14` | [`kerasformers/dinov2_vits14`](https://huggingface.co/kerasformers/dinov2_vits14) | ViT-S/14 |
+| `dinov2_vitb14` | [`kerasformers/dinov2_vitb14`](https://huggingface.co/kerasformers/dinov2_vitb14) | ViT-B/14 |
+| `dinov2_vitl14` | [`kerasformers/dinov2_vitl14`](https://huggingface.co/kerasformers/dinov2_vitl14) | ViT-L/14 |
+
+## Tips
+
+- Set `KERAS_BACKEND` **before** importing Keras / kerasformers.
+- The processor normalizes; pair it with `include_normalization=False`. To skip it, feed raw `[0, 255]` pixels and keep the default `include_normalization=True`.
+- See [DINOv2 docs](https://imvision12.github.io/KerasFormers/dinov2/) and [Loading Weights](https://imvision12.github.io/KerasFormers/loading_weights/).
+- Community / upstream weights: `DinoV2Model.from_weights("hf:facebook/dinov2-large")`.
+
+## Special Thanks
+
+A huge thank you to the Facebook AI Research DINOv2 authors for creating and releasing these models.
+
+License: Apache 2.0.

kf_preprocessor.json

@@ -0,0 +1,23 @@
+{
+  "library_name": "kerasformers",
+  "kerasformers_version": "1.2.1",
+  "preprocessor_module": "kerasformers.models.dino_v2",
+  "preprocessor_class": "DinoV2ImageProcessor",
+  "variant": "dinov2_vitl14",
+  "resize_size": 256,
+  "crop_size": 224,
+  "mean": [
+    0.48500001430511475,
+    0.4560000002384186,
+    0.4059999883174896
+  ],
+  "std": [
+    0.2290000021457672,
+    0.2240000069141388,
+    0.22499999403953552
+  ],
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "data_format": "channels_last"
+}