zeromodels
/

mobilenetv3_small_050_lamb_in1k

@@ -1,84 +1,84 @@
----
-pipeline_tag: image-classification
-license: apache-2.0
-base_model: timm/mobilenetv3_small_050.lamb_in1k
-library_name: zeromodels
-tags:
-- keras
-- zeromodels
-- image-classification
-- mobilenetv3
-- backbone
-- arxiv:1905.02244
-- pytorch
-- jax
-- tf
----
-## ***See [our collection](https://huggingface.co/collections/zeromodels/mobilenetv3-6a8eaed5388ae9631ea13186) for all versions of MobileNetV3.***
-# Run MobileNetV3 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-MobileNetV3-blue)](https://imvision12.github.io/ZeroModels/classification_backbones/) [![Collection](https://img.shields.io/badge/HF-MobileNetV3%20collection-yellow)](https://huggingface.co/collections/zeromodels/mobilenetv3-6a8eaed5388ae9631ea13186)
-# zeromodels/mobilenetv3_small_050_lamb_in1k
-Paper: [Searching for MobileNetV3 (arXiv:1905.02244)](https://arxiv.org/abs/1905.02244) · [HF Papers](https://huggingface.co/papers/1905.02244)
-MobileNetV3 combines NAS, NetAdapt, and hard-swish / SE for efficient mobile vision. Classifier or backbone.
-For more details on the model, please go to the upstream [model card](https://huggingface.co/timm/mobilenetv3_small_050.lamb_in1k).
-Pure-**Keras 3** conversion of [`timm/mobilenetv3_small_050.lamb_in1k`](https://huggingface.co/timm/mobilenetv3_small_050.lamb_in1k) for [zeromodels](https://github.com/IMvision12/ZeroModels). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
-This is an **image-classification / backbone** checkpoint (`MobileNetV3ImageClassify` / `MobileNetV3Model`).
-## ✨ Quick start
-```python
-import os
-os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
-from PIL import Image
-import numpy as np
-from zeromodels.models.mobilenetv3 import MobileNetV3ImageClassify, MobileNetV3Model
-model = MobileNetV3ImageClassify.from_weights("zeromodels/mobilenetv3_small_050_lamb_in1k")
-backbone = MobileNetV3Model.from_weights(
-    "zeromodels/mobilenetv3_small_050_lamb_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 MobileNetV3 variant the same way with `from_weights("zeromodels/<variant>")`:
-| Variant | Hub |
-|---|---|
-| `mobilenetv3_large_100_miil_in21k` | [`zeromodels/mobilenetv3_large_100_miil_in21k`](https://huggingface.co/zeromodels/mobilenetv3_large_100_miil_in21k) |
-| `mobilenetv3_large_100_miil_in21k_ft_in1k` | [`zeromodels/mobilenetv3_large_100_miil_in21k_ft_in1k`](https://huggingface.co/zeromodels/mobilenetv3_large_100_miil_in21k_ft_in1k) |
-| `mobilenetv3_large_100_ra4_e3600_r224_in1k` | [`zeromodels/mobilenetv3_large_100_ra4_e3600_r224_in1k`](https://huggingface.co/zeromodels/mobilenetv3_large_100_ra4_e3600_r224_in1k) |
-| `mobilenetv3_large_100_ra_in1k` | [`zeromodels/mobilenetv3_large_100_ra_in1k`](https://huggingface.co/zeromodels/mobilenetv3_large_100_ra_in1k) |
-| `mobilenetv3_large_150d_ra4_e3600_r256_in1k` | [`zeromodels/mobilenetv3_large_150d_ra4_e3600_r256_in1k`](https://huggingface.co/zeromodels/mobilenetv3_large_150d_ra4_e3600_r256_in1k) |
-| `mobilenetv3_rw_rmsp_in1k` | [`zeromodels/mobilenetv3_rw_rmsp_in1k`](https://huggingface.co/zeromodels/mobilenetv3_rw_rmsp_in1k) |
-| `mobilenetv3_small_050_lamb_in1k` | [`zeromodels/mobilenetv3_small_050_lamb_in1k`](https://huggingface.co/zeromodels/mobilenetv3_small_050_lamb_in1k) |
-| `mobilenetv3_small_075_lamb_in1k` | [`zeromodels/mobilenetv3_small_075_lamb_in1k`](https://huggingface.co/zeromodels/mobilenetv3_small_075_lamb_in1k) |
-| `mobilenetv3_small_100_lamb_in1k` | [`zeromodels/mobilenetv3_small_100_lamb_in1k`](https://huggingface.co/zeromodels/mobilenetv3_small_100_lamb_in1k) |
-## Tips
-- Set `KERAS_BACKEND` **before** importing Keras / zeromodels.
-- `MobileNetV3ImageClassify` returns class logits; `MobileNetV3Model` 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: `MobileNetV3ImageClassify.from_weights("hf:timm/mobilenetv3_small_050.lamb_in1k")`.
-## Special Thanks
-A huge thank you to the MobileNetV3 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/mobilenetv3_small_050.lamb_in1k
+library_name: zeromodels
+tags:
+- keras
+- zeromodels
+- image-classification
+- mobilenetv3
+- backbone
+- arxiv:1905.02244
+- pytorch
+- jax
+- tf
+---
+## ***See [our collection](https://huggingface.co/collections/zeromodels/mobilenetv3-6a8eaed5388ae9631ea13186) for all versions of MobileNetV3.***
+# Run MobileNetV3 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-MobileNetV3-blue)](https://imvision12.github.io/ZeroModels/classification_backbones/) [![Collection](https://img.shields.io/badge/HF-MobileNetV3%20collection-yellow)](https://huggingface.co/collections/zeromodels/mobilenetv3-6a8eaed5388ae9631ea13186)
+# zeromodels/mobilenetv3_small_050_lamb_in1k
+Paper: [Searching for MobileNetV3 (arXiv:1905.02244)](https://arxiv.org/abs/1905.02244) · [HF Papers](https://huggingface.co/papers/1905.02244)
+MobileNetV3 combines NAS, NetAdapt, and hard-swish / SE for efficient mobile vision. Classifier or backbone.
+For more details on the model, please go to the upstream [model card](https://huggingface.co/timm/mobilenetv3_small_050.lamb_in1k).
+Pure-**Keras 3** conversion of [`timm/mobilenetv3_small_050.lamb_in1k`](https://huggingface.co/timm/mobilenetv3_small_050.lamb_in1k) for [zeromodels](https://github.com/IMvision12/ZeroModels). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
+This is an **image-classification / backbone** checkpoint (`MobileNetV3ImageClassify` / `MobileNetV3Model`).
+## ✨ Quick start
+```python
+import os
+os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
+from PIL import Image
+from zeromodels.models.mobilenetv3 import MobileNetV3ImageClassify, MobileNetV3Model, MobileNetV3ImageProcessor
+model = MobileNetV3ImageClassify.from_weights("zeromodels/mobilenetv3_small_050_lamb_in1k")
+processor = MobileNetV3ImageProcessor.from_weights("zeromodels/mobilenetv3_small_050_lamb_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 = MobileNetV3Model.from_weights("zeromodels/mobilenetv3_small_050_lamb_in1k", as_backbone=True)
+features = backbone(pixels, training=False)
+```
+Load any MobileNetV3 variant the same way with `from_weights("zeromodels/<variant>")`:
+| Variant | Hub |
+|---|---|
+| `mobilenetv3_large_100_miil_in21k` | [`zeromodels/mobilenetv3_large_100_miil_in21k`](https://huggingface.co/zeromodels/mobilenetv3_large_100_miil_in21k) |
+| `mobilenetv3_large_100_miil_in21k_ft_in1k` | [`zeromodels/mobilenetv3_large_100_miil_in21k_ft_in1k`](https://huggingface.co/zeromodels/mobilenetv3_large_100_miil_in21k_ft_in1k) |
+| `mobilenetv3_large_100_ra4_e3600_r224_in1k` | [`zeromodels/mobilenetv3_large_100_ra4_e3600_r224_in1k`](https://huggingface.co/zeromodels/mobilenetv3_large_100_ra4_e3600_r224_in1k) |
+| `mobilenetv3_large_100_ra_in1k` | [`zeromodels/mobilenetv3_large_100_ra_in1k`](https://huggingface.co/zeromodels/mobilenetv3_large_100_ra_in1k) |
+| `mobilenetv3_large_150d_ra4_e3600_r256_in1k` | [`zeromodels/mobilenetv3_large_150d_ra4_e3600_r256_in1k`](https://huggingface.co/zeromodels/mobilenetv3_large_150d_ra4_e3600_r256_in1k) |
+| `mobilenetv3_rw_rmsp_in1k` | [`zeromodels/mobilenetv3_rw_rmsp_in1k`](https://huggingface.co/zeromodels/mobilenetv3_rw_rmsp_in1k) |
+| `mobilenetv3_small_050_lamb_in1k` | [`zeromodels/mobilenetv3_small_050_lamb_in1k`](https://huggingface.co/zeromodels/mobilenetv3_small_050_lamb_in1k) |
+| `mobilenetv3_small_075_lamb_in1k` | [`zeromodels/mobilenetv3_small_075_lamb_in1k`](https://huggingface.co/zeromodels/mobilenetv3_small_075_lamb_in1k) |
+| `mobilenetv3_small_100_lamb_in1k` | [`zeromodels/mobilenetv3_small_100_lamb_in1k`](https://huggingface.co/zeromodels/mobilenetv3_small_100_lamb_in1k) |
+## Tips
+- Set `KERAS_BACKEND` **before** importing Keras / zeromodels.
+- `MobileNetV3ImageClassify` returns class logits; `MobileNetV3Model` 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: `MobileNetV3ImageClassify.from_weights("hf:timm/mobilenetv3_small_050.lamb_in1k")`.
+## Special Thanks
+A huge thank you to the MobileNetV3 authors and the timm / Hub communities for creating and releasing these models.
+License: see YAML `license` (usually matches the upstream checkpoint).