Instructions to use keras/swin_small_patch4_window7_224 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KerasHub
How to use keras/swin_small_patch4_window7_224 with KerasHub:
import keras_hub import keras # Load ImageClassifier model image_classifier = keras_hub.models.ImageClassifier.from_preset( "hf://keras/swin_small_patch4_window7_224", num_classes=2, ) # Fine-tune image_classifier.fit( x=keras.random.randint((32, 64, 64, 3), 0, 256), y=keras.random.randint((32, 1), 0, 2), ) # Classify image image_classifier.predict(keras.random.randint((1, 64, 64, 3), 0, 256))import keras_hub # Create a Backbone model unspecialized for any task backbone = keras_hub.models.Backbone.from_preset("hf://keras/swin_small_patch4_window7_224") - Keras
How to use keras/swin_small_patch4_window7_224 with Keras:
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://keras/swin_small_patch4_window7_224") - Notebooks
- Google Colab
- Kaggle
Download model.weights.h5 from keras/swin_small_patch4_window7_224: direct link, hf CLI and curl.
- Browser
- Download file 196 MB
-
https://huggingface.co/keras/swin_small_patch4_window7_224/resolve/main/model.weights.h5
- Command line
-
hf download hf://keras/swin_small_patch4_window7_224/model.weights.h5
-
curl -L -o model.weights.h5 https://huggingface.co/keras/swin_small_patch4_window7_224/resolve/main/model.weights.h5
196 MB
- Xet hash:
- a255b9c0b556d6e165e4ecfda51a244191f2b0f125c9023bed617f18e26525a4
- Size of remote file:
- 196 MB
- SHA256:
- 7c4ec52bfc9453ce2ca7de25bdd6bc088ca1be96a94f99ab56e62e2009eaab49
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.