Instructions to use keras/vit_large_patch32_384_imagenet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KerasHub
How to use keras/vit_large_patch32_384_imagenet with KerasHub:
import keras_hub import keras # Load ImageClassifier model image_classifier = keras_hub.models.ImageClassifier.from_preset( "hf://keras/vit_large_patch32_384_imagenet", 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/vit_large_patch32_384_imagenet") - Keras
How to use keras/vit_large_patch32_384_imagenet with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://keras/vit_large_patch32_384_imagenet") - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files- config.json +8 -0
- metadata.json +3 -3
- model.weights.h5 +1 -1
- task.json +8 -0
- task.weights.h5 +1 -1
config.json
CHANGED
|
@@ -4,6 +4,14 @@
|
|
| 4 |
"config": {
|
| 5 |
"name": "vi_t_backbone",
|
| 6 |
"trainable": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
"image_shape": [
|
| 8 |
384,
|
| 9 |
384,
|
|
|
|
| 4 |
"config": {
|
| 5 |
"name": "vi_t_backbone",
|
| 6 |
"trainable": true,
|
| 7 |
+
"dtype": {
|
| 8 |
+
"module": "keras",
|
| 9 |
+
"class_name": "DTypePolicy",
|
| 10 |
+
"config": {
|
| 11 |
+
"name": "float32"
|
| 12 |
+
},
|
| 13 |
+
"registered_name": null
|
| 14 |
+
},
|
| 15 |
"image_shape": [
|
| 16 |
384,
|
| 17 |
384,
|
metadata.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"keras_version": "3.
|
| 3 |
-
"keras_hub_version": "0.
|
| 4 |
"parameter_count": 305607680,
|
| 5 |
-
"date_saved": "
|
| 6 |
"tasks": [
|
| 7 |
"ImageClassifier"
|
| 8 |
]
|
|
|
|
| 1 |
{
|
| 2 |
+
"keras_version": "3.14.1",
|
| 3 |
+
"keras_hub_version": "0.30.0.dev0",
|
| 4 |
"parameter_count": 305607680,
|
| 5 |
+
"date_saved": "2026-05-13@23:34:59",
|
| 6 |
"tasks": [
|
| 7 |
"ImageClassifier"
|
| 8 |
]
|
model.weights.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1223296840
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c25abd8a99953a5a1c16041021241d4d6f1e67a0d8a8b5f89b798f9fa899e69
|
| 3 |
size 1223296840
|
task.json
CHANGED
|
@@ -8,6 +8,14 @@
|
|
| 8 |
"config": {
|
| 9 |
"name": "vi_t_backbone",
|
| 10 |
"trainable": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
"image_shape": [
|
| 12 |
384,
|
| 13 |
384,
|
|
|
|
| 8 |
"config": {
|
| 9 |
"name": "vi_t_backbone",
|
| 10 |
"trainable": true,
|
| 11 |
+
"dtype": {
|
| 12 |
+
"module": "keras",
|
| 13 |
+
"class_name": "DTypePolicy",
|
| 14 |
+
"config": {
|
| 15 |
+
"name": "float32"
|
| 16 |
+
},
|
| 17 |
+
"registered_name": null
|
| 18 |
+
},
|
| 19 |
"image_shape": [
|
| 20 |
384,
|
| 21 |
384,
|
task.weights.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1227412992
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4abb56a16cc8b7925b9aeed6e0d8407647cac6009eee1bb366835ccf8ed976c
|
| 3 |
size 1227412992
|