Instructions to use zeromodels/regnet-y-320 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use zeromodels/regnet-y-320 with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://zeromodels/regnet-y-320") - Notebooks
- Google Colab
- Kaggle
Upload zm_preprocessor.json with huggingface_hub
Browse files- zm_preprocessor.json +34 -0
zm_preprocessor.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"library_name": "zeromodels",
|
| 3 |
+
"zeromodels_version": "1.2.7",
|
| 4 |
+
"preprocessor_module": "zeromodels.models.regnet",
|
| 5 |
+
"preprocessor_class": "RegNetImageProcessor",
|
| 6 |
+
"variant": "regnet-y-320",
|
| 7 |
+
"size": {
|
| 8 |
+
"height": 224,
|
| 9 |
+
"width": 224
|
| 10 |
+
},
|
| 11 |
+
"crop_size": {
|
| 12 |
+
"height": 224,
|
| 13 |
+
"width": 224
|
| 14 |
+
},
|
| 15 |
+
"resample": "bicubic",
|
| 16 |
+
"do_resize": true,
|
| 17 |
+
"do_center_crop": false,
|
| 18 |
+
"do_rescale": true,
|
| 19 |
+
"rescale_factor": 0.00392156862745098,
|
| 20 |
+
"do_normalize": true,
|
| 21 |
+
"image_mean": [
|
| 22 |
+
0.485,
|
| 23 |
+
0.456,
|
| 24 |
+
0.406
|
| 25 |
+
],
|
| 26 |
+
"image_std": [
|
| 27 |
+
0.229,
|
| 28 |
+
0.224,
|
| 29 |
+
0.225
|
| 30 |
+
],
|
| 31 |
+
"antialias": true,
|
| 32 |
+
"return_tensor": true,
|
| 33 |
+
"data_format": null
|
| 34 |
+
}
|