Instructions to use zeromodels/convnextv2_tiny_fcmae_ft_in1k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use zeromodels/convnextv2_tiny_fcmae_ft_in1k 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/convnextv2_tiny_fcmae_ft_in1k") - Notebooks
- Google Colab
- Kaggle
Upload kf_config.json with huggingface_hub
Browse files- kf_config.json +26 -0
kf_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"library_name": "kerasformers",
|
| 3 |
+
"kerasformers_version": "1.1.3",
|
| 4 |
+
"model_module": "kerasformers.models.convnextv2",
|
| 5 |
+
"model_class": "ConvNeXtV2ImageClassify",
|
| 6 |
+
"variant": "convnextv2_tiny_fcmae_ft_in1k",
|
| 7 |
+
"weights": "model.weights.h5",
|
| 8 |
+
"model_type": "convnextv2",
|
| 9 |
+
"depths": [
|
| 10 |
+
3,
|
| 11 |
+
3,
|
| 12 |
+
9,
|
| 13 |
+
3
|
| 14 |
+
],
|
| 15 |
+
"projection_dim": [
|
| 16 |
+
96,
|
| 17 |
+
192,
|
| 18 |
+
384,
|
| 19 |
+
768
|
| 20 |
+
],
|
| 21 |
+
"use_conv": false,
|
| 22 |
+
"use_grn": true,
|
| 23 |
+
"layer_scale_init": null,
|
| 24 |
+
"image_size": 224,
|
| 25 |
+
"num_classes": 1000
|
| 26 |
+
}
|