Image Segmentation
Keras
PyTorch
JAX
TensorFlow
zeromodels
mobilevit
deeplabv3
semantic-segmentation
Instructions to use zeromodels/mobilevitv2_100_deeplabv3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use zeromodels/mobilevitv2_100_deeplabv3 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/mobilevitv2_100_deeplabv3") - Notebooks
- Google Colab
- Kaggle
Upload kf_config.json with huggingface_hub
Browse files- kf_config.json +19 -0
kf_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"library_name": "kerasformers",
|
| 3 |
+
"model_module": "kerasformers.models.mobilevitv2",
|
| 4 |
+
"model_class": "MobileViTV2SemanticSegment",
|
| 5 |
+
"variant": "mobilevitv2_100_deeplabv3",
|
| 6 |
+
"weights": "model.weights.h5",
|
| 7 |
+
"model_type": "mobilevitv2",
|
| 8 |
+
"multiplier": 1.0,
|
| 9 |
+
"image_size": 512,
|
| 10 |
+
"output_stride": 16,
|
| 11 |
+
"atrous_rates": [
|
| 12 |
+
6,
|
| 13 |
+
12,
|
| 14 |
+
18
|
| 15 |
+
],
|
| 16 |
+
"aspp_out_channels": 512,
|
| 17 |
+
"aspp_dropout_prob": 0.1,
|
| 18 |
+
"num_classes": 21
|
| 19 |
+
}
|