Instructions to use zeromodels/dfine-medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KerasFormers
How to use zeromodels/dfine-medium with KerasFormers:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Keras
How to use zeromodels/dfine-medium 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/dfine-medium") - Notebooks
- Google Colab
- Kaggle
Upload kf_config.json with huggingface_hub
Browse files- kf_config.json +58 -0
kf_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"library_name": "kerasformers",
|
| 3 |
+
"kerasformers_version": "1.1.3",
|
| 4 |
+
"model_module": "kerasformers.models.dfine",
|
| 5 |
+
"model_class": "DFineDetect",
|
| 6 |
+
"variant": "dfine-medium",
|
| 7 |
+
"weights": "model.weights.h5",
|
| 8 |
+
"config": {
|
| 9 |
+
"stem_channels": [
|
| 10 |
+
3,
|
| 11 |
+
24,
|
| 12 |
+
32
|
| 13 |
+
],
|
| 14 |
+
"stage_in_channels": [
|
| 15 |
+
32,
|
| 16 |
+
96,
|
| 17 |
+
384,
|
| 18 |
+
768
|
| 19 |
+
],
|
| 20 |
+
"stage_mid_channels": [
|
| 21 |
+
32,
|
| 22 |
+
64,
|
| 23 |
+
128,
|
| 24 |
+
256
|
| 25 |
+
],
|
| 26 |
+
"stage_out_channels": [
|
| 27 |
+
96,
|
| 28 |
+
384,
|
| 29 |
+
768,
|
| 30 |
+
1536
|
| 31 |
+
],
|
| 32 |
+
"stage_num_blocks": [
|
| 33 |
+
1,
|
| 34 |
+
1,
|
| 35 |
+
3,
|
| 36 |
+
1
|
| 37 |
+
],
|
| 38 |
+
"stage_numb_of_layers": [
|
| 39 |
+
4,
|
| 40 |
+
4,
|
| 41 |
+
4,
|
| 42 |
+
4
|
| 43 |
+
],
|
| 44 |
+
"use_lab": true,
|
| 45 |
+
"encoder_in_channels": [
|
| 46 |
+
384,
|
| 47 |
+
768,
|
| 48 |
+
1536
|
| 49 |
+
],
|
| 50 |
+
"ccfm_num_blocks": 2,
|
| 51 |
+
"decoder_num_layers": 4,
|
| 52 |
+
"decoder_n_points": [
|
| 53 |
+
3,
|
| 54 |
+
6,
|
| 55 |
+
3
|
| 56 |
+
]
|
| 57 |
+
}
|
| 58 |
+
}
|