Instructions to use zeromodels/eomt_large_coco_instance_640 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ZeroModels
How to use zeromodels/eomt_large_coco_instance_640 with ZeroModels:
# pip install -U zeromodels # ZeroModels is pure Keras 3, so pick a backend: "jax", "torch" or "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" from zeromodels import AutoZModel # AutoZModel reads the repo's model_type and loads the matching class. # For a task head use the matching loader, e.g. AutoZMImageClassify / AutoZMDetect / # AutoZMSemanticSegment / AutoZMTextGenerate (see zeromodels.auto). model = AutoZModel.from_weights("zeromodels/eomt_large_coco_instance_640") - Keras
How to use zeromodels/eomt_large_coco_instance_640 with Keras:
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://zeromodels/eomt_large_coco_instance_640") - Notebooks
- Google Colab
- Kaggle
Upload kf_config.json with huggingface_hub
Browse files- kf_config.json +25 -0
kf_config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"library_name": "kerasformers",
|
| 3 |
+
"kerasformers_version": "1.1.3",
|
| 4 |
+
"model_module": "kerasformers.models.eomt",
|
| 5 |
+
"model_class": "EoMTUniversalSegment",
|
| 6 |
+
"variant": "eomt_large_coco_instance_640",
|
| 7 |
+
"weights": "model.weights.h5",
|
| 8 |
+
"model_type": "eomt",
|
| 9 |
+
"hidden_dim": 1024,
|
| 10 |
+
"num_hidden_layers": 24,
|
| 11 |
+
"num_heads": 16,
|
| 12 |
+
"depths": 4,
|
| 13 |
+
"num_queries": 200,
|
| 14 |
+
"num_classes": 80,
|
| 15 |
+
"layerscale_value": 1e-05,
|
| 16 |
+
"patch_size": 16,
|
| 17 |
+
"num_register_tokens": 4,
|
| 18 |
+
"num_upscale_blocks": 2,
|
| 19 |
+
"mlp_ratio": 4,
|
| 20 |
+
"drop_path_rate": 0.0,
|
| 21 |
+
"attention_dropout": 0.0,
|
| 22 |
+
"use_swiglu_ffn": false,
|
| 23 |
+
"layer_norm_eps": 1e-06,
|
| 24 |
+
"image_size": 640
|
| 25 |
+
}
|