Instructions to use zeromodels/depth_anything_v2_large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use zeromodels/depth_anything_v2_large 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/depth_anything_v2_large") - DepthAnythingV2
How to use zeromodels/depth_anything_v2_large with DepthAnythingV2:
# Install from https://github.com/DepthAnything/Depth-Anything-V2 # Load the model and infer depth from an image import cv2 import torch from depth_anything_v2.dpt import DepthAnythingV2 # instantiate the model model = DepthAnythingV2(encoder="<ENCODER>", features=<NUMBER_OF_FEATURES>, out_channels=<OUT_CHANNELS>) # load the weights filepath = hf_hub_download(repo_id="zeromodels/depth_anything_v2_large", filename="depth_anything_v2_<ENCODER>.pth", repo_type="model") state_dict = torch.load(filepath, map_location="cpu") model.load_state_dict(state_dict).eval() raw_img = cv2.imread("your/image/path") depth = model.infer_image(raw_img) # HxW raw depth map in numpy - Notebooks
- Google Colab
- Kaggle
Upload kf_config.json with huggingface_hub
Browse files- kf_config.json +34 -0
kf_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"library_name": "kerasformers",
|
| 3 |
+
"kerasformers_version": "1.1.3",
|
| 4 |
+
"model_module": "kerasformers.models.depth_anything_v2",
|
| 5 |
+
"model_class": "DepthAnythingV2DepthEstimation",
|
| 6 |
+
"variant": "depth_anything_v2_large",
|
| 7 |
+
"weights": "model.weights.h5",
|
| 8 |
+
"model_type": "depth_anything",
|
| 9 |
+
"backbone_dim": 1024,
|
| 10 |
+
"backbone_depth": 24,
|
| 11 |
+
"backbone_num_heads": 16,
|
| 12 |
+
"out_indices": [
|
| 13 |
+
5,
|
| 14 |
+
12,
|
| 15 |
+
18,
|
| 16 |
+
24
|
| 17 |
+
],
|
| 18 |
+
"neck_hidden_sizes": [
|
| 19 |
+
256,
|
| 20 |
+
512,
|
| 21 |
+
1024,
|
| 22 |
+
1024
|
| 23 |
+
],
|
| 24 |
+
"fusion_hidden_size": 256,
|
| 25 |
+
"reassemble_factors": [
|
| 26 |
+
4,
|
| 27 |
+
2,
|
| 28 |
+
1,
|
| 29 |
+
0.5
|
| 30 |
+
],
|
| 31 |
+
"depth_estimation_type": "relative",
|
| 32 |
+
"max_depth": 1.0,
|
| 33 |
+
"image_size": 518
|
| 34 |
+
}
|