Instructions to use zeromodels/depth_anything_small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ZeroModels
How to use zeromodels/depth_anything_small 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/depth_anything_small") - Keras
How to use zeromodels/depth_anything_small 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/depth_anything_small") - Notebooks
- Google Colab
- Kaggle
docs: load image processor via from_weights
Browse files
README.md
CHANGED
|
@@ -42,7 +42,7 @@ from PIL import Image
|
|
| 42 |
from kerasformers.models.depth_anything_v1 import DepthAnythingV1DepthEstimation, DepthAnythingV1ImageProcessor
|
| 43 |
|
| 44 |
model = DepthAnythingV1DepthEstimation.from_weights("kerasformers/depth_anything_small")
|
| 45 |
-
processor = DepthAnythingV1ImageProcessor()
|
| 46 |
|
| 47 |
image = Image.open("your_image.jpg").convert("RGB")
|
| 48 |
output = model(processor(image)["pixel_values"], training=False)
|
|
|
|
| 42 |
from kerasformers.models.depth_anything_v1 import DepthAnythingV1DepthEstimation, DepthAnythingV1ImageProcessor
|
| 43 |
|
| 44 |
model = DepthAnythingV1DepthEstimation.from_weights("kerasformers/depth_anything_small")
|
| 45 |
+
processor = DepthAnythingV1ImageProcessor.from_weights("kerasformers/depth_anything_small")
|
| 46 |
|
| 47 |
image = Image.open("your_image.jpg").convert("RGB")
|
| 48 |
output = model(processor(image)["pixel_values"], training=False)
|