Instructions to use julienkay/sentis-DepthPro-float16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- unity-sentis
How to use julienkay/sentis-DepthPro-float16 with unity-sentis:
string modelName = "[Your model name here].sentis"; Model model = ModelLoader.Load(Application.streamingAssetsPath + "/" + modelName); IWorker engine = WorkerFactory.CreateWorker(BackendType.GPUCompute, model); // Please see provided C# file for more details
- Notebooks
- Google Colab
- Kaggle
metadata
license: apple-ascl
base_model:
- apple/DepthPro
library_name: unity-sentis
pipeline_tag: depth-estimation
The DepthPro model converted to Unity Sentis
The model uses a static input with shape (1, 3, 1536, 1536). The image is expected to be in the [-1.0, 1.0] range. Models were converted and quantized to float16 format using Sentis v2.1.0