fp16 model

animation

Update framework to ONNX Runtime (FP32/FP16), remove Apple dependencies, add validation script for ONNX conversion with FP32-preserving ops, fix FP16 precision issues, update inference CLI with depth exaggeration, rename docs, and enable LFS support.

Refactor FP16 quantization using ONNX-native methods, update tolerance configs for depth/quaternions/colors, add FP32-preserving op block list, fix calibration workflow, enhance validation with FP16/FP32 distinction, optimize inference with external data support.

something

Fix precision tolerances, remove legacy FP16 logic, update data handling, standardize execution provider

Add precision constraints for ops like Resize/Gather, optimize FP16 casting with onnxoptimizer fallback, implement dynamic cast helpers, update CoreML provider priority, improve mixed-float error handling

inference script

updates to conversion

Add quaternion validation, enable dynamic tolerance config, optimize ONNX export, fix race conditions in cleanup, add image-based validation, improve structured output reporting.

initial stuff

initial commit