ONNX export with a dynamic input size

README.md

@@ -14,7 +14,8 @@ Depth Anything V2 Small, metric, Hypersim (indoor, max depth 20 m), converted fr
 
 - `dinov2_vits14.safetensors`, `da2_head_vits.safetensors`: the encoder and the DPT head, for candle
   (converted by `tools/convert_weights.py`; includes the unused ImageNet classifier head candle's dinov2 loads).
-- `da2_metric_hypersim_vits_364x448.onnx`: an ONNX export with a fixed 364x448 input, for TensorRT on Jetsons.
+- `da2_metric_hypersim_vits.onnx`: an ONNX export taking any input size that is a multiple of 14, for TensorRT
+  (made by the crate's `tools/export_onnx.py`). `da2_metric_hypersim_vits_364x448.onnx` is the older fixed-size one.
 - `da2_metric_hypersim_vits_364x448_trt100700_sm87.engine`: that ONNX as an fp16 TensorRT 10.7 engine, built on a
   Jetson AGX Orin (sm_87, JetPack 6 / L4T R36.3), so Orins skip the minutes-long engine build. Other TensorRT
   versions or GPUs reject it and the crate builds its own from the ONNX.

da2_metric_hypersim_vits.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beaeaeacdb66fc067fc82dd30463b255549367dc251d6cdff3db31bc3edf0750
+size 101177651