depth2depth model files: DA2-Small metric Hypersim (safetensors for candle, 364x448 ONNX for TensorRT)

README.md

@@ -0,0 +1,19 @@
+---
+license: apache-2.0
+base_model: depth-anything/Depth-Anything-V2-Metric-Hypersim-Small
+tags:
+  - depth-estimation
+  - depth2depth
+---
+
+# depth2depth model files
+
+The model files the [depth2depth](https://github.com/jeff-hykin/depth2depth) crate builds into itself. They are
+Depth Anything V2 Small, metric, Hypersim (indoor, max depth 20 m), converted from the official
+`depth_anything_v2_metric_hypersim_vits.pth`:
+
+- `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.
+
+The crate pins these files by sha256 in its `model.json`. Weights are Apache-2.0, as the upstream Small model.

da2_head_vits.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f9f283b1355547f8871312ad2279088e89dbe280b9232b0cee056812e6bc786
+size 10921332

da2_metric_hypersim_vits_364x448.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7e55312dc399f19f619f349434c29c21b470043826b8223deb48d2ef41f3181
+size 98940388

dinov2_vits14.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd0ce9e13402978685c13cbfab905493dd947c15308ba21c74e21df1600f0075
+size 91316672