Add baseline checkpoints

README.md

@@ -0,0 +1,29 @@
+---
+license: mit
+library_name: pytorch
+tags:
+- robotics
+- tactile-sensing
+- multimodal
+datasets:
+- TUM-ICS/Hide-and-Seek
+---
+
+# HAS-Bench Baselines
+
+Pretrained baseline checkpoints for the [Hide-and-Seek tactile dataset](https://huggingface.co/datasets/TUM-ICS/Hide-and-Seek): a dual-head multimodal classifier with an object head and a weight head, trained with the public release pipeline (seed 42).
+
+| File | Modalities |
+|---|---|
+| `m123/best_model.pt` | tactile point cloud + raw skin signals + virtual skin wrenches |
+| `m12345/best_model.pt` | + end-effector pose + wrist F/T |
+
+Each directory also contains the `last_metrics.json` written at the end of training.
+
+## Usage
+
+```bash
+hf download TUM-ICS/HAS-Bench-baselines --local-dir checkpoints
+```
+
+Dataloaders and evaluation scripts: https://github.com/TUM-ICS/Tactile-Hide-and-Seek

m123/best_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0281881557edca98d31f836bd0f8764573c97de49cc6c6fb5112ca86455c5a55
+size 6968475

m123/last_metrics.json

@@ -0,0 +1,8 @@
+{
+  "validation": {
+    "loss": 0.41280303381904654,
+    "object_acc": 0.9346707818930041,
+    "weight_acc": 0.875,
+    "joint_acc": 0.8461934156378601
+  }
+}

m12345/best_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a89dd9182fc8b522ff6b7b466d220dea819c8dda7ae4d813137db17262c695f5
+size 10306331

m12345/last_metrics.json

@@ -0,0 +1,8 @@
+{
+  "validation": {
+    "loss": 0.4156359742345756,
+    "object_acc": 0.9382716049382716,
+    "weight_acc": 0.885545267489712,
+    "joint_acc": 0.856224279835391
+  }
+}