Upload from Ropedia Academy

README.md

@@ -1,13 +1,54 @@
 ---
 license: mit
+library_name: pytorch
 tags:
 - ropedia-academy
 - educational
+- keypoint-detection
 ---
 
-# A_pose_heatmap
+# 2D pose estimation (heatmap regression)
 
-Trained from scratch in **Ropedia Academy** (https://chaoyue0307.github.io/ropedia-academy/) — an educational lab. The checkpoint and full loss/eval history (`metrics.json`) are included.
+A fully-convolutional net that predicts per-joint heatmaps, decoded to coordinates by soft-argmax. Best-checkpoint by PCK.
 
+Trained from scratch in **[Ropedia Academy](https://chaoyue0307.github.io/ropedia-academy/)** — an interactive, bilingual course on embodied & spatial AI. **Educational model:** small and quick to train; the value is the *method* and a reproducible pipeline, not a leaderboard score.
 
-![results](figure.png)
+| | |
+|---|---|
+| **Task** | 2D keypoint detection |
+| **Data** | synthetic articulated arm |
+| **Track** | A · Human modeling |
+| **Notebook** | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ChaoYue0307/ropedia-academy/blob/main/notebooks/training/A_pose_heatmap.ipynb) |
+
+## Results
+
+| metric | value |
+|---|---|
+| pck (final) | 0.396 |
+
+
+![figure](figure.png)
+
+## How to use
+
+```python
+import torch
+state = torch.load("model.pt", map_location="cpu")   # some labs save pose.pt / gaussians.pt / transform.pt
+# Rebuild the model class from the Ropedia Academy notebook (linked above), then:
+# model.load_state_dict(state)
+```
+
+## Files
+
+- `figure.png`
+- `metrics.json`
+- `pose.pt`
+
+
+## Reproduce / train your own
+
+Open the [lab notebook in Colab](https://colab.research.google.com/github/ChaoYue0307/ropedia-academy/blob/main/notebooks/training/A_pose_heatmap.ipynb) → **Runtime → GPU → Run all**, then its *Publish to the Hugging Face Hub* cell. Browse every lab in the [Ropedia Academy Labs tab](https://chaoyue0307.github.io/ropedia-academy/labs).
+
+
+---
+*Part of the [Ropedia Academy](https://chaoyue0307.github.io/ropedia-academy/) trained-model collection.*

metrics.json

@@ -2,47 +2,47 @@
   "pck": [
     [
       0,
-      0.188
+      0.349
     ],
     [
       100,
-      0.333
+      0.328
     ],
     [
       200,
-      0.375
+      0.365
     ],
     [
       300,
-      0.292
+      0.406
     ],
     [
       400,
-      0.333
+      0.391
     ],
     [
       500,
-      0.417
+      0.391
     ],
     [
       600,
-      0.438
+      0.411
     ],
     [
       700,
-      0.354
+      0.401
     ],
     [
       800,
-      0.438
+      0.406
     ],
     [
       900,
-      0.521
+      0.375
     ],
     [
       1000,
-      0.458
+      0.396
     ]
   ]
 }

pose.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ee409899d373f66344104204ae33f5ef75b85d3fcc8206cca995739d7ab4e53
+oid sha256:1bb8ac0d292cba19d91258ab1097db2109ff4aeffd7efa86d796d32eb901d9ff
 size 122339