Upload curated v1 multihead ONNX bundle

Source run: runs/20260610_curated_v1_multihead_w10_cuda
Tag: curated-v1-multihead-w10-cuda-20260610
Includes SDK bundle files and confusion-matrix reports.

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+action_classifier_curated_v1_multihead_w10_cuda.onnx.data filter=lfs diff=lfs merge=lfs -text
+reports/confusion_locomotion.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,36 @@
+---
+library_name: onnx
+tags:
+- action-recognition
+- mediapipe
+- onnx
+- sdk-bundle
+---
+
+# VideoInference
+
+ActionLinkPerception SDK model bundle.
+
+## Version
+
+- Tag: `curated-v1-multihead-w10-cuda-20260610`
+- Source run: `runs/20260610_curated_v1_multihead_w10_cuda`
+- Window size: 10 frames
+- Dataset: `dataset/clip_data_back_v1_curated_20260610`
+
+## Files
+
+- `manifest.json`: SDK bundle entry point
+- `model.onnx`: ONNX graph
+- `action_classifier_curated_v1_multihead_w10_cuda.onnx.data`: ONNX external tensor data
+- `model.json`: label maps, heads, keypoints and metadata
+- `smoothing.json`: SDK label smoothing configuration
+- `reports/`: training log and confusion matrices
+
+## Usage
+
+Download this repo with Hugging Face CLI and point the SDK model bundle directory to the downloaded folder.
+
+```powershell
+hf download Zihanj/VideoInference --local-dir .\models\VideoInference --local-dir-use-symlinks False
+```

action_classifier_curated_v1_multihead_w10_cuda.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c978bac43086354be483a797a809ebfa3093af0e62d70818401eb6deacc7751
+size 5192488

manifest.json

@@ -0,0 +1,6 @@
+{
+  "tag": "curated-v1-multihead-w10-cuda-20260610",
+  "model": "model.onnx",
+  "metadata": "model.json",
+  "smoothing": "smoothing.json"
+}

model.json

@@ -0,0 +1,235 @@
+{
+  "model_file": "action_classifier_curated_v1_multihead_w10_cuda.onnx",
+  "window": 10,
+  "feat_per_frame": 731,
+  "input": {
+    "name": "skeleton_window",
+    "shape": [
+      "batch",
+      10,
+      731
+    ],
+    "dtype": "float32",
+    "description": "Sliding window of skeleton features. Each frame is a 731-dim vector: hip-centred (x,y,z,conf)×73 + motion_mag + ref_offset(dx,dy,dz)×73 + ref_std×73. World coordinates (metres, hip-centred). See docs/arch/v1.1/README.md for feature layout."
+  },
+  "outputs": [
+    {
+      "name": "locomotion",
+      "shape": [
+        "batch",
+        18
+      ],
+      "dtype": "float32",
+      "classes": [
+        "walk",
+        "fastwalk",
+        "run",
+        "lowrun",
+        "lstride",
+        "lstride_back",
+        "rstride",
+        "rstride_back",
+        "lfwdstride",
+        "lfwdstride_back",
+        "rfwdstride",
+        "rfwdstride_back",
+        "lbkstep",
+        "lbkstep_back",
+        "rbkstep",
+        "rbkstep_back",
+        "highknee",
+        "noaction"
+      ],
+      "label_map": {
+        "walk": 0,
+        "fastwalk": 1,
+        "run": 2,
+        "lowrun": 3,
+        "lstride": 4,
+        "lstride_back": 5,
+        "rstride": 6,
+        "rstride_back": 7,
+        "lfwdstride": 8,
+        "lfwdstride_back": 9,
+        "rfwdstride": 10,
+        "rfwdstride_back": 11,
+        "lbkstep": 12,
+        "lbkstep_back": 13,
+        "rbkstep": 14,
+        "rbkstep_back": 15,
+        "highknee": 16,
+        "noaction": 17
+      },
+      "noaction_index": 17
+    },
+    {
+      "name": "jump_squat",
+      "shape": [
+        "batch",
+        5
+      ],
+      "dtype": "float32",
+      "classes": [
+        "jump",
+        "jump_back",
+        "squat",
+        "squat_back",
+        "noaction"
+      ],
+      "label_map": {
+        "jump": 0,
+        "jump_back": 1,
+        "squat": 2,
+        "squat_back": 3,
+        "noaction": 4
+      },
+      "noaction_index": 4
+    },
+    {
+      "name": "arms",
+      "shape": [
+        "batch",
+        6
+      ],
+      "dtype": "float32",
+      "classes": [
+        "larmchop",
+        "rarmchop",
+        "multichop",
+        "larmlowside",
+        "rarmlowside",
+        "noaction"
+      ],
+      "label_map": {
+        "larmchop": 0,
+        "rarmchop": 1,
+        "multichop": 2,
+        "larmlowside": 3,
+        "rarmlowside": 4,
+        "noaction": 5
+      },
+      "noaction_index": 5
+    },
+    {
+      "name": "hands",
+      "shape": [
+        "batch",
+        7
+      ],
+      "dtype": "float32",
+      "classes": [
+        "lhandgesture",
+        "rhandgesture",
+        "bothhandgesture",
+        "lhandchest",
+        "rhandchest",
+        "pickup",
+        "noaction"
+      ],
+      "label_map": {
+        "lhandgesture": 0,
+        "rhandgesture": 1,
+        "bothhandgesture": 2,
+        "lhandchest": 3,
+        "rhandchest": 4,
+        "pickup": 5,
+        "noaction": 6
+      },
+      "noaction_index": 6
+    },
+    {
+      "name": "seals",
+      "shape": [
+        "batch",
+        6
+      ],
+      "dtype": "float32",
+      "classes": [
+        "lhandseal",
+        "rhandseal",
+        "headseal",
+        "chestseal",
+        "bellyseal",
+        "noaction"
+      ],
+      "label_map": {
+        "lhandseal": 0,
+        "rhandseal": 1,
+        "headseal": 2,
+        "chestseal": 3,
+        "bellyseal": 4,
+        "noaction": 5
+      },
+      "noaction_index": 5
+    },
+    {
+      "name": "head",
+      "shape": [
+        "batch",
+        5
+      ],
+      "dtype": "float32",
+      "classes": [
+        "headdown",
+        "headup",
+        "lheadturn",
+        "rheadturn",
+        "noaction"
+      ],
+      "label_map": {
+        "headdown": 0,
+        "headup": 1,
+        "lheadturn": 2,
+        "rheadturn": 3,
+        "noaction": 4
+      },
+      "noaction_index": 4
+    },
+    {
+      "name": "torso",
+      "shape": [
+        "batch",
+        5
+      ],
+      "dtype": "float32",
+      "classes": [
+        "llean",
+        "rlean",
+        "lshoulderturn",
+        "rshoulderturn",
+        "noaction"
+      ],
+      "label_map": {
+        "llean": 0,
+        "rlean": 1,
+        "lshoulderturn": 2,
+        "rshoulderturn": 3,
+        "noaction": 4
+      },
+      "noaction_index": 4
+    },
+    {
+      "name": "poses",
+      "shape": [
+        "batch",
+        5
+      ],
+      "dtype": "float32",
+      "classes": [
+        "tpose",
+        "tpose_back",
+        "ypose",
+        "ypose_back",
+        "noaction"
+      ],
+      "label_map": {
+        "tpose": 0,
+        "tpose_back": 1,
+        "ypose": 2,
+        "ypose_back": 3,
+        "noaction": 4
+      },
+      "noaction_index": 4
+    }
+  ]
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec5f6d87bc0466b9741510f37a2925c6c6d158ec4bf417ed50458fddec6c9349
+size 116025

reports/train.log

@@ -0,0 +1,292 @@
+  [partial train] only training branches: ['arms', 'hands', 'jump_squat', 'locomotion', 'poses']
+  [base model] loaded 8 branches from model_jump_squat_squat_fast_rise_w10_cuda.pth: ['locomotion', 'jump_squat', 'arms', 'hands', 'seals', 'head', 'torso', 'poses']
+Loading data from dataset\clip_data_back_v1_curated_20260610 …
+  [partial load] loading 37 classes, skipping 13: ['bellyseal', 'chestseal', 'headdown', 'headseal', 'headup', 'lhandseal', 'lheadturn', 'llean', 'lshoulderturn', 'rhandseal', 'rheadturn', 'rlean', 'rshoulderturn']
+  calibration: 37 clips matched to noaction, 1009 clips using own frame-0 fallback
+  classes : ['bellyseal', 'bothhandgesture', 'chestseal', 'fastwalk', 'headdown', 'headseal', 'headup', 'highknee', 'jump', 'jump_back', 'larmchop', 'larmlowside', 'lbkstep', 'lbkstep_back', 'lfwdstride', 'lfwdstride_back', 'lhandchest', 'lhandgesture', 'lhandseal', 'lheadturn', 'llean', 'lowrun', 'lshoulderturn', 'lstride', 'lstride_back', 'multichop', 'noaction', 'pickup', 'rarmchop', 'rarmlowside', 'rbkstep', 'rbkstep_back', 'rfwdstride', 'rfwdstride_back', 'rhandchest', 'rhandgesture', 'rhandseal', 'rheadturn', 'rlean', 'rshoulderturn', 'rstride', 'rstride_back', 'run', 'squat', 'squat_back', 'tpose', 'tpose_back', 'walk', 'ypose', 'ypose_back']
+  files   : 1017  |  windows: 49231
+  train files=932  test files=85
+  device  : cuda
+  run dir : C:\Workspace\ActionLinkPerception\runs\20260610_curated_v1_multihead_w10_cuda
+
+  model   : multi-branch ensemble (['locomotion', 'jump_squat', 'arms', 'hands', 'seals', 'head', 'torso', 'poses'])
+    [build_samples] remapped→noaction: 20705 kept=20705 (action_windows=23204, ratio=1)  dropped: 0
+    [build_samples] remapped→noaction: 1988  dropped: 0
+
+── Branch [locomotion] keypoints=['left_hip', 'right_hip', 'left_knee', 'right_knee', 'left_ankle', 'right_ankle', 'left_heel', 'right_heel', 'left_foot_index', 'right_foot_index']  classes=['walk', 'fastwalk', 'run', 'lowrun', 'lstride', 'lstride_back', 'rstride', 'rstride_back', 'lfwdstride', 'lfwdstride_back', 'rfwdstride', 'rfwdstride_back', 'lbkstep', 'lbkstep_back', 'rbkstep', 'rbkstep_back', 'highknee', 'noaction']
+   train=45208  test=4023
+  [locomotion] training settings: batch=96, lr=0.001, weight_decay=0.0001, label_smoothing=0.05, class_weight_mode=inverse, augment=True
+  [locomotion] class weights:
+    walk         0.68
+    fastwalk     5.41
+    run          0.65
+    lowrun       3.84
+    lstride      2.11
+    lstride_back 2.68
+    rstride      1.93
+    rstride_back 4.08
+    lfwdstride   2.21
+    lfwdstride_back 3.92
+    rfwdstride   2.20
+    rfwdstride_back 7.02
+    lbkstep      2.08
+    lbkstep_back 5.23
+    rbkstep      2.33
+    rbkstep_back 4.26
+    highknee     0.65
+    noaction     0.11
+  [locomotion] select metric: macro_f1
+  [locomotion] epoch   1/35  loss=1.9875  test_acc=0.3791  macro_f1=0.3785  weighted_f1=0.4203  select=0.3785
+  [locomotion] epoch  10/35  loss=1.2763  test_acc=0.6030  macro_f1=0.5282  weighted_f1=0.6425  select=0.5282
+  [locomotion] epoch  20/35  loss=1.1639  test_acc=0.7375  macro_f1=0.6295  weighted_f1=0.7441  select=0.6295
+  [locomotion] epoch  30/35  loss=1.1183  test_acc=0.7102  macro_f1=0.6275  weighted_f1=0.7351  select=0.6275
+  [locomotion] Best selected metric (macro_f1): 0.6421 @ epoch 25  acc=0.7298
+  [locomotion] Per-class test accuracy:
+    walk           153/ 413  37.05%
+    fastwalk         4/  86  4.65%
+    run            170/ 216  78.70%
+    lowrun          91/ 109  83.49%
+    lstride         32/  48  66.67%
+    lstride_back    62/  62  100.00%
+    rstride         62/  83  74.70%
+    rstride_back    51/  51  100.00%
+    lfwdstride      46/  77  59.74%
+    lfwdstride_back    33/  40  82.50%
+    rfwdstride      88/  96  91.67%
+    rfwdstride_back    43/  51  84.31%
+    lbkstep         68/  77  88.31%
+    lbkstep_back     2/   2  100.00%
+    rbkstep         56/ 122  45.90%
+    rbkstep_back    37/  37  100.00%
+    highknee       181/ 242  74.79%
+    noaction      1757/2211  79.47%
+
+  [locomotion] Classification metrics:
+    class          prec  recall     f1   supp   sw_rate   sw# n_clip  perfect
+    ------------------------------------------------------------------------------
+    walk          0.845   0.370  0.515    413     0.058  8.00      3        0
+    fastwalk      0.085   0.047  0.060     86     0.106  9.00      1        0
+    run           0.756   0.787  0.771    216     0.047  5.00      2        0
+    lowrun        0.843   0.835  0.839    109     0.037  4.00      1        0
+    lstride       0.166   0.667  0.266     48     0.039  0.67      3        1
+    lstride_back  1.000   1.000  1.000     62     0.000  0.00      3        3
+    rstride       0.805   0.747  0.775     83     0.068  1.33      3        0
+    rstride_back  1.000   1.000  1.000     51     0.000  0.00      3        3
+    lfwdstride    0.177   0.597  0.273     77     0.160  6.00      2        0
+    lfwdstride_back  1.000   0.825  0.904     40     0.019  0.50      2        1
+    rfwdstride    0.391   0.917  0.548     96     0.041  2.00      2        1
+    rfwdstride_back  1.000   0.843  0.915     51     0.050  1.00      2        1
+    lbkstep       0.591   0.883  0.708     77     0.087  2.00      2        1
+    lbkstep_back  0.071   1.000  0.133      2     0.000  0.00      1        1
+    rbkstep       0.862   0.459  0.599    122     0.080  6.00      2        0
+    rbkstep_back  0.712   1.000  0.831     37     0.000  0.00      2        2
+    highknee      0.439   0.748  0.554    242     0.029  3.50      2        0
+    noaction      0.952   0.795  0.866   2211     0.037  1.84     49       24
+    accuracy      0.730
+    macro         0.650   0.751  0.642
+    weighted      0.828   0.730  0.753
+
+  [locomotion] Label smoothness (per clip):
+    clips evaluated : 85  (mean len 47.3 windows)
+    mean switches   : 2.18
+    mean switch rate: 0.041  (0 = no flipping, 1 = flip every frame)
+    perfectly stable clips: 38 / 85
+  [locomotion] Confusion matrix → C:\Workspace\ActionLinkPerception\runs\20260610_curated_v1_multihead_w10_cuda\confusion_locomotion.png
+    [build_samples] remapped→noaction: 41171 kept=2738 (action_windows=2738, ratio=1)  dropped: 0
+    [build_samples] remapped→noaction: 3465  dropped: 0
+
+── Branch [jump_squat] keypoints=['left_shoulder', 'right_shoulder', 'left_hip', 'right_hip', 'left_knee', 'right_knee', 'left_ankle', 'right_ankle', 'left_heel', 'right_heel', 'left_foot_index', 'right_foot_index']  classes=['jump', 'jump_back', 'squat', 'squat_back', 'noaction']
+   train=6775  test=4023
+  [jump_squat] training settings: batch=96, lr=0.001, weight_decay=0.0001, label_smoothing=0.05, class_weight_mode=inverse, augment=True
+  [jump_squat] class weights:
+    jump         1.18
+    jump_back    3.34
+    squat        4.84
+    squat_back   1.50
+    noaction     0.34
+  [jump_squat] select metric: macro_f1
+  [jump_squat] epoch   1/35  loss=1.0462  test_acc=0.8459  macro_f1=0.4195  weighted_f1=0.8664  select=0.4195
+  [jump_squat] epoch  10/35  loss=0.5983  test_acc=0.7857  macro_f1=0.4877  weighted_f1=0.8498  select=0.4877
+  [jump_squat] epoch  20/35  loss=0.5445  test_acc=0.8620  macro_f1=0.6241  weighted_f1=0.8965  select=0.6241
+  [jump_squat] epoch  30/35  loss=0.5208  test_acc=0.9182  macro_f1=0.7559  weighted_f1=0.9312  select=0.7559
+  [jump_squat] Best selected metric (macro_f1): 0.7943 @ epoch 26  acc=0.9354
+  [jump_squat] Per-class test accuracy:
+    jump           135/ 166  81.33%
+    jump_back       58/  61  95.08%
+    squat           11/  11  100.00%
+    squat_back      97/  97  100.00%
+    noaction      3462/3688  93.87%
+
+  [jump_squat] Classification metrics:
+    class          prec  recall     f1   supp   sw_rate   sw# n_clip  perfect
+    ------------------------------------------------------------------------------
+    jump          0.429   0.813  0.561    166     0.058  3.00      3        1
+    jump_back     0.716   0.951  0.817     61     0.013  0.33      3        2
+    squat         0.550   1.000  0.710     11     0.000  0.00      3        3
+    squat_back    0.851   1.000  0.919     97     0.000  0.00      4        4
+    noaction      0.991   0.939  0.964   3688     0.012  0.69     72       53
+    accuracy      0.935
+    macro         0.707   0.941  0.794
+    weighted      0.959   0.935  0.944
+
+  [jump_squat] Label smoothness (per clip):
+    clips evaluated : 85  (mean len 47.3 windows)
+    mean switches   : 0.71
+    mean switch rate: 0.012  (0 = no flipping, 1 = flip every frame)
+    perfectly stable clips: 63 / 85
+  [jump_squat] Confusion matrix → C:\Workspace\ActionLinkPerception\runs\20260610_curated_v1_multihead_w10_cuda\confusion_jump_squat.png
+    [build_samples] remapped→noaction: 34332 kept=9577 (action_windows=9577, ratio=1)  dropped: 0
+    [build_samples] remapped→noaction: 2940  dropped: 0
+
+── Branch [arms] keypoints=['left_shoulder', 'right_shoulder', 'left_elbow', 'right_elbow', 'left_wrist', 'right_wrist', 'left_pinky', 'right_pinky', 'left_index', 'right_index', 'left_thumb', 'right_thumb']  classes=['larmchop', 'rarmchop', 'multichop', 'larmlowside', 'rarmlowside', 'noaction']
+   train=20453  test=4023
+  [arms] training settings: batch=96, lr=0.001, weight_decay=0.0001, label_smoothing=0.05, class_weight_mode=inverse, augment=True
+  [arms] class weights:
+    larmchop     2.46
+    rarmchop     2.22
+    multichop    1.00
+    larmlowside  2.07
+    rarmlowside  2.15
+    noaction     0.31
+  [arms] select metric: macro_f1
+  [arms] epoch   1/35  loss=1.0829  test_acc=0.4919  macro_f1=0.5031  weighted_f1=0.5718  select=0.5031
+  [arms] epoch  10/35  loss=0.6931  test_acc=0.8484  macro_f1=0.7428  weighted_f1=0.8715  select=0.7428
+  [arms] epoch  20/35  loss=0.6171  test_acc=0.8541  macro_f1=0.7129  weighted_f1=0.8725  select=0.7129
+  [arms] epoch  30/35  loss=0.5746  test_acc=0.8633  macro_f1=0.7430  weighted_f1=0.8790  select=0.7430
+  [arms] Best selected metric (macro_f1): 0.7892 @ epoch 28  acc=0.9075
+  [arms] Per-class test accuracy:
+    larmchop       116/ 128  90.62%
+    rarmchop       114/ 157  72.61%
+    multichop      306/ 379  80.74%
+    larmlowside     83/  83  100.00%
+    rarmlowside    105/ 113  92.92%
+    noaction      2927/3163  92.54%
+
+  [arms] Classification metrics:
+    class          prec  recall     f1   supp   sw_rate   sw# n_clip  perfect
+    ------------------------------------------------------------------------------
+    larmchop      0.655   0.906  0.761    128     0.013  0.67      3        2
+    rarmchop      0.437   0.726  0.545    157     0.044  2.33      3        0
+    multichop     0.867   0.807  0.836    379     0.032  3.25      4        0
+    larmlowside   0.741   1.000  0.851     83     0.000  0.00      2        2
+    rarmlowside   0.682   0.929  0.787    113     0.029  1.50      2        0
+    noaction      0.987   0.925  0.955   3163     0.014  0.62     71       50
+    accuracy      0.908
+    macro         0.728   0.882  0.789
+    weighted      0.930   0.908  0.915
+
+  [arms] Label smoothness (per clip):
+    clips evaluated : 85  (mean len 47.3 windows)
+    mean switches   : 0.81
+    mean switch rate: 0.016  (0 = no flipping, 1 = flip every frame)
+    perfectly stable clips: 54 / 85
+  [arms] Confusion matrix → C:\Workspace\ActionLinkPerception\runs\20260610_curated_v1_multihead_w10_cuda\confusion_arms.png
+    [build_samples] remapped→noaction: 37741 kept=6168 (action_windows=6168, ratio=1)  dropped: 0
+    [build_samples] remapped→noaction: 3231  dropped: 0
+
+── Branch [hands] keypoints=['left_shoulder', 'right_shoulder', 'left_elbow', 'right_elbow', 'left_wrist', 'right_wrist', 'left_pinky', 'right_pinky', 'left_index', 'right_index', 'left_thumb', 'right_thumb']  classes=['lhandgesture', 'rhandgesture', 'bothhandgesture', 'lhandchest', 'rhandchest', 'pickup', 'noaction']
+   train=13635  test=4023
+  [hands] training settings: batch=96, lr=0.001, weight_decay=0.0001, label_smoothing=0.05, class_weight_mode=inverse, augment=True
+  [hands] class weights:
+    lhandgesture 13.25
+    rhandgesture 10.94
+    bothhandgesture 9.99
+    lhandchest   1.44
+    rhandchest   0.96
+    pickup       0.86
+    noaction     0.26
+  [hands] select metric: macro_f1
+  [hands] epoch   1/35  loss=1.6970  test_acc=0.3659  macro_f1=0.3179  weighted_f1=0.4572  select=0.3179
+  [hands] epoch  10/35  loss=1.2178  test_acc=0.7517  macro_f1=0.5221  weighted_f1=0.8032  select=0.5221
+  [hands] epoch  20/35  loss=1.1389  test_acc=0.8305  macro_f1=0.5640  weighted_f1=0.8588  select=0.5640
+  [hands] epoch  30/35  loss=1.1133  test_acc=0.7671  macro_f1=0.5215  weighted_f1=0.8108  select=0.5215
+  [hands] Best selected metric (macro_f1): 0.5987 @ epoch 35  acc=0.8479
+  [hands] Per-class test accuracy:
+    lhandgesture    40/  40  100.00%
+    rhandgesture    42/  45  93.33%
+    bothhandgesture    59/  65  90.77%
+    lhandchest      39/  98  39.80%
+    rhandchest     143/ 145  98.62%
+    pickup         127/ 176  72.16%
+    noaction      2961/3454  85.73%
+
+  [hands] Classification metrics:
+    class          prec  recall     f1   supp   sw_rate   sw# n_clip  perfect
+    ------------------------------------------------------------------------------
+    lhandgesture  0.215   1.000  0.354     40     0.000  0.00      1        1
+    rhandgesture  0.300   0.933  0.454     45     0.023  1.00      1        0
+    bothhandgesture  0.513   0.908  0.656     65     0.016  1.00      1        0
+    lhandchest    0.487   0.398  0.438     98     0.009  0.50      2        1
+    rhandchest    0.769   0.986  0.864    145     0.007  0.33      3        2
+    pickup        0.390   0.722  0.506    176     0.029  2.50      2        0
+    noaction      0.990   0.857  0.919   3454     0.040  1.43     75       47
+    accuracy      0.848
+    macro         0.523   0.829  0.599
+    weighted      0.921   0.848  0.872
+
+  [hands] Label smoothness (per clip):
+    clips evaluated : 85  (mean len 47.3 windows)
+    mean switches   : 1.36
+    mean switch rate: 0.037  (0 = no flipping, 1 = flip every frame)
+    perfectly stable clips: 51 / 85
+  [hands] Confusion matrix → C:\Workspace\ActionLinkPerception\runs\20260610_curated_v1_multihead_w10_cuda\confusion_hands.png
+
+── Branch [seals]  [INHERITED from base model, acc=0.9506]
+
+── Branch [head]  [INHERITED from base model, acc=0.9339]
+
+── Branch [torso]  [INHERITED from base model, acc=0.9731]
+    [build_samples] remapped→noaction: 41687 kept=2222 (action_windows=2222, ratio=1)  dropped: 0
+    [build_samples] remapped→noaction: 3576  dropped: 0
+
+── Branch [poses] keypoints=['nose', 'left_shoulder', 'right_shoulder', 'left_elbow', 'right_elbow', 'left_wrist', 'right_wrist', 'left_hip', 'right_hip', 'left_knee', 'right_knee', 'left_ankle', 'right_ankle']  classes=['tpose', 'tpose_back', 'ypose', 'ypose_back', 'noaction']
+   train=5743  test=4023
+  [poses] training settings: batch=96, lr=0.001, weight_decay=0.0001, label_smoothing=0.05, class_weight_mode=inverse, augment=True
+  [poses] class weights:
+    tpose        1.52
+    tpose_back   3.84
+    ypose        1.11
+    ypose_back   8.64
+    noaction     0.33
+  [poses] select metric: macro_f1
+  [poses] epoch   1/35  loss=0.9267  test_acc=0.8996  macro_f1=0.5665  weighted_f1=0.9269  select=0.5665
+  [poses] epoch  10/35  loss=0.5963  test_acc=0.8941  macro_f1=0.7469  weighted_f1=0.9249  select=0.7469
+  [poses] epoch  20/35  loss=0.5634  test_acc=0.9413  macro_f1=0.7813  weighted_f1=0.9506  select=0.7813
+  [poses] epoch  30/35  loss=0.5584  test_acc=0.9669  macro_f1=0.8223  weighted_f1=0.9674  select=0.8223
+  [poses] Best selected metric (macro_f1): 0.8565 @ epoch 15  acc=0.9804
+  [poses] Per-class test accuracy:
+    tpose           38/ 102  37.25%
+    tpose_back      17/  17  100.00%
+    ypose           83/  89  93.26%
+    ypose_back      16/  16  100.00%
+    noaction      3790/3799  99.76%
+
+  [poses] Classification metrics:
+    class          prec  recall     f1   supp   sw_rate   sw# n_clip  perfect
+    ------------------------------------------------------------------------------
+    tpose         1.000   0.373  0.543    102     0.009  0.67      3        2
+    tpose_back    1.000   1.000  1.000     17     0.000  0.00      2        2
+    ypose         0.664   0.933  0.776     89     0.024  1.00      2        0
+    ypose_back    0.941   1.000  0.970     16     0.000  0.00      2        2
+    noaction      0.991   0.998  0.994   3799     0.001  0.09     76       74
+    accuracy      0.980
+    macro         0.919   0.861  0.856
+    weighted      0.983   0.980  0.978
+
+  [poses] Label smoothness (per clip):
+    clips evaluated : 85  (mean len 47.3 windows)
+    mean switches   : 0.13
+    mean switch rate: 0.002  (0 = no flipping, 1 = flip every frame)
+    perfectly stable clips: 80 / 85
+  [poses] Confusion matrix → C:\Workspace\ActionLinkPerception\runs\20260610_curated_v1_multihead_w10_cuda\confusion_poses.png
+
+Multi-branch model saved → C:\Workspace\ActionLinkPerception\runs\20260610_curated_v1_multihead_w10_cuda\model_curated_v1_multihead_w10_cuda.pth
+  locomotion  acc=0.7298  classes=['walk', 'fastwalk', 'run', 'lowrun', 'lstride', 'lstride_back', 'rstride', 'rstride_back', 'lfwdstride', 'lfwdstride_back', 'rfwdstride', 'rfwdstride_back', 'lbkstep', 'lbkstep_back', 'rbkstep', 'rbkstep_back', 'highknee', 'noaction']
+  jump_squat  acc=0.9354  classes=['jump', 'jump_back', 'squat', 'squat_back', 'noaction']
+  arms        acc=0.9075  classes=['larmchop', 'rarmchop', 'multichop', 'larmlowside', 'rarmlowside', 'noaction']
+  hands       acc=0.8479  classes=['lhandgesture', 'rhandgesture', 'bothhandgesture', 'lhandchest', 'rhandchest', 'pickup', 'noaction']
+  seals       acc=0.9506  classes=['lhandseal', 'rhandseal', 'headseal', 'chestseal', 'bellyseal', 'noaction']
+  head        acc=0.9339  classes=['headdown', 'headup', 'lheadturn', 'rheadturn', 'noaction']
+  torso       acc=0.9731  classes=['llean', 'rlean', 'lshoulderturn', 'rshoulderturn', 'noaction']
+  poses       acc=0.9804  classes=['tpose', 'tpose_back', 'ypose', 'ypose_back', 'noaction']
+Branch config saved → C:\Workspace\ActionLinkPerception\runs\20260610_curated_v1_multihead_w10_cuda\model_curated_v1_multihead_w10_cuda.json

smoothing.json

@@ -0,0 +1,91 @@
+{
+  "algorithm": "moving_average",
+  "window_frames": 5,
+  "back_transition_enabled": true,
+  "back_transition_trigger_threshold": 0.55,
+  "back_transition_boost": 0.2,
+  "back_transition_active_frames": 12,
+  "back_transition_stable_frames": 3,
+  "back_transition_pairs": [
+    {
+      "branch_name": "locomotion",
+      "action": "lstride",
+      "back": "lstride_back",
+      "branch_index": 0,
+      "action_index": 4,
+      "back_index": 5
+    },
+    {
+      "branch_name": "locomotion",
+      "action": "rstride",
+      "back": "rstride_back",
+      "branch_index": 0,
+      "action_index": 6,
+      "back_index": 7
+    },
+    {
+      "branch_name": "locomotion",
+      "action": "lfwdstride",
+      "back": "lfwdstride_back",
+      "branch_index": 0,
+      "action_index": 8,
+      "back_index": 9
+    },
+    {
+      "branch_name": "locomotion",
+      "action": "rfwdstride",
+      "back": "rfwdstride_back",
+      "branch_index": 0,
+      "action_index": 10,
+      "back_index": 11
+    },
+    {
+      "branch_name": "locomotion",
+      "action": "lbkstep",
+      "back": "lbkstep_back",
+      "branch_index": 0,
+      "action_index": 12,
+      "back_index": 13
+    },
+    {
+      "branch_name": "locomotion",
+      "action": "rbkstep",
+      "back": "rbkstep_back",
+      "branch_index": 0,
+      "action_index": 14,
+      "back_index": 15
+    },
+    {
+      "branch_name": "jump_squat",
+      "action": "jump",
+      "back": "jump_back",
+      "branch_index": 1,
+      "action_index": 0,
+      "back_index": 1
+    },
+    {
+      "branch_name": "jump_squat",
+      "action": "squat",
+      "back": "squat_back",
+      "branch_index": 1,
+      "action_index": 2,
+      "back_index": 3
+    },
+    {
+      "branch_name": "poses",
+      "action": "tpose",
+      "back": "tpose_back",
+      "branch_index": 7,
+      "action_index": 0,
+      "back_index": 1
+    },
+    {
+      "branch_name": "poses",
+      "action": "ypose",
+      "back": "ypose_back",
+      "branch_index": 7,
+      "action_index": 2,
+      "back_index": 3
+    }
+  ]
+}