dtourolle/scene-actor-extraction
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: deploy from 4b55579

Browse Source
This commit is contained in:
dtourolle
2026-07-19 22:28:14 +02:00
parent 252625330f
commit 36f75ba199
29 changed files with 1024 additions and 260 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lvface-deep-dive/index.html
+227 -70
View File
@@ -10,11 +10,13 @@
<link rel="canonical" href="https://pages.tourolle.paris/dtourolle/scene-actor-extraction/lvface-deep-dive/">
<link rel="prev" href="../pose-expansion/">
<link rel="next" href="../rep4-optimizer-results/">
<link rel="next" href="../model-bakeoff/">
@@ -51,6 +53,8 @@
<link rel="stylesheet" href="../stylesheets/extra.css">
<script>__md_scope=new URL("..",location),__md_hash=e=>[...e].reduce(((e,_)=>(e<<5)-e+_.charCodeAt(0)),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
@@ -67,7 +71,7 @@
<body dir="ltr" data-md-color-scheme="slate" data-md-color-primary="indigo" data-md-color-accent="indigo">
<body dir="ltr" data-md-color-scheme="slate" data-md-color-primary="black" data-md-color-accent="amber">
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
@@ -123,7 +127,21 @@
<input class="md-option" data-md-color-media="" data-md-color-scheme="slate" data-md-color-primary="indigo" data-md-color-accent="indigo" aria-hidden="true" type="radio" name="__palette" id="__palette_0">
<input class="md-option" data-md-color-media="(prefers-color-scheme: dark)" data-md-color-scheme="slate" data-md-color-primary="black" data-md-color-accent="amber" aria-label="Switch to light mode" type="radio" name="__palette" id="__palette_0">
<label class="md-header__button md-icon" title="Switch to light mode" for="__palette_1" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 7a5 5 0 0 1 5 5 5 5 0 0 1-5 5 5 5 0 0 1-5-5 5 5 0 0 1 5-5m0 2a3 3 0 0 0-3 3 3 3 0 0 0 3 3 3 3 0 0 0 3-3 3 3 0 0 0-3-3m0-7 2.39 3.42C13.65 5.15 12.84 5 12 5s-1.65.15-2.39.42zM3.34 7l4.16-.35A7.2 7.2 0 0 0 5.94 8.5c-.44.74-.69 1.5-.83 2.29zm.02 10 1.76-3.77a7.131 7.131 0 0 0 2.38 4.14zM20.65 7l-1.77 3.79a7.02 7.02 0 0 0-2.38-4.15zm-.01 10-4.14.36c.59-.51 1.12-1.14 1.54-1.86.42-.73.69-1.5.83-2.29zM12 22l-2.41-3.44c.74.27 1.55.44 2.41.44.82 0 1.63-.17 2.37-.44z"/></svg>
</label>
<input class="md-option" data-md-color-media="(prefers-color-scheme: light)" data-md-color-scheme="default" data-md-color-primary="black" data-md-color-accent="indigo" aria-label="Switch to dark mode" type="radio" name="__palette" id="__palette_1">
<label class="md-header__button md-icon" title="Switch to dark mode" for="__palette_0" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="m17.75 4.09-2.53 1.94.91 3.06-2.63-1.81-2.63 1.81.91-3.06-2.53-1.94L12.44 4l1.06-3 1.06 3zm3.5 6.91-1.64 1.25.59 1.98-1.7-1.17-1.7 1.17.59-1.98L15.75 11l2.06-.05L18.5 9l.69 1.95zm-2.28 4.95c.83-.08 1.72 1.1 1.19 1.85-.32.45-.66.87-1.08 1.27C15.17 23 8.84 23 4.94 19.07c-3.91-3.9-3.91-10.24 0-14.14.4-.4.82-.76 1.27-1.08.75-.53 1.93.36 1.85 1.19-.27 2.86.69 5.83 2.89 8.02a9.96 9.96 0 0 0 8.02 2.89m-1.64 2.02a12.08 12.08 0 0 1-7.8-3.47c-2.17-2.19-3.33-5-3.49-7.82-2.81 3.14-2.7 7.96.31 10.98 3.02 3.01 7.84 3.12 10.98.31"/></svg>
</label>
</form>
@@ -248,13 +266,13 @@
<li class="md-tabs__item">
<a href="../rep4-optimizer-results/" class="md-tabs__link">
<a href="../model-bakeoff/" class="md-tabs__link">
Rep4 Bake-off & Re-tune (full log)
Model Bake-off & Re-tune (full log)
</a>
</li>
@@ -578,6 +596,17 @@
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#what-good-looks-like" class="md-nav__link">
<span class="md-ellipsis">
What good looks like
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#training-vs-held-out-the-generalization-gap" class="md-nav__link">
<span class="md-ellipsis">
@@ -590,10 +619,10 @@
</li>
<li class="md-nav__item">
<a href="#failure-mode-1-frozen-bbox-ghost-tracks" class="md-nav__link">
<a href="#mechanism-1-extinction-bridging-usually-right-wrong-at-hard-cuts" class="md-nav__link">
<span class="md-ellipsis">
Failure mode 1: frozen-bbox "ghost tracks"
Mechanism 1: extinction bridging — usually right, wrong at hard cuts
</span>
</a>
@@ -601,10 +630,10 @@
</li>
<li class="md-nav__item">
<a href="#failure-mode-2-a-genuine-misid-for-contrast" class="md-nav__link">
<a href="#mechanism-2-the-face-vs-presence-ceiling" class="md-nav__link">
<span class="md-ellipsis">
Failure mode 2: a genuine misID (for contrast)
Mechanism 2: the face-vs-presence ceiling
</span>
</a>
@@ -656,14 +685,14 @@
<li class="md-nav__item">
<a href="../rep4-optimizer-results/" class="md-nav__link">
<a href="../model-bakeoff/" class="md-nav__link">
<span class="md-ellipsis">
Rep4 Bake-off & Re-tune (full log)
Model Bake-off & Re-tune (full log)
@@ -756,6 +785,17 @@
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#what-good-looks-like" class="md-nav__link">
<span class="md-ellipsis">
What good looks like
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#training-vs-held-out-the-generalization-gap" class="md-nav__link">
<span class="md-ellipsis">
@@ -768,10 +808,10 @@
</li>
<li class="md-nav__item">
<a href="#failure-mode-1-frozen-bbox-ghost-tracks" class="md-nav__link">
<a href="#mechanism-1-extinction-bridging-usually-right-wrong-at-hard-cuts" class="md-nav__link">
<span class="md-ellipsis">
Failure mode 1: frozen-bbox "ghost tracks"
Mechanism 1: extinction bridging — usually right, wrong at hard cuts
</span>
</a>
@@ -779,10 +819,10 @@
</li>
<li class="md-nav__item">
<a href="#failure-mode-2-a-genuine-misid-for-contrast" class="md-nav__link">
<a href="#mechanism-2-the-face-vs-presence-ceiling" class="md-nav__link">
<span class="md-ellipsis">
Failure mode 2: a genuine misID (for contrast)
Mechanism 2: the face-vs-presence ceiling
</span>
</a>
@@ -829,14 +869,44 @@
<h1 id="deep-dive-lvface-b-glint360k">Deep dive: LVFace-B Glint360K<a class="headerlink" href="#deep-dive-lvface-b-glint360k" title="Permanent link">&para;</a></h1>
<p>LVFace won the model bake-off (see <code>best-model.md</code>) and is the shipped default
embedder. This page is the honest accounting of how it actually performs —
including where it's wrong, and one case where the ground truth itself is
wrong and LVFace is right.</p>
<p>LVFace won the model bake-off (see <a href="../best-model/">Which model is best?</a>) and is
the shipped default embedder. This page is the honest accounting of how it
actually performs — what a good second looks like, where the errors actually
come from, and two cases where the ground truth itself is wrong and LVFace is
right.</p>
<div class="admonition note">
<p class="admonition-title">How to read the frames on this page</p>
<p>The top is the film frame, with a box and name on every face the pipeline
identified. The bottom panels are the per-second verdict against X-Ray:
<strong>Onscreen</strong> lists faces named in the frame, <strong>Offscreen</strong> lists cast
X-Ray marks present in the scene without a visible face — presence
carried by the tracker's windows, not by a detection. Colors are the
score: <span style="color:#0ca30c"><strong>green</strong></span> = correct (TPI),
<span style="color:#eb6834"><strong>orange</strong></span> = wrong (FPI),
<span style="color:#3987e5"><strong>blue</strong></span> = missed (FN).</p>
</div>
<h2 id="what-good-looks-like">What good looks like<a class="headerlink" href="#what-good-looks-like" title="Permanent link">&para;</a></h2>
<p><img alt="Wedding couple correctly identified, Downton Abbey: A New Era" src="../assets/images/downton_wedding_couple.jpg" /></p>
<p>Six faces on screen, all six named correctly — including Penelope Wilton at the
edge of the pews and a half-occluded Michelle Dockery — while thirteen more
cast members X-Ray marks present in the scene are correctly carried as
"Offscreen" by their presence windows. One miss in the whole frame: Maggie
Smith (blue). Score for this second: 0.86.</p>
<p><img alt="19 of 20 correct in the funeral crowd" src="../assets/images/downton_funeral_19of20.jpg" /></p>
<p>The same film's funeral gathering: mourning dress, hats, half the faces turned.
<strong>Nineteen of the twenty cast X-Ray lists for this scene are scored correctly</strong>
— seven named on screen at up to 100% confidence, twelve more correctly held
as present off-screen.</p>
<p>And the pipeline doesn't need the face to be <em>real</em>:</p>
<p><img alt="Herbie Hancock identified on an in-fiction video call" src="../assets/images/valerian_screen_call.jpg" /></p>
<p>That's Herbie Hancock at 98% — as a face on a <em>screen inside the movie</em>, over a
sci-fi HUD overlay, during a video call in Valerian. A face is a face, whether
it's in the room or on the bridge's comms display.</p>
<h2 id="training-vs-held-out-the-generalization-gap">Training vs. held-out: the generalization gap<a class="headerlink" href="#training-vs-held-out-the-generalization-gap" title="Permanent link">&para;</a></h2>
<p>The shipped config (<code>prob_threshold=0.754, anneal_sec=35.54,
extinction_sec=57.43, expand_gallery=true</code>) was tuned against 4 films. Scored
against the 5 films the optimizer never saw:</p>
<p><img alt="Held-out per-film F1 vs. the training-set fit" src="../assets/images/holdout_f1_by_film.png" /></p>
<table>
<thead>
<tr>
@@ -915,61 +985,108 @@ against the 5 films the optimizer never saw:</p>
</table>
<p><strong>67.4% held-out vs. 75.3% on training</strong> — an ~8pp drop, and a <strong>37pp spread
between the best and worst held-out film</strong>. The config does not generalize
uniformly; two films are outright failure cases, for two different reasons.</p>
<h2 id="failure-mode-1-frozen-bbox-ghost-tracks">Failure mode 1: frozen-bbox "ghost tracks"<a class="headerlink" href="#failure-mode-1-frozen-bbox-ghost-tracks" title="Permanent link">&para;</a></h2>
<p>Both Many Saints of Newark (974 misIDs) and Downton Abbey (FN=80084, the worst
recall of the five) trace to the same root cause, verified directly against
the raw per-frame stream and the HDF5 dump's own detection counts — not
inferred from the score alone.</p>
<p><img alt="Frozen ghost boxes over background, The Many Saints of Newark" src="../assets/images/many_saints_ghost_fpi.jpg" /></p>
<p>At this second, three of the four labeled boxes ("Jon Bernthal", "Joey Diaz",
"Billy Magnussen") sit over empty background — a blurred wall, hanging
plates — with no face in them. The real face in frame carries a second,
colliding label from another frozen box.</p>
<p><img alt="15 ghost boxes over a blank title card, Downton Abbey: A New Era" src="../assets/images/downton_abbey_ghost_fpi.jpg" /></p>
<p>This is the starkest case: <strong>15 actors named, all wrong, over a completely
blank closing title card.</strong> Confirmed against the dump directly: <code>face_count</code>
is 0 from this point onward (no detector output at all), yet the same 15
identities keep appearing with the <em>exact same bounding box, unchanged to the
pixel</em>, for 57+ consecutive seconds.</p>
<p>This is <code>SceneTrackerFunc::active_[actor_idx].last_bbox</code>
(<code>src/nodes/scene_tracker_node.hpp</code>) being re-emitted unchanged — the
extinction state machine working exactly as coded, not a bug. The film cuts
from a packed group shot straight into 40+ seconds of blank titles/credits,
and <code>extinction_sec=57.4</code> is comfortably long enough to bridge that entire gap
without expiring, so the tracker faithfully reports "last known position" for
a cast that is no longer on screen at all. <code>extinction_sec</code> was tuned toward
long windows specifically because they bridge real gaps (occlusion, a turned
face) in most training footage — this is the cost side of that trade,
surfacing only when a film has a long enough faceless stretch to expose it.</p>
<h2 id="failure-mode-2-a-genuine-misid-for-contrast">Failure mode 2: a genuine misID (for contrast)<a class="headerlink" href="#failure-mode-2-a-genuine-misid-for-contrast" title="Permanent link">&para;</a></h2>
<p>Not every held-out failure is a ghost. This is a real face, correctly
detected, confidently misidentified:</p>
<p><em>(same many_saints_ghost_fpi.jpg frame above also shows Leslie Odom Jr.'s box
carrying a second, colliding "Michael Gandolfini" label — two real tracks'
frozen positions happening to overlap, not a detection error.)</em></p>
uniformly, and the spread traces to two mechanisms, both visible frame by
frame below.</p>
<h2 id="mechanism-1-extinction-bridging-usually-right-wrong-at-hard-cuts">Mechanism 1: extinction bridging — usually right, wrong at hard cuts<a class="headerlink" href="#mechanism-1-extinction-bridging-usually-right-wrong-at-hard-cuts" title="Permanent link">&para;</a></h2>
<p>The extinction window keeps an identity alive through seconds where no face is
detectable. <strong>Most of the time this is exactly what you want</strong>, and it's where
a lot of the TPI count comes from:</p>
<p><img alt="Two faces on screen, six more correctly bridged" src="../assets/images/lovelace_polygraph_bridged.jpg" /></p>
<p>Lovelace's polygraph scene: only Eric Roberts and Amanda Seyfried have visible
faces, but X-Ray lists eight cast present — and all eight score green, the
other six correctly carried by presence windows through a scene where the
camera never shows them. A perfect second, and the extinction/anneal machinery
is <em>why</em>.</p>
<p>The same mechanism has a failure case: a hard cut into long faceless footage.
Both Many Saints of Newark (974 misIDs) and Downton Abbey (FN=80084, the worst
recall of the five) are dominated by it — verified directly against the raw
per-frame stream and the HDF5 dump's own detection counts, not inferred from
the score alone. <strong>This is not a malfunction</strong>: the tracker is doing exactly
what its window is for; the footage just stops cooperating. In the debug
overlay (which draws a bridged identity's last-known bbox, unlike the shipped
output, which emits presence windows and no boxes at all) the bridged state is
visible spatially:</p>
<p><img alt="Debug overlay: bridged identities drawn at their last-known positions" src="../assets/images/many_saints_ghost_fpi.jpg" />
<em>Debug-overlay rendering (<code>dump_error_frames.py --raw</code>): "Jon Bernthal", "Joey
Diaz" and "Billy Magnussen" are extinction-bridged identities from the previous
shot, drawn frozen over the wall and the hanging plates. Frame
<code>many_saints/fpi/fpi_t03543.jpg</code>, <code>montage-frames</code> artifact package.</em></p>
<p>The cost is measurable, not just visible. Downton Abbey's hard cut into its
closing credits, plotting the dump's own per-second <code>face_count</code> (detector
output, independent of the tracker) against what the tracker reports:</p>
<p><img alt="Detector vs. tracker through Downton Abbey's cut to credits" src="../assets/images/downton_ghost_timeline.png" /></p>
<p>From the cut onward the detector sees <strong>zero faces for nearly a minute</strong> — and
the tracker keeps reporting the last shot's 15 identities the whole time
(verified for Hugh Bonneville: bbox <code>(1743.2, 0.0, 171.3, 317.8)</code>, unchanged to
the pixel, at every sampled second for 57+ seconds). The staircase at the right
edge is the extinction window expiring actor by actor. That plateau is
<code>SceneTrackerFunc::active_[actor_idx].last_bbox</code>
(<a href="https://gitea.tourolle.paris/dtourolle/scene-actor-extraction/raw/commit/4b5557974bef8783bacc375c0869e8f589d1b0a3/src/nodes/scene_tracker_node.hpp"><code>src/nodes/scene_tracker_node.hpp</code></a>)
re-emitted as designed: <code>extinction_sec=57.4</code> was tuned long because bridging
wins on most footage (see the polygraph frame above) — the training films just
never contained a faceless stretch long enough to show the cost side, and the
held-out set did.</p>
<p>The same track-continuation machinery has one milder spatial artifact, worth
knowing when reading these frames:</p>
<p><img alt="Two labels on one face after a shot/reverse-shot cut" src="../assets/images/cafe_society_rapid_cut.jpg" />
<em>Café Society (a training film), a shot/reverse-shot dialog: that is Steve
Carell wearing both his own label and Jesse Eisenberg's.</em></p>
<p>At a rapid cut, the previous shot's track can linger for a beat at nearly the
same screen position the new face occupies — here Jesse Eisenberg's box from
the counter-shot lands on Steve Carell. Note what the score panel says,
though: both actors are green, because both <em>are</em> present in this dialog
scene per X-Ray. The spatial label is briefly wrong; the per-second presence
claim — the thing the pipeline actually ships — is right. It's the same trade
as the extinction window: track continuation smooths over cuts, and 1 fps
sampling occasionally catches the seam.</p>
<h2 id="mechanism-2-the-face-vs-presence-ceiling">Mechanism 2: the face-vs-presence ceiling<a class="headerlink" href="#mechanism-2-the-face-vs-presence-ceiling" title="Permanent link">&para;</a></h2>
<p>Downton Abbey's recall didn't collapse because faces were misread — it
collapsed because for most of its 80084 FN-seconds there was <strong>no face to
read</strong>:</p>
<p><img alt="22 cast credited, nobody facing the camera" src="../assets/images/downton_crew_fn.jpg" /></p>
<p>A newsreel crew hauls equipment through the hall: X-Ray credits 22 cast as
present in this scene; not one face looks at the camera. Eight are still
scored green (windows bridging from adjacent shots) — the other fourteen are
blue FNs that no face-recognition pipeline could ever recover. X-Ray encodes
<em>scene membership</em>; the pipeline measures <em>on-screen faces</em>. In ensemble films
those two definitions diverge massively, and that gap — not identification
error — is most of what the FN column counts.</p>
<p><img alt="Presence without a detectable face, The Many Saints of Newark" src="../assets/images/many_saints_outofcast_fpi.jpg" /></p>
<p>Same ceiling from the other side: Michela De Rossi in frame but turned away,
five cast correctly bridged as offscreen (green), four blue FNs — and one
orange we'll come back to below.</p>
<h2 id="where-lvface-beat-x-ray">Where LVFace beat X-Ray<a class="headerlink" href="#where-lvface-beat-x-ray" title="Permanent link">&para;</a></h2>
<p>Not every "misID" is actually wrong. <code>second_score.py</code> counts a name as a true
out-of-cast misID whenever the named actor isn't in X-Ray's credited cast list
for the film at all — but X-Ray's cast list is itself incomplete.</p>
<p>Not every orange in these frames is actually wrong.
<a href="https://gitea.tourolle.paris/dtourolle/scene-actor-extraction/raw/commit/4b5557974bef8783bacc375c0869e8f589d1b0a3/scripts/optimizer/second_score.py"><code>scripts/optimizer/second_score.py</code></a>
scores strictly against X-Ray — but X-Ray itself has holes, and the pipeline
found two kinds.</p>
<p><img alt="LVFace correctly identifies Germar Terrell Gardner, uncredited by X-Ray" src="../assets/images/germar_beats_xray.jpg" /></p>
<p>Germar Terrell Gardner — a real, clean, high-confidence detection — is counted
as a misID here because he doesn't appear in X-Ray's <code>people.csv</code> for The Many
Saints of Newark at all. But Jellyfin's independent cast metadata <em>does</em> credit
him for this exact film (cross-checked via <code>experiments/manifests/
jellyfin_casts.json</code>, a completely separate data source from X-Ray). This
isn't a lookalike error or a gallery mixup — it's the pipeline correctly
recognising a real cast member that one ground-truth source happened to omit.</p>
as an out-of-cast misID because he doesn't appear in X-Ray's <code>people.csv</code> for
The Many Saints of Newark at all. But Jellyfin's independent cast metadata
<em>does</em> credit him for this exact film (cross-checked via
<code>experiments/manifests/jellyfin_casts.json</code> from the <code>experiment-data</code> artifact
package, a completely separate data source from X-Ray). That's also him in
orange in the frame above — every one of those "errors" is the pipeline being
right about a person X-Ray forgot.</p>
<p><img alt="Robert Patrick, clearly on screen, scored wrong by a ground-truth gap" src="../assets/images/lovelace_robert_patrick_fpi.jpg" /></p>
<p>And it isn't only uncredited bit-parts. That is <strong>Robert Patrick</strong> — top-billed
in Lovelace, unmistakably on screen, reading his newspaper, identified at
100% — scored orange because X-Ray's people-in-scene list for <em>this scene</em>
doesn't include him. The identification is flawless; the ground truth missed
an actor sitting in the middle of the frame.</p>
<p>This doesn't mean every flagged misID is secretly correct — Many Saints'
974-count total is still overwhelmingly the frozen-bbox failure mode above,
not uncredited-but-real cameos. But it's a reminder that the X-Ray corpus is a
convenient, large-scale ground truth, not a perfect one, and the "misID" number
in any of these tables has some irreducible noise floor from ground-truth gaps
in the other direction too.</p>
974-count total is still overwhelmingly extinction bridging at cuts, not
uncredited cameos. But the X-Ray corpus is a convenient, large-scale ground
truth, not a perfect one, and the misID/FPI numbers in these tables carry an
irreducible noise floor from ground-truth gaps in both directions.</p>
<h2 id="summary">Summary<a class="headerlink" href="#summary" title="Permanent link">&para;</a></h2>
<p>LVFace is the right default: it wins the model comparison outright, and its
failures are traceable, understood, and mostly attributable to one tunable
knob (<code>extinction_sec</code>) rather than the embedder itself. The held-out
<p>LVFace is the right default: it wins the model comparison outright, it names
19 of 20 correctly across a hat-heavy funeral crowd, and it recognises a face
on a screen inside the movie. Its error budget decomposes into two understood
mechanisms — extinction bridging at hard cuts (a tunable trade, not a bug) and
the face-vs-presence ceiling baked into X-Ray's semantics — plus a nonzero
slice where the pipeline is right and the ground truth is wrong. The held-out
generalization gap (75.3% → 67.4%) is real and should be treated as the honest
expected performance, not the training-set number.</p>
@@ -1002,6 +1119,46 @@ expected performance, not the training-set number.</p>
<footer class="md-footer">
<nav class="md-footer__inner md-grid" aria-label="Footer" >
<a href="../pose-expansion/" class="md-footer__link md-footer__link--prev" aria-label="Previous: Pose Expansion">
<div class="md-footer__button md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11z"/></svg>
</div>
<div class="md-footer__title">
<span class="md-footer__direction">
Previous
</span>
<div class="md-ellipsis">
Pose Expansion
</div>
</div>
</a>
<a href="../model-bakeoff/" class="md-footer__link md-footer__link--next" aria-label="Next: Model Bake-off &amp; Re-tune (full log)">
<div class="md-footer__title">
<span class="md-footer__direction">
Next
</span>
<div class="md-ellipsis">
Model Bake-off & Re-tune (full log)
</div>
</div>
<div class="md-footer__button md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M4 11v2h12l-5.5 5.5 1.42 1.42L19.84 12l-7.92-7.92L10.5 5.5 16 11z"/></svg>
</div>
</a>
</nav>
<div class="md-footer-meta md-typeset">
<div class="md-footer-meta__inner md-grid">
<div class="md-copyright">
@@ -1027,7 +1184,7 @@ expected performance, not the training-set number.</p>
<script id="__config" type="application/json">{"annotate": null, "base": "..", "features": ["navigation.tabs", "navigation.sections", "navigation.top", "content.code.copy", "content.code.annotate"], "search": "../assets/javascripts/workers/search.2c215733.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
<script id="__config" type="application/json">{"annotate": null, "base": "..", "features": ["navigation.tabs", "navigation.sections", "navigation.top", "navigation.footer", "content.code.copy", "content.code.annotate"], "search": "../assets/javascripts/workers/search.2c215733.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
<script src="../assets/javascripts/bundle.d7400e89.min.js"></script>