Add v3mix weights and the negative result that came with them

README.md

@@ -14,12 +14,17 @@ tags:
 Reads an analog clock and returns the time. Finds the dial first, then reads it.
 11.5 MB of weights.
 
-> **It does not work on real photographs.** On 1,728 real photos it is off by
-> 155.9 minutes on average. Guessing at random is off by 180. On the synthetic
-> renders it trained on, it is off by 4.8 minutes. I am publishing it because
+> **It does not work on real photographs.** Off by 155.9 minutes on average
+> across 1,728 of them. Guessing at random is off by 180. On the synthetic
+> renders it trained on it is off by 4.8 minutes. I am publishing it because
 > that gap is the only interesting thing here.
 
-Version 263701, trained on synth v2.
+Two weight sets are here. `stage2_best.pt` was trained on renders alone.
+`v3mix_stage2.pt` was trained on rougher renders plus 1,528 real photographs,
+to see whether real data closed the gap. It did not, and both are published
+rather than only the flattering one.
+
+Version 263701.
 
 ## The metric
 
@@ -71,6 +76,32 @@ Do not quote these. The renderer that made the labels also made the pixels, so
 the model is being marked by its own teacher. They are here for one reason: 4.8
 minutes on renders against 156 on photographs is the whole story.
 
+## Does training on real photographs help? No.
+
+`v3mix_stage2.pt` was trained on a rougher synthetic corpus (sensor noise up to
+sigma 42, JPEG down to q25, occlusion, far wider hand geometry) plus 1,528 real
+photographs, holding out 200 for evaluation. 106 of those 200 have labels I
+checked by hand against the image; the rest are third-party and unverified.
+
+On the 106 labels I actually verified:
+
+| weights | trained on | MAE | within 5 min |
+|---|---|---|---|
+| stage2_best.pt | renders only | 148.5 min | 10.4% |
+| v3mix_stage2.pt | rougher renders + 1,528 real photos | 151.9 min | 12.3% |
+| random guessing | | 180 min | |
+
+Adding real photographs moved it from 148.5 to 151.9, which is to say nowhere.
+
+On the full 200-photo held-out set v3mix scores MAE 120.6 with 24.5% within
+five minutes, which looks better and mostly is not: that set contains the
+pre-cropped clock faces, which are the easy ones. Its own verified subset scores
+151.9. Composition, not skill.
+
+Its synthetic score is 35.0 minutes against the older model's 4.8, because the
+renders it trained on are much harder. That is the intended direction and it
+still did not transfer.
+
 ## Where it goes wrong
 
 Of the 1,421 predictions off by more than half an hour, 720 would improve if you