Score photos once, weigh them per storefront

A marketplace asks sellers for a good main photo. "Is this a good photo?" hides what makes it good, and different storefronts care about different things. Valen scores each photo once on three dimensions; code combines them with weights each storefront can change without another model call.

Studio	Kitchen counter	Dim	Cropped

How it works

Three score questions, each with three levels described as situations a person could recognize:

Dimension	Levels
lighting	poor · fair · good
background	cluttered · plain · studio
framing	cut off · loose · centered

A score runs from 0 to 2 over three levels; code divides by 2 so each dimension is on 0–1, then takes a weighted sum per storefront:

Profile	lighting	background	framing
marketplace	0.3	0.2	0.5
premium_shop	0.3	0.5	0.2

Run it

Download the bundle once. The recorded answers in caches/composite_scoring.json let the script run without an API key; --replay off calls the free hosted API instead.

Bash

curl -fLO https://valen-team.github.io/cookbook/valen-cookbook.zip
python -m zipfile -e valen-cookbook.zip .
cd valen-cookbook && python -m pip install -r requirements.txt
python composite_scoring.py
python composite_scoring.py --replay off --base-url https://api.valen-team.workers.dev/v1

Code

composite_scoring.py

"""Score listing photos once per dimension, then let code weigh the dimensions for each storefront. Apache-2.0."""
import json

from common import HERE, client, emit, image_bytes, image_input, parser, request

DIMENSIONS = {
    "lighting": ("How well lit is the mug?", [
        ("poor", "Dark, heavily shadowed or color-cast; the glaze is hard to see"),
        ("fair", "Ordinary indoor light; the glaze is visible but flat"),
        ("good", "Bright, even light that shows the glaze clearly")]),
    "background": ("How clean is the background behind the mug?", [
        ("cluttered", "Other household objects compete with the mug"),
        ("plain", "A table or cloth with nothing else in view"),
        ("studio", "A seamless studio backdrop")]),
    "framing": ("How much of the mug is in the frame?", [
        ("cut_off", "Part of the mug, such as the handle, is outside the frame"),
        ("loose", "The whole mug is visible but small or off-center"),
        ("centered", "The whole mug is centered and fills the frame")]),
}
# Weights are business choices in code; changing them never needs another model call.
PROFILES = {"marketplace": {"lighting": 0.3, "background": 0.2, "framing": 0.5},
            "premium_shop": {"lighting": 0.3, "background": 0.5, "framing": 0.2}}


def score(predict, photo):
    questions = [{"name": name, "type": "score", "instructions": text,
                  "levels": [{"label": label, "description": description} for label, description in levels]}
                 for name, (text, levels) in DIMENSIONS.items()]
    answers = request(predict, image_input(image_bytes(HERE / "media" / photo)), questions)
    # Scores run 0-2 over three levels; divide by 2 so every dimension is on 0-1.
    return {"photo": photo, **{name: answers[name]["score"] / 2 for name in DIMENSIONS}}


def rank(scores, weights):
    total = lambda s: round(sum(weights[name] * s[name] for name in DIMENSIONS), 3)
    return sorted(({"photo": s["photo"], "score": total(s)} for s in scores), key=lambda x: x["score"], reverse=True)


def main():
    args = parser(__doc__).parse_args()
    photos = json.loads((HERE / "composite_scoring_data.json").read_text())
    with client(args) as predict:
        scores = [score(predict, photo) for photo in photos]
    emit({"dimensions": scores, "rankings": {name: rank(scores, w) for name, w in PROFILES.items()}}, args)


if __name__ == "__main__":
    main()

Output

The kitchen-counter photo is well lit and fully framed, so the marketplace ranks it second; the premium shop weighs the clutter and ranks it last.

Recorded output

{
  "dimensions": [
    {
      "photo": "mug-studio.jpg",
      "lighting": 0.9991636368077078,
      "background": 0.9938775610787292,
      "framing": 0.9752801720575722
    },
    {
      "photo": "mug-counter.jpg",
      "lighting": 0.9860608196005157,
      "background": 0.006156532209375251,
      "framing": 0.9074895660257324
    },
    {
      "photo": "mug-dim.jpg",
      "lighting": 0.17881670806358135,
      "background": 0.641231147103601,
      "framing": 0.8176063590643421
    },
    {
      "photo": "mug-cropped.jpg",
      "lighting": 0.9932250863251958,
      "background": 0.5433575647609814,
      "framing": 0.29707197970072985
    }
  ],
  "rankings": {
    "marketplace": [
      {
        "photo": "mug-studio.jpg",
        "score": 0.986
      },
      {
        "photo": "mug-counter.jpg",
        "score": 0.751
      },
      {
        "photo": "mug-dim.jpg",
        "score": 0.591
      },
      {
        "photo": "mug-cropped.jpg",
        "score": 0.555
      }
    ],
    "premium_shop": [
      {
        "photo": "mug-studio.jpg",
        "score": 0.992
      },
      {
        "photo": "mug-cropped.jpg",
        "score": 0.629
      },
      {
        "photo": "mug-dim.jpg",
        "score": 0.538
      },
      {
        "photo": "mug-counter.jpg",
        "score": 0.48
      }
    ]
  }
}

Make it yours

• Store the per-dimension scores, not only the total. New weights, filters or a learned model can use them later without calling Valen again.
• The photos are generated for this recipe.