Mirrors/photoprism
1
0
Fork 0
mirror of https://github.com/photoprism/photoprism.git synced 2026-01-23 02:24:24 +00:00
Code Issues Projects Releases Wiki Activity
photoprism/internal/ai/nsfw
History
Exact
Michael Mayer 28eb11d468 TensorFlow: Trigger explicit GC to free C-allocated tensor memory #5394 
Signed-off-by: Michael Mayer <michael@photoprism.app>
2025-12-23 12:06:26 +01:00
..
testdata Backend: Rename /internal/tensorflow to /internal/ai 2024-07-02 08:08:14 +02:00
.gitignore Backend: Rename /internal/tensorflow to /internal/ai 2024-07-02 08:08:14 +02:00
model.go TensorFlow: Trigger explicit GC to free C-allocated tensor memory #5394 2025-12-23 12:06:26 +01:00
nsfw.go CI: Apply Go more linter recommendations to "ai/nsfw" package #5330 2025-11-22 11:33:28 +01:00
nsfw_test.go CI: Apply Go more linter recommendations to "ai/nsfw" package #5330 2025-11-22 11:33:28 +01:00
README.md TensorFlow: Trigger explicit GC to free C-allocated tensor memory #5394 2025-12-23 12:06:26 +01:00

README.md

PhotoPrism — NSFW Package

Last Updated: December 23, 2025

Overview

internal/ai/nsfw runs the built-in TensorFlow NSFW classifier to score images for drawing, hentai, neutral, porn, and sexy content. It is used during indexing and metadata workflows when the NSFW model is enabled.

How It Works

  • Model Loading — Loads the NSFW SavedModel from assets/models/ and resolves input/output ops (inferred if missing).
  • Input Preparation — JPEG images are decoded and transformed to the configured input resolution.
  • Inference & Output — Produces five class probabilities mapped into a Result struct for downstream thresholds and UI badges.

Memory & Performance

TensorFlow tensors allocate C memory and are freed by Go GC finalizers. To keep RSS bounded during long runs, PhotoPrism periodically triggers garbage collection to return freed tensor memory to the OS. Tune with:

  • PHOTOPRISM_TF_GC_EVERY (default 200, 0 disables).
    Lower values reduce peak RSS but increase GC overhead and can slow indexing.

Troubleshooting Tips

  • Model fails to load: Verify saved_model.pb and variables/ exist under the model path.
  • Unexpected scores: Confirm the input resolution matches the model and that logits are handled correctly.
  • High memory usage: Adjust PHOTOPRISM_TF_GC_EVERY or reduce concurrent indexing load.

Related Docs