Cotton Disease AI Settings

Settings

Model provenance and runtime configuration, read from the environment at boot.

Model
Filecotton_mnv3s_fp16.tflite
Version930c20fa33fe
Size 2.10 MB · 2.000 MiB
Formattflite-fp16
Runtimeai_edge_litert
Input224 × 224 × 3 · float32
Input range 0–255 raw; the model rescales internally
Feature map 7 × 7 × 576
Class mapping
0Aphids1Armyworm2Bacterial Blight3Healthy4Powdery Mildew5Target Spot
Verified yes
Methodprobe_labels.py: sorted train dirs + empirical modal argmax over 360 images, agreed
Recorded2026-09-12
Verified against the dataset Confirmed two ways by tools/probe_labels.py — sorted class directories, and the modal prediction over 60 images per class. Both agreed on all six indices.
Runtime
Grad-CAM available · analytic (closed-form, no autodiff)
Max upload10 MB
Acceptedimage/jpeg, image/png, image/webp
Interpreter threads1
Low-confidence cutoff 50%
Confidence precision 1 decimal · FP16 noise ≈ 0.6%
App version0.1.0
Privacy

Images are classified in-process and are not sent anywhere — no external service, no network call at inference time. Nothing is written to disk in this phase. When persisted history arrives in Phase 6, uploads are re-encoded through Pillow on save, which strips EXIF metadata including GPS coordinates from phone photos.