Shaq2/chashibhai-corn-disease-cls

ChashiBhAI Corn Disease Classifier

Author	Shaq2 (Shakil Ahmed)
Crop	corn (ভুট্টা)
Task	Image classification (leaf disease)
Architecture	YOLO26-cls → TFLite FP16
Input	[1, 640, 640, 3] NHWC RGB /255.0
Output	[1, 4] softmax probabilities (nms: false)
Status	production-demo
App	ChashiBhAI (Expo / React Native, on-device diagnosis)
Code	GitHub
Collection	ChashiBhAI on-device classifiers

Disease ID in ChashiBhAI always runs on-device. Gemini / KrishokChat generate advisory text only and never see the photo.

Files

File	Role
model.tflite	On-device graph used by the Android app (~10.93 MB)
labels.json	Canonical class names and preprocess contract
best.pt	Ultralytics source weights (export parent)

Classes (4)

Label	English	Bangla
Common_Rust	Common Rust	কমন রাস্ট
Gray_Leaf_Spot	Gray Leaf Spot	ধূসর পাতা দাগ
Healthy	Healthy	সুস্থ
Northern_Leaf_Blight	Northern Leaf Blight	নর্দার্ন লিফ ব্লাইট

Preprocessing (variant C) — required

Do not letterbox. Letterbox disagreed with the .pt on non-square photos.

1. Resize the shortest side to imgsz = 640, keep aspect ratio.
2. Centre-crop to 640×640.
3. RGB, NHWC, float32 / 255.0.

labels.json is the source of truth (preprocess: centercrop).

Measured export checks

Check	Result
Preprocess verified vs .pt	yes (variant C; independent machine test pass)
FP16 vs FP32 top-1 agreement	1.0
FP16 vs FP32 max softmax diff	1.19209e-07
Independent machine test	pass (August 2026)
Bundled in APK	no — Model Manager download

Validation

Independent test on a separate machine (August 2026) confirmed this TFLite export loads and classifies correctly with the variant-C contract in labels.json. Rice, brassica, and corn all passed the same check.

Intended use

• On-device diagnosis in ChashiBhAI for Bangladeshi farmers (Bangla-first UI).
• Research reproduction of the mobile export.

Out of scope: detection / bounding boxes, crop auto-routing, chemical dosage (handled by a separate advisory stack with a refuse gate).

Limitations

Four-class corn head. Downloaded on demand in the app (not bundled). Not a plant-pathologist substitute. Retake if confidence is low or the leaf is not centred.

Load (Python)

import json
from pathlib import Path
import numpy as np
from PIL import Image
import tensorflow as tf

def preprocess_centercrop(path: str, imgsz: int = 640) -> np.ndarray:
    im = Image.open(path).convert("RGB")
    w, h = im.size
    scale = imgsz / min(w, h)
    nw, nh = int(round(w * scale)), int(round(h * scale))
    im = im.resize((nw, nh), Image.BILINEAR)
    left, top = (nw - imgsz) // 2, (nh - imgsz) // 2
    im = im.crop((left, top, left + imgsz, top + imgsz))
    return (np.asarray(im, dtype=np.float32) / 255.0)[None, ...]

labels = json.loads(Path("labels.json").read_text(encoding="utf-8"))
it = tf.lite.Interpreter(model_path="model.tflite")
it.allocate_tensors()
inp, out = it.get_input_details()[0], it.get_output_details()[0]
it.set_tensor(inp["index"], preprocess_centercrop("leaf.jpg", labels["imgsz"]))
it.invoke()
p = it.get_tensor(out["index"])[0]
i = int(p.argmax())
print(labels["names"][i], float(p[i]))

Related models (same author)

• Rice
• Brassica
• Corn
• Suite index: chashibhai-disease-classifiers

Credit (not this model)

KrishokChat Bengali advisory LLM / RAG is not this classifier. See RaiyanKhaan/KrishokChat-Advisory-System and arXiv:2606.29243 (Reza & Shahid).

Citation

@software{ahmed2026chashibhai_corn_cls,
  author = {Ahmed, Shakil},
  title  = {ChashiBhAI Corn Disease Classifier},
  year   = {2026},
  url    = {https://huggingface.co/Shaq2/chashibhai-corn-disease-cls}
}

License

MIT (see LICENSE). Ultralytics remains under its own license. This pack redistributes weights, not training images.