ixrbhii/rice-disease-convnext

Rice leaf disease classifier

Tells which of 14 classes a rice leaf photo shows: Bacterial Blight, Bacterial Leaf Streak, Bacterial Panicle Blight, Blast, Brown Spot, Dead Heart, Downy Mildew, Healthy, Hispa, Leaf Scald, Narrow Brown Leaf Spot, Neck Blast, Sheath Blight, Tungro.

ConvNeXt-Small (convnext_small, from convnext_small.fb_in22k_ft_in1k), 224 × 224 RGB, 99 MB (half precision). 93.5 % test accuracy, macro-F1 0.940, on 1,579 held-out photos. Test photos come from the same datasets the model learned from, so real field photos score lower.

Class	Recall	F1	Test photos
Bacterial Blight	88.0%	0.926	150
Bacterial Leaf Streak	98.2%	0.957	56
Bacterial Panicle Blight	100.0%	0.962	50
Blast	85.3%	0.880	150
Brown Spot	90.7%	0.935	150
Dead Heart	98.0%	0.990	150
Downy Mildew	94.5%	0.887	91
Healthy	89.3%	0.896	150
Hispa	89.3%	0.879	150
Leaf Scald	98.2%	0.946	54
Narrow Brown Leaf Spot	100.0%	0.959	35
Neck Blast	100.0%	1.000	144
Sheath Blight	99.0%	0.990	99
Tungro	96.7%	0.948	150

Use

import timm, torch
from PIL import Image

model = timm.create_model("hf-hub:ixrbhii/rice-disease-convnext", pretrained=True).eval()
cfg = timm.data.resolve_data_config({}, model=model)
x = timm.data.create_transform(**cfg)(Image.open("leaf.jpg").convert("RGB")).unsqueeze(0)
p = model(x).softmax(-1)[0]
labels = model.pretrained_cfg["label_names"]
for i in p.argsort(descending=True)[:3]:
    print(labels[i], f"{100 * p[i]:.1f} %")

The training images were resized to 224 × 224 without cropping; timm's transform above (resize + 224 centre crop) gives the same result for square photos. label_descriptions in config.json maps each name to the dataset's original label. Best results: one leaf filling most of the photo, in daylight and in focus. Below about 45 % confidence, ask for a better photo.

In an app: LULC Fetch (Agri ▸ Diagnose crop disease) recognises the crop first and then runs the right disease model, with a photo-quality check and a disease map from geotagged photos.

Related

• All 44 models (2 crop detectors, 42 crops) as separate repositories: the collection
• All 44 models in one repository: ixrbhii/multicrop-disease-models
• Symptoms, treatment and pests for each disease: ixrbhii/crop-disease-qa

Training data and licence

Trained on LeafNet (CC-BY-4.0) and the authors' own field photos. Released under CC-BY-4.0: please credit "Multi-crop disease models, IXR (agritechixr)" and the training datasets. A diagnosis supports, but doesn't replace, a local agriculture expert.