Downloads · 30 days
0
MoshinAli/iccit2026-crop-disease-results
iccit2026-crop-disease-results is a machine learning model from MoshinAli. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Generated automatically by the accompanying Kaggle notebook.
Downloads · 30 days
0
Access
Public
Updated Aug 28, 2026
Repo size
199 MB
Likes
0
Public
Click a slice to open those files.
.pth115 MB · 94%
From the Hugging Face model README
Generated automatically by the accompanying Kaggle notebook.
Primary: /kaggle/input/datasets/nirmalsankalana/dhan-shomadhan
Secondary (cross-dataset test): /kaggle/input/datasets/vbookshelf/rice-leaf-diseases
Primary classes (5): ['Rice___bacterial_blight', 'Rice___blast', 'Rice___brown_spot', 'Rice___leaf_scald', 'Rice___tungro']
mobilenet_v2, resnet18, efficientnet_b0
| Accuracy | Precision | Recall | F1 | |
|---|---|---|---|---|
| mobilenet_v2 | 0.7478 | 0.7313 | 0.7158 | 0.7196 |
| resnet18 | 0.7913 | 0.7941 | 0.7554 | 0.7661 |
| efficientnet_b0 | 0.7565 | 0.7308 | 0.7288 | 0.7259 |
Fastest model: mobilenet_v2 (1.2 ms/image)
| Mean (ms) | Std (ms) | FPS | Mobile Est. (ms) | |
|---|---|---|---|---|
| mobilenet_v2 | 1.2 | 0 | 842 | 5 |
| resnet18 | 1.2 | 0.2 | 833 | 5 |
| efficientnet_b0 | 1.4 | 0.1 | 709 | 6 |
All models achieve <200ms inference on mobile devices (real-time capable).
| Accuracy | Precision | Recall | F1 | |
|---|---|---|---|---|
| mobilenet_v2 | 0.5625 | 0.37 | 0.225 | 0.2563 |
| resnet18 | 0.5375 | 0.3745 | 0.215 | 0.2727 |
| efficientnet_b0 | 0.3625 | 0.2833 | 0.145 | 0.1589 |
figures/ - all figures in PNG and PDF (300 dpi)
models/ - trained model weights (.pth)
metrics/ - CSV/JSON metrics and per-model classification reports
ICCIT2026_all_figures_report.pdf - combined multi-page figure report