Update README.md

README.md

@@ -1,55 +1,124 @@
-# AgriScan EfficientNetB0 — Crop and Disease Classification
+---
+language:
+  - en
+license: other
+library_name: keras
+pipeline_tag: image-classification
+tags:
+  - agriscan
+  - agriculture
+  - plant-disease
+  - crop-classification
+  - image-classification
+  - efficientnet
+  - efficientnetb0
+  - tensorflow
+  - keras
+  - plantvillage
+datasets:
+  - mohanty/PlantVillage
+---
+
+# AgriScan EfficientNetB0 — Crop and Plant Disease Classifiers
+
+AgriScan is an agricultural intelligence project developing computer-vision tools to support crop identification and plant-health screening.
+
+This repository is intended to contain two separately trained EfficientNetB0 models:
+
+1. **Crop classifier** — predicts whether an image belongs to maize, potato, or tomato.
+2. **Disease classifier** — predicts one of 17 crop-condition classes across those crops.
+
+> **Status:** Research and pilot prototype. Add measured evaluation results after the training notebook has completed successfully.
+
+## Repository contents
+
+Expected files:
+
+```text
+.
+├── README.md
+├── agriscan_efficientnet_crop.keras
+├── agriscan_efficientnet_disease.keras
+├── crop_names.json
+├── class_names.json
+├── evaluation_metrics.json
+├── crop_classification_report.csv
+├── disease_classification_report.csv
+├── crop_confusion_matrix.csv
+└── disease_confusion_matrix.csv
+```
+
+Upload only the files that have actually been generated. Evaluation reports and metrics should be added after the training and evaluation cells finish.
+
+## Model details
+
+| Property | Crop classifier | Disease classifier |
+|---|---|---|
+| Architecture | EfficientNetB0 | EfficientNetB0 |
+| Task | Crop classification | Crop-condition classification |
+| Number of output classes | 3 | 17 |
+| Input | RGB image | RGB image |
+| Input size | 224 × 224 pixels | 224 × 224 pixels |
+| Model format | Keras `.keras` | Keras `.keras` |
+
+The training workflow uses transfer learning with an ImageNet-pretrained EfficientNetB0 backbone, first training the classification head and then fine-tuning upper backbone layers.
+
+### Crop classes
 
-## Overview
+- Maize
+- Potato
+- Tomato
 
-AgriScan EfficientNetB0 is an experimental agricultural image-classification system developed by CDSA (Cross Domain Solution Architect).
+### Disease classes
 
-The system uses two independently trained EfficientNetB0 classifiers to identify selected crops and predict their corresponding disease or healthy condition.
+The 17 output labels are defined in `class_names.json`. **The JSON order is significant** because it maps each output index to its label. Use the exact file produced by the training notebook; do not manually reorder the labels.
 
-## Model Architecture
+## Dataset and evaluation
 
-### 1. Crop Classifier
+The training workflow uses the `mohanty/PlantVillage` dataset and its `splits/color_train.txt` and `splits/color_test.txt` manifests, filtered to maize, potato, and tomato classes.
 
-Model file: `agriscan_efficientnet_crop.keras`
+The training partition is divided into training and validation subsets. The source test partition is reserved for final evaluation.
 
-Predicts one of three crop categories:
-- Maize
-- Potato
-- Tomato
+No performance metrics are stated here because the EfficientNetB0 training run must complete before results can be reported. After evaluation, update this section using the generated `evaluation_metrics.json` and classification reports. Report the test-set size and metrics exactly as measured; do not use training or validation scores as test scores.
+
+## Input preprocessing
 
-### 2. Disease Classifier
+- Convert the image to RGB.
+- Resize to 224 × 224 pixels.
+- Supply pixel values in the range expected by the saved model.
+- The Keras EfficientNetB0 backbone includes input rescaling. Do not apply MobileNetV2-specific `Rescaling(1/127.5, offset=-1)` preprocessing unless the model architecture is deliberately changed and retrained.
 
-Model file: `agriscan_efficientnet_disease.keras`
+Use the model's actual training/inference pipeline when deploying it.
 
-Predicts one of 17 crop-disease or healthy classes across maize, potato and tomato.
+## Recommended inference flow
 
-## Training
+1. Run the crop classifier.
+2. Run the disease classifier.
+3. Read the predicted labels using `crop_names.json` and `class_names.json`.
+4. Compare the crop predicted by the crop classifier with the crop implied by the disease-class label.
+5. If the two classifiers disagree, or confidence is low, return an uncertain/review result instead of presenting a definitive diagnosis.
 
-- Architecture: EfficientNetB0
-- Framework: TensorFlow / Keras
-- Input dimensions: 224 × 224 pixels
-- Input format: RGB
-- Dataset: PlantVillage
-- Training method: Transfer learning followed by fine-tuning
-- Evaluation: Held-out test set from the source dataset
+The two classifiers are independent models. A downstream application must implement the routing, confidence policy, and disagreement handling.
 
-## Evaluation
+## Intended use
 
-Evaluation metrics and class-level reports are provided in the repository.
+This model is intended for research, prototyping, and controlled pilot evaluation of crop classification and plant-disease image classification for maize, potato, and tomato.
 
-Published performance figures should be taken from the completed evaluation artifacts, not assumed from the training process.
+## Limitations and responsible use
 
-## Intended Use
+- This is a closed-set classifier. It is not a general plant detector and may assign an unsupported label to non-plant images.
+- It predicts only among the classes represented in the training labels; unknown diseases and other crops are not supported.
+- PlantVillage images may differ from farmer field photographs in lighting, backgrounds, camera quality, geography, crop varieties, and disease severity.
+- A high softmax score is not a guarantee of correctness and should not be treated as calibrated probability without further calibration work.
+- Predictions are not a substitute for expert agricultural advice or laboratory diagnosis.
+- Validate on representative real-world field images before operational deployment.
 
-This model is intended for research, prototyping and testing agricultural image-classification workflows.
+## Citation and attribution
 
-## Limitations
+The dataset used by the training workflow is available as [`mohanty/PlantVillage`](https://huggingface.co/datasets/mohanty/PlantVillage). Review the dataset card and its terms before redistributing derived assets.
 
-- The classifiers cover only the crop and disease classes represented in training.
-- The model is not guaranteed to identify unfamiliar diseases or distinguish all non-plant images from crop leaves.
-- PlantVillage images may differ from photographs taken under real farming conditions.
-- Predictions should be validated using field data and, where necessary, agricultural expertise.
+## Contact and project
 
-## Development
+Project: **AgriScan**, an agricultural intelligence initiative associated with CDSA.
 
-Developed as part of the AgriScan agricultural intelligence initiative by CDSA.
+For deployment, document the model version, training date, dataset version, evaluation results, and any changes to preprocessing or class mappings.