How sifat192/rice-type-classification-pytorch works
This repository is a PyTorch rice-type classifier. Its documented workflow takes morphological rice measurements through preprocessing and a train/test split, then uses a custom Dataset and DataLoader to train a neural network, evaluate it on test data, and predict rice type. The tree contains a notebook but no sampled notebook source, so the graph relies on the README’s workflow and capability descriptions; implementation-level calls and any additional integrations cannot be verified.
Main entry points: Rice_classification.ipynb Feature Preprocessing
Components 9
Data Preparation
- Feature Preprocessing
Rice_classification.ipynb - Train/Test Split
Rice_classification.ipynb - Custom Dataset
Rice_classification.ipynb - DataLoader
Rice_classification.ipynb
Modeling
- Neural Network
Rice_classification.ipynb - Model Training
Rice_classification.ipynb
Evaluation and Prediction
- Test Evaluation
Rice_classification.ipynb - Rice Prediction
Rice_classification.ipynb
Other components
- Rice Dataset
Connections 8
- Rice Dataset → Feature Preprocessing: provides features
README.md - Feature Preprocessing → Train/Test Split: prepares data
README.md - Train/Test Split → Custom Dataset: partitions data
README.md - Custom Dataset → DataLoader: supplies samples
README.md - DataLoader → Model Training: feeds batches
README.md - Model Training → Neural Network: optimizes
README.md - Neural Network → Test Evaluation: evaluated on test set
README.md - Test Evaluation → Rice Prediction: supports prediction
README.md