Commit ·
88c669c
1
Parent(s): 290f5c4
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# 2050_Materials_Models
|
| 2 |
+
|
| 3 |
+
## Overview
|
| 4 |
+
|
| 5 |
+
This repository, titled `2050_materials_models`, is a part of the 2050-materials platform. It contains various machine learning models developed to enhance the platform's capabilities.
|
| 6 |
+
|
| 7 |
+
## Models in this Repository
|
| 8 |
+
|
| 9 |
+
Currently, the repository hosts two models:
|
| 10 |
+
|
| 11 |
+
1. `prediction_model_material.pth`: A model for predicting the best match from a list of material types.
|
| 12 |
+
2. `prediction_model_product.pth`: A model used to predict the best match from a range of product types.
|
| 13 |
+
|
| 14 |
+
These models are built to streamline the process of identifying and categorizing different materials and products used in construction, assisting in making more environmentally informed choices.
|
| 15 |
+
|
| 16 |
+
## How to Use
|
| 17 |
+
|
| 18 |
+
### Requirements
|
| 19 |
+
|
| 20 |
+
The primary requirements include:
|
| 21 |
+
|
| 22 |
+
- PyTorch
|
| 23 |
+
- Joblib (if applicable)
|
| 24 |
+
|
| 25 |
+
### Loading the Models
|
| 26 |
+
|
| 27 |
+
You can load these models using PyTorch. Here's a quick snippet on how to do it:
|
| 28 |
+
|
| 29 |
+
```python
|
| 30 |
+
import torch
|
| 31 |
+
|
| 32 |
+
# Load the material prediction model
|
| 33 |
+
material_model_path = 'path/to/prediction_model_material.pth'
|
| 34 |
+
material_model = torch.load(material_model_path)
|
| 35 |
+
|
| 36 |
+
# Load the product prediction model
|
| 37 |
+
product_model_path = 'path/to/prediction_model_product.pth'
|
| 38 |
+
product_model = torch.load(product_model_path)
|
| 39 |
+
|
| 40 |
+
# Example of using the models for prediction
|
| 41 |
+
|
| 42 |
+
|