https://github.com/muhammadakmal137/pytorch_training_pipeline_using_dataset_and_dataloader_class.ipynb

Binary classification of breast cancer using PyTorch. Used StandardScaler, LabelEncoder, Dataset, DataLoader, custom nn.Module model, BCELoss, and SGD. Focused on implementing a complete training pipeline, not optimizing accuracy.
https://github.com/muhammadakmal137/pytorch_training_pipeline_using_dataset_and_dataloader_class.ipynb

ai-healthcare bcelosses binary-classification breast-cancer classification dataset deep-learning labelencoder machine-learing nn-module preprocessing pytorch sigmoid-function standardscaler

Last synced: about 2 months ago
JSON representation

Binary classification of breast cancer using PyTorch. Used StandardScaler, LabelEncoder, Dataset, DataLoader, custom nn.Module model, BCELoss, and SGD. Focused on implementing a complete training pipeline, not optimizing accuracy.

• Host: GitHub
• URL: https://github.com/muhammadakmal137/pytorch_training_pipeline_using_dataset_and_dataloader_class.ipynb
• Owner: MUHAMMADAKMAL137
• Created: 2025-04-07T19:22:36.000Z (about 2 months ago)
• Default Branch: main
• Last Pushed: 2025-04-07T19:31:58.000Z (about 2 months ago)
• Last Synced: 2025-04-13T11:14:30.727Z (about 2 months ago)
• Topics: ai-healthcare, bcelosses, binary-classification, breast-cancer, classification, dataset, deep-learning, labelencoder, machine-learing, nn-module, preprocessing, pytorch, sigmoid-function, standardscaler
• Language: Jupyter Notebook
• Homepage:
• Size: 11.7 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
Breast Cancer Classification using PyTorch

This notebook presents a simple binary classification pipeline using the Breast Cancer dataset implemented with PyTorch. The main focus is to apply key PyTorch components and techniques rather than optimize for model accuracy.

Key steps include:

Data Preprocessing: Standardized the features using StandardScaler and converted categorical labels using LabelEncoder.

Data Batching: Converted the processed data into tensors and used TensorDataset and DataLoader to create mini-batches, enabling mini-batch stochastic gradient descent.

Model Creation: Defined a custom neural network class MySimpleNN with a single linear layer and sigmoid activation function using nn.Module.

Training: Used BCELoss as the loss function and SGD optimizer for training the model over mini-batches.

Evaluation: The goal was to demonstrate the complete pipeline, including model creation, data loading, and training—not to maximize accuracy.