02. PyTorch Neural Network Classification

Metadata

• Author: learnpytorch.io
• Full Title: 02. PyTorch Neural Network Classification
• Category:articles
• Summary: The text discusses building PyTorch classification models, preparing data as tensors, and training models with different optimizers and loss functions. It also covers evaluating model predictions, creating multi-class models, and training loops for improving model performance.
• URL: https://www.learnpytorch.io/02_pytorch_classification/

Highlights

• If a loss function measures how wrong your model is, I like to think of evaluation metrics as measuring how right it is. (View Highlight)
• the raw outputs of our model are often referred to as logits. (View Highlight)
• Out of 100 predictions, how many does your model get correct? (View Highlight)
  • Note: accuracy
• Precision Proportion of true positives over total number of samples. (View Highlight)
• Precision Proportion of true positives over total number of samples. (View Highlight)
• Proportion of true positives over total number of samples. (View Highlight)
  • Note: Precision
• Recall Proportion of true positives over total number of true positives and false negatives (View Highlight)