Train a PyTorch neural network step-by-step | PyTorch deep learning (Feb 2023)

preview_player
Показать описание
Putting everyone we've learned in the pytorch tutorial series, we're building a neural network for classification and training our classifier using a train and test loop! 85% test accuracy on Fashion MNIST with less than 1 hour of work!

00:00 Mental model: Training a neural network in PyTorch
01:45 PyTorch imports and hyperparemeters
04:10 Training and test data for our FashionMNIST classification
08:03 Creating our Neural Network using PyTorch's nn module
15:16 Loss function, Cross-Entropy Loss and Optimizers
24:39 Setting up a training loop for the forward pass + backward pass
43:42 Visualize our computation graph with pytorchviz
46:02 Saving and loading pytorch models

Watch the whole PyTorch GPU deep learning series:

New to PyTorch? Start here:

Need an explanation of backpropagation and gradient descent?
Рекомендации по теме
Комментарии
Автор

The way you are explaning that is easy to understand, if you share this code, then it will be more better

mightylearning