Training with PyTorch

preview_player
Показать описание
This video covers the tools you'll use to train your PyTorch deep learning model, including The Dataset and DataLoader classes, which ease moving your data from storage into active memory for learning; the suite of loss functions available in PyTorch; PyTorch optimizers, which encapsulate algorithms for adjusting learning weights; and the structure of a basic PyTorch training loop.

Рекомендации по теме
Комментарии
Автор

I was really hoping for something more complex than mnist. Most of the time, the data won't come prepackaged for you. For instance, how do you get data into the datasets and dataloaders? There are tons of videos giving this basic rundown and have been for years. After 4 years, I was hoping for something a bit more substantial.

dezh
Автор

Love your vids man! Reading a tutorial is sometimes a little boring, seeing it in video format gives you a good gist on how stuff works and when implementing your own model you already kind off know where to look in the textual tutorial when you need to refresh the specifics.

xseyrdh
Автор

My jupyter stuck when num_worker > 0, I do not have a GPU and I work only with a CPU. Many people say that Jupyter notebooks have known issues with mutilprocessing. How can I solve it?

tiqurqu
Автор

Thank you for this video, but i have a question about training model with pytorch,
I'm working on prediction model with pytorch and i need that the process of preparing data abd training run in parallel, is there any way of doing that?

tayssirmoussa
Автор

max system volume + youtube volume and i still cannot hear what's being said + 720p

calllen
Автор

720p with bad balanced audio? How more amateur can this get?

tonyaxis