PyTorch Project: Handwritten Digit Recognition

preview_player
Показать описание
Today we train a neural network to classify handwritten digits using PyTorch.

◾◾◾◾◾◾◾◾◾◾◾◾◾◾◾◾◾
📚 Programming Books & Merch 📚

💼 Services 💼

🌐 Social Media & Contact 🌐
Рекомендации по теме
Комментарии
Автор

I wish you explained some of your steps or reasoning more, I followed along but I feel like I just copied code without truly understanding what is doing what. Still useful, but as a beginner it leaves me wanting!

Lucas-rzvl
Автор

Dayum! i built it and IT WORKS!!! It took about a hour of debugging bcos i misspelt a lot, like l instead of 1, etc, BUT IT WORKS AND IM SO PROUD OF MYSELF

rdagain-fp
Автор

I used your architecture basically and yes, it performs great on the testset. But when inputing my self drawn numbers it sucks, can't get a single one right... I don't understand this..

esserk
Автор

10/10 video bro! I love your expositions, do you think you could show us how to do spatial recognition with a neural network to extract information from specific entities on forms? For example, extracting information from a tax form or medical record

ddpigger
Автор

I created a gui to input my own numbers into the model that was coded in this video, but no matter what I try, I cannot get the prediction to be 9. Any thoughts on why that is?

rykermcknight
Автор

please more pytorch videos, do you think of doing lives about kaggle comp?

scarysticks
Автор

Can you please recommend me sources from which I can study Python for system and network administration? Thank you very much!

DonaldJevgenjevichPanasonic
Автор

Can we use this for decimal number and mixed fraction recognition too??

himanshujha
Автор

What for to use shuffle=True on a test data?

vladmirbc
Автор

21:50 from now on don't write these kinds of fstrings.

B_I_S_H_A_L_
join shbcf.ru