Introduction to PyTorch

In the first video of this series, we give a broad overview of the parts of the PyTorch toolchain, including: Tensors, automatic gradient computation, model building basics, data loading abstractions, model training, and deployment for inference. This video is meant as a survey, with each topic being covered in more depth in subsequent videos.

Download individual notebooks here:

1. Tensors - 04:45 to 07:50

2. Autograd - 08:00 to 9:50

3. A simple model - 10:00 to 14:00

4. Datasets - 14:00 to 17:10

5. Training loop - 17:10 to 21:00

[mosa]

The colors make it really hard to read the slides

[nafisaanjum]

0:00 Intro
0:52 PyTorch Installation
1:32 What is PyTorch
3:51 Tensors
7:56 Autograd
10:00 A simple model
14:00 Datasets
17:00 Training Loop
21:15 Deployment

[ryanhoward]

If PyTorch is so smart, why can't you use it to increase your video BRIGHTNESS GODD!!!

[niyongaboeric]

I like the introduction video as I could see how you can use Pytorch to train model, visualize results and deploying in production. You helped me and I just want to say thank you.

[manuelplank]

Love how he roasts his CPU while training

[rmajdodin]

7:04 it should be (torch.rand(2, 2) -0.5) * 2, otherwise it works like torch.rand(2, 2) -1, because of operator precedence

[deehzee]

Very hard to read the slide due to unfortunate choices of font colors (no contrast)

[davidmurphy]

Obviously this is a year old and the narrator probably won't see this but a zoomed in view would make this infinitely more accessible on mobile. Great video regardless.

[kalok]

Hello, something might be wrong there. at 11:01 we have the C1 size (28*28), and the code in the comment said "# 1 input image channel (black & white), 6 output channels, 3x3 square convolution". But apply a 3*3 window on 32*32 input will get 30*30 output. I think the graph describes the structure in the original paper which was using 5*5 window at C1.

[PRonYouTube]

Is there a typo ~ 15:10 when the image normalization is done? if we're seeking to achieve an average of 0, shouldn't the first tuple passed in be (0, 0, 0) instead of (0.5, 0.5, 0.5)?

[d.mort.]

This was quite a good rapid intro video. Thank you very much!

[josechavez]

HI, I get this error when runnung the dataset notebook. "URLError: <urlopen error [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: certificate has expired (_ssl.c:1123)>" Can it be fixed?

[pouyanebrahimilialekol]

Thanks for the video. If the CIFAR10 dataset isn't downloading by the code, you may for as below:
import ssl
=
trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
download=True, transform=transform)

[emrek]

I think in code segment 6 the first line should be r1 = (torch.rand(2, 2)-0.5) * 2
otherwise it will be equivalent to r1 = torch.rand(2, 2) - 1

[nicolasaragon]

I found this helpful. Thanks for sharing this tutorial!

I found a problem in the Autograd section, which could be corrected. I'm using Pytorch2.1.1 and it seems that `loss.backdward()` requires that the tensors get constructed with `requires_grad=True`.

I checked the documentation and it seems that this is the default, but it didn't work for me until I specified the value explicitly.

[RajarshiBandopadhyay]

Is it just my machine, or is this video kinda dark?

[Sirvaiya]

thanks a lot. very good video. It was littleee fast i think. And best thing was there was no ad for me :)

[orjihvy]

Does PyTorch have something equivalent to TensorFlow Probability?

[CaptainKokomoGaming]

Where do I run these commands??? I am trying to teach myself this stuff on the fly but my wings are on fire. I only want to learn ths stuff to stop the damn cuda errors on my Stable Diffusion local install. It's driving me nuts! I don't know where to put the "torch.cuda.empty_cache()" either.
Can someone please help me?

[heera_ai]

@7:14
r = (torch.rand(2, 2) - 0.5) * 2 # normalize values to -1. to 1.
r = torch.rand(2, 2) - 0.5 * 2 # generates random values in range of [-1., 0.]

@8:00 Set requires_grad = True
example:
x = torch.rand(1, 10, requires_grad = True)