Introduction to PyTorch

[@nafisaanjum1146]

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

[@tanmoymazumder664]

thanks mate

[@dr_flunks]

19:25 The roomba joins the chat

[@mosa36]

The colors make it really hard to read the slides

[@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.

[@davidmurphy563]

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.

[@deehzee]

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

[@mikeanthony773]

I think the brightness is too low. This is how a monitor looks with no backlight. You can see at 3:20ish the slide suddenly becomes bright and readable and then the video stays that way.

[@manuelplank5406]

Love how he roasts his CPU while training

[@ryanhoward5999]

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

[@luisfelipecarreira]

If you didn't pay, why are you complaining about a knowledge being shared for free? It's not that dark...

[@d.mort.]

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

[@user-or7ji5hv8y]

Audio volume is a bit low.

[@drmosfet]

I have to turn up the volume to hear you, When the commercial come on the audio levels or high enough to wake up every one in the house.

[@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

[@pullrequest1296]

Glad to see 720p back.

[@kalok87]

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.

[@pouyanebrahimilialekol2197]

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

[@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)?

[@emrek1]

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

[@rohith2454]

yes , I was wondering the same, glad to see your comment

[@RajarshiBandopadhyay]

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

[@josechavez8754]

HI, I get this error when runnung the dataset notebook. "URLError: " Can it be fixed?

[@Schaelpy]

Loved that Video! Thank you so much

[@Sirvaiya]

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

[@Sirvaiya]

Hope to see more like these :)

[@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)

[@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?

[@golgiwaffles]

I dont seem to understand the AutoGrad aspect as im doing this with no prior ML/DL knowledge. Am i on the right track, or must i learn something prior to his

[@morancium]

i thiiink you should have atleast basic understanding of backpropogation

[@nicolasaragon1078]

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.

[@felixx2012]

For me "images, labels = dataiter.next()" returns the following error: "AttributeError: '_MultiProcessingDataLoaderIter' object has no attribute 'next'". I fixed this by changing the line to "images, labels = next(dataiter)" which I think is the correct implementation. But I am still confused, surely an official tutorial video is not mistaken.

[@vaibhavverma7962]

thanks, worked for me too

[@satvikvenkatesh]

An excellent tutorial!! Thank you.

[@interesting_stuffs]

good videos but audio quality in these videos is very poor, anyway to improve it?

[@heera_ai]

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

[@user-or7ji5hv8y]

Does PyTorch have something equivalent to TensorFlow Probability?

[@BlackHermit]

Great introduction! Thanks

[@Raminder1984]

great video. in the net class at 18.03 needs num_flat_features function without which it wont run looks like.

[@needmusic790]

WHY THE VIDEO IS SO DARK?

[@mikeanthony773]

Some kind of issue with the upload or brightness or something. It goes away at 3:20.

[@chucksaber8332]

loss.backward() does not compute at 9:42 lol

[@istvanszepesi-nagy2516]

nice "how to read the text" tutorial!

[@scaredyfish]

16:54 I get an error on dataiter.next() - next(dataiter) works

[@johnhellewell9550]

worked for me, thank you

[@xiangliangxia5559]

I have the same error

[@angelsancheese]

Thank you for the video

[@imperfect7719]

what is this interface that starts from 4:35 ? where am I gonna actually write this codes if iam onto building some model using Pytorch?

[@Schaelpy]

It is a Jupyter Notebook. You can write Python code basically everywhere with a terminal but an IDEs is recommended. Or for beginners, Google Colab and Kaggle are good choices

[@Tina-gj9qw]

I got a “name ‘transform’ is not defined”when creating a CIFAR10 dataset on 15:14. Still wondering how to fix this.

[@Tina-gj9qw]

i got it：i forgot to run some cells above😓

[@heera_ai]

@11:35 LeNet model for the 32X32 one channel images. import torch import torch.nn as nn import torch.nn.functional as F class LeNet(nn.Module): def __init__(self): super(LeNet, self).__init__() self.conv1 = nn.Conv2d(1, 6,3) self.conv2 = nn.Conv2d(6, 16, 3) self.fc1 = nn.Linear(16*6*6, 120) self.fc2 = nn.Linear(120, 84) self.fc3 = nn.Linear(84,10) self.relu = F.relu def forward(self , x): x = self.conv1(x) #input shape 32X32 -> ouput shape 30X30 x = self.relu(x) x = F.max_pool2d(x ,2) #input shape 30X30 -> ouput shape 15X15 x = self.conv2(x) #input shape 15X15 -> ouput shape 13X13 x = self.relu(x) x = F.max_pool2d(x ,2) #input shape 13X13 -> ouput shape 6X6 x = torch.flatten(x) x = self.fc1(x) x = self.relu(x) x = self.fc2(x) x = self.relu(x) x = self.fc3(x) return x net = LeNet() input_image = torch.rand(1, 1, 32, 32) output = net(input_image) output

[@Yilgrimage]

It really help a lot!😀

[@yuanjizhang9753]

How does torchscript compare to onnx?

[@Urdatorn]

08:41 Keyboard connection is lost just as he defines 'loss' ^^

[@aimatters5600]

increase your browser window man. hard to read

[@emmanuelakpet4735]

Am I the only one that feels the display brightness is too low?

[@dibyaranjansahoo4552]

o boy is the noise because of model training 😏

[@NishantKumar-mp9zg]

There is a background noise that continuously comes forth . It's a static sound that occurs in the second last module. Request you to kindly check it out .

[@felixn.7397]

Probably his graphics card doing the training :P

[@NishantKumar-mp9zg]

@@felixn.7397 Might be :p

[@deeptisinha7348]

Slides are not readable.

[@jeffg4686]

PyTorch only has 27K subscribers ?

[@samrasoli]

useful

[@OpenMicDropNight]

Is this synthetic voice?

[@clearmind9817]

It is only reading the scripts! We can read them too! Unfortunately not a perfect tutorial 😒

[@da-hn]

1729, the hipster version of 42

[@kavorka8855]

the video's dim, very difficult to follow

[@82NeXus]

Working at Facebook? Surely that's an oxymoron? If you were working to permanently disable Facebook (while keeping all user data for download if they want it), that would be work of benefit to humanity!

[@yolowex6876]

For God's sake please increase your text size

[@PurtiRS]

Low brightness, low contrast, low readability, low volume, content is good, but I don't like the mouth sounds in between the words, very distracting, and these are pronounced because I have to increase the volume too high to listen to the content. Kya official video banayega re tu.