Pix2Pix Paper Walkthrough

❤️ Support the channel ❤️

Paid Courses I recommend for learning (affiliate links, no extra cost for you):

✨ Free Resources that are great:

💻 My Deep Learning Setup and Recording Setup:

GitHub Repository:

✅ One-Time Donations:

▶️ You Can Connect with me on:

Timestamps:
0:00 - Introduction
1:29 - Overview of paper
2:25 - Why GANs for Pix2Pix
3:16 - Loss Function
5:12 - Generator Architecture
9:24 - Discriminator Architecture
12:00 - Some training details
13:24 - Turkers to evaluate GANs
14:10 - Patch size for Discriminator
15:19 - Generator works for larger images
15:50 - More details for implementation
19:05 - Ending

[AladdinPersson]

Next video will be a from scratch implementation on Pix2Pix. Like the video if you want to see more paper implementations!

Timestamps:
0:00 - Introduction
1:29 - Overview of paper
2:25 - Why GANs for Pix2Pix
3:16 - Loss Function
5:12 - Generator Architecture
9:24 - Discriminator Architecture
12:00 - Some training details
13:24 - Turkers to evaluate GANs
14:10 - Patch size for Discriminator
15:19 - Generator works for larger images
15:50 - More details for implementation
19:05 - Ending

[Lutz]

I really like and appreciate your videos, there are no good channels for practical deep learning coding.

[superaluis]

Normally people don't explain the implementation details of the papers like you did (and very clearly). Awesome video.

[verve]

I didn't know how much I needed this until I saw this :")

[kl]

Minibatch SGD is just referring to running on mini batches I guess. Not using the "full" gradient of the data set, but stochastic estimates.
Thanks for the video man.

[oliverl]

Thanks for the video! I think that "we alternate between one gradient descent step on D, then one step on G. We use minibatch SGD and apply the Adam solver" might solve your confusion at 12:44.

[damascenoalisson]

Amazing explanation, I've read this paper many times before but only now I really understood it!

[sureshgohane]

Superlike !!! can't wait for implementation.

[harshmankodiya]

I think in depth explanation for loss function and the notations used for it in paper could have helped more

[IndrainKorea]

Nice video man, great explanation as well 👍👍

[hanantanasra]

thanks for the tutorial!! great job. do you have a tutorial regarding GauGan? thanks!

[alonalon]

@Aladdin Persson
great explanations.
some questions:
at 13:25..the paragraph below the yellow marked test, what do they mean by applying dropout at test time why do they do that? dropout technique is usually used to avoid overfitting in training phase and isn't relevant to inference if i'm not mistaken.
Also, what's meant by applying batchnorm using the statistics of the test batch? batchnorm is also something that is relevant to training and not inference, isn't it?

[joviandsouza]

Hi Aladdin Awesome video, Just curious which software are you using to annotate the pdfs ?

[riis]

@Aladdin Persson.... thanks once again... for these good videos....

[prajotkuvalekar]

Can u please make a vdo on implementation of ssd in pytorch

[saharmokarrami]

Please implement adversarial attacks in nlp, thanks

[sfaroy]

What PDF viewer do you use? I like the annotation toolbar

[Georgesbarsukov]

Personally, my favorite part of the paper is the PatchGAN.

[hoaxuan]

That's nice. What do you think about low curvature initialization of neural nets versus high curvature initialization with random noise. My view is you will never squeez all the randomness out of the system and that the net is actually harder to train.
However my personal view is no training algorithm can do more than search the set of statistical solutions to fit a neural network. More than that is not so possible in higher dimensional space.
So the you would expect random initialization only to slow training but negatively leave a residue of noisy responses in the net.
I suppose pruning and retraining would help you move away from purely statistical behavior. And likewise 'explainable' neural networks where you train a first net to map inputs to human concepts and then train a second net from those concepts to the wanted results.

[palashkamble]

Can you shed some light on what it means to learn a loss function mentioned in the paper? And how is it different from the other loss functions used in, say, conv nets? My interpretation is that usual loss functions are hand-engineered but have no idea regarding the former loss function.