Diffusion Models | PyTorch Implementation

แชร์
ฝัง
  • เผยแพร่เมื่อ 29 ธ.ค. 2024

ความคิดเห็น • 184

  • @outliier
    @outliier  2 ปีที่แล้ว +21

    Link to the code: github.com/dome272/Diffusion-Models-pytorch

    • @bao-dai
      @bao-dai 2 ปีที่แล้ว +2

      21:56 The way you starred your own repo makes my day bro 🤣🤣 really appreciate your work, just keep going!!

    • @outliier
      @outliier  2 ปีที่แล้ว

      @@bao-dai xd

    • @leif1075
      @leif1075 ปีที่แล้ว

      @@outliier Thanks for sharing but how do you not get bored or tired of doing the same thing for so long and deal with all the math?

    • @outliier
      @outliier  ปีที่แล้ว

      @@leif1075 I love to do it. I don’t get bored

    • @ananpinya835
      @ananpinya835 ปีที่แล้ว

      After I saw your next video "Cross Attention | method and math explained", I would like to see ControlNet's openpose in PyTorch Implementation which control posing on image of a dogs. Or if it is too complicate, you may simplify it to control 2 - 3 branches shape of a tree.

  • @aladinwunderlampe7478
    @aladinwunderlampe7478 2 ปีที่แล้ว +54

    Hello, this has become a great video once again. We didn't understand much, but it's still nice to watch. Greetings from home say Mam & Dad. ;-))))

  • @javiersolisgarcia
    @javiersolisgarcia 10 หลายเดือนก่อน +7

    This videos is crazy! I don't get tired of recommend it to anyone interesting in diffusion models. I have recently started to research with these type of models and I think your video as huge source of information and guidance in this topic. I find myself recurrently re-watching your video to revise some information. Incredible work, we need more people like you!

    • @outliier
      @outliier  10 หลายเดือนก่อน +3

      Thank you so much for the kind words!

  • @AICoffeeBreak
    @AICoffeeBreak 2 ปีที่แล้ว +35

    Great, this video is finally out! Awesome coding explanation! 👏

  • @astrophage381
    @astrophage381 6 หลายเดือนก่อน +2

    These implementation videos are marvelous. You really should do more of them. Big fan of your channel!

  • @terencelee6492
    @terencelee6492 ปีที่แล้ว +7

    We chose Diffusion Model as part of our course project, and your videos do save much of my time to understand the concepts and have more focus on implementing the main part. I am really grateful for your contribution.

  • @MrScorpianwarrior
    @MrScorpianwarrior 6 หลายเดือนก่อน +1

    Hey! I am start my CompSci Masters program in the Fall, and just wanted to say that I love this video.
    I've never really had time to sit down and learn PyTorch, so the brevity of this video is greatly appreciated! It gives me a fantastic starting point that I can tinker around with, and I have an idea on how I can apply this in a non-conventional way that I haven't seen much research on...
    Thanks again!

    • @outliier
      @outliier  6 หลายเดือนก่อน +1

      Love to hear that
      Good luck on your journey!

  • @Mandollr
    @Mandollr ปีที่แล้ว +1

    After my midterm week i wanna study diffusion models with your videos im so exited .thanks a lot for good explanation

  • @ethansmith7608
    @ethansmith7608 ปีที่แล้ว

    this is the most underrated channel i've ever seen, amazing explanation !

    • @outliier
      @outliier  ปีที่แล้ว

      thank you so much!

  • @rewixx69420
    @rewixx69420 2 ปีที่แล้ว +1

    I was wating for so long i learnd about condicional difusion models

  • @stevemurch3245
    @stevemurch3245 2 ปีที่แล้ว +2

    Incredible. Very thorough and clear. Very, very well done.

  • @yingwei3436
    @yingwei3436 ปีที่แล้ว +1

    thank you so much for your detailed explaination of the code. It helped me a lot on my way of learning diffusion model. Wish there are more youtubers like you!

  • @Miurazzo
    @Miurazzo 2 ปีที่แล้ว +8

    Hi, @Outlier , thank you for the awesome explanation !
    Just one observation, I believe in line 50 of your code (at 19:10) it should be:
    uncond_predicted_noise = model(x,t,None)
    😁

    • @outliier
      @outliier  2 ปีที่แล้ว +6

      good catch thank you. (It's correct in the github code tho :))

  • @subtainmalik5182
    @subtainmalik5182 ปีที่แล้ว

    most informative and easy to understand video on diffusion models on youtube, Thanks Man

  • @potisseslikitap7605
    @potisseslikitap7605 2 ปีที่แล้ว +3

    This channel seems to be growing very fast. Thanks for this amazing tutorial.🤩

  • @mmouz2
    @mmouz2 ปีที่แล้ว

    Sincere gratitude for this tutorial, this has really helped me with my project. Please continue with such videos.

  • @haoxu3204
    @haoxu3204 11 หลายเดือนก่อน

    The best video for diffusion! Very Clear

  • @TheAero
    @TheAero ปีที่แล้ว

    This is my first few days of trying to understand diffusion models. Coding was kinda fun on this one. I will take a break for 1-2 months and study something related like GANs or VAE, or even energy-based models. Then comeback with more general understanding :) Thanks !

    • @zenchiassassin283
      @zenchiassassin283 ปีที่แล้ว

      And transformers for the attention mechanisms + positional encoding

    • @TheAero
      @TheAero ปีที่แล้ว

      I got that snatched in the past 2 months. Gotta learn the math, what is actually a distribution etc.@@zenchiassassin283

  • @manuelsebastianriosbeltran972
    @manuelsebastianriosbeltran972 2 ปีที่แล้ว +1

    Congrats, This is a great channel!! hope to see more of these videos in the future.

  • @FLLCI
    @FLLCI 2 ปีที่แล้ว +1

    This video is really timely and needed. Thanks for the implementation and keep up the good work!

  • @gaggablagblag9997
    @gaggablagblag9997 ปีที่แล้ว

    Dude, you're amazing! Thanks for uploading this!

  • @pratyanshvaibhav
    @pratyanshvaibhav 6 หลายเดือนก่อน

    The Under rated OG channel

  • @prabhavkaula9697
    @prabhavkaula9697 2 ปีที่แล้ว

    Thank you for sharing the implementation since authentic resources are rare

  • @ZhangzhiPeng-x8r
    @ZhangzhiPeng-x8r 2 ปีที่แล้ว +2

    great tutorial! looking to seeing more of this! keep it up!

  • @SeonhoonKim
    @SeonhoonKim ปีที่แล้ว +1

    Hello, thanks for your a lot contribution ! But a bit confused, At 06:04, just sampling from N(0, 1) totally randomly would not have any "trace" of an image. How come the model infer the image from the totally random noise ?

    • @outliier
      @outliier  ปีที่แล้ว +1

      Hey there, that is sort of the "magic" of diffusion models which is hard to grasp your mind around. But since the model is trained to always see noise between 0% and 100% it sees full noise during training for which it is then trained to denoise it. And usually when you provide conditioning to the model such as class labels or text information, the model has more information than just random noise. But still, unconditional training still works.

  • @salehgholamzadeh3368
    @salehgholamzadeh3368 3 หลายเดือนก่อน

    Great video
    I faced a question at 19:10 line 50 of the code. why do we call
    ```model(x,label,None)```
    what happened to t? shouldn't we instead call it like ```model(x,t,None)``` ??
    also line 17 in ema (20:31) ```retrun old * self.beta +(1+self.beta) * new``` why 1+self.beta? shouldnt it be 1-self.beta?

  • @vinc6966
    @vinc6966 ปีที่แล้ว

    Amazing tutorial, very informative and clear, nice work!

  • @DiogoSanti
    @DiogoSanti 10 หลายเดือนก่อน

    Very well done! Keep the great content!!

  • @scotth.hawley1560
    @scotth.hawley1560 10 หลายเดือนก่อน

    Wonderful video! I notice that at 18:50, the equation for the new noise seems to differ from Eq. 6 in the CFG paper, as if the unconditioned and conditioned epsilons are reversed. Can you comment on that?

  • @NickSergievskiy
    @NickSergievskiy ปีที่แล้ว

    Thank you. Best explanation with good DNN models

  • @947973
    @947973 ปีที่แล้ว

    Very helpful walk-through. Thank you!

  • @yuhaowang9846
    @yuhaowang9846 ปีที่แล้ว

    Thank you so much for this sharing, that was perfect!

  • @chickenp7038
    @chickenp7038 2 ปีที่แล้ว +2

    great walkthrough. but where would i implement dynamic or static thresholding as described in the imagen paper? the static thresholding clips all values larger then 1 but my model regularly outputs numbers as high as 5. but it creates images and loss decreases to 0.016 with SmoothL1Loss.

  • @smnvrs
    @smnvrs ปีที่แล้ว

    Thanks, this implementation really helped clear things up.

  • @dylanwattles7303
    @dylanwattles7303 11 หลายเดือนก่อน

    nice demonstration, thanks for sharing

  • @qq-mf9pw
    @qq-mf9pw ปีที่แล้ว

    Incredible explanation, thanks a lot!

  • @Gruell
    @Gruell 8 หลายเดือนก่อน

    Sorry if I am misunderstanding, but at 19:10, shouldn't the code be:
    "uncond_predicted_noise = model(x, t, None)" instead of "uncond_predicted_noise = model(x, labels, None)"
    Also, according to the CFG paper's formula, shouldn't the next line be: "predicted_noise = torch.lerp(predicted_noise, uncond_predicted_noise, -cfg_scale)" under the definition of lerp?
    One last question: have you tried using L1Loss instead of MSELoss? On my implementation, L1 Loss performs much better (although my implementation is different than yours). I know the ELBO term expands to essentially an MSE term wrt predicted noise, so I am confused as to why L1 Loss performs better for my model.
    Thank you for your time.

    • @Gruell
      @Gruell 8 หลายเดือนก่อน

      Great videos by the way

    • @Gruell
      @Gruell 8 หลายเดือนก่อน

      Ah, I see you already fixed the first question in the codebase

  • @kashishmathukiya8091
    @kashishmathukiya8091 ปีที่แล้ว

    8:38 in the UNet section, how do you decide on the number of channels to set in both input and output to the Down and Up classes. Why just 64,128, etc. ?

    • @outliier
      @outliier  ปีที่แล้ว +1

      People just go with powers of 2 usually. And usually you go to more channels in the deeper layers of the network.

    • @kashishmathukiya8091
      @kashishmathukiya8091 ปีที่แล้ว

      @@outliier oh okay got it. Thank you so much for clearing that and for the video! I had seen so many videos / read articles for diffusion but yours were the best and explained every thing which others considered prerequisites!! Separating the paper explanation and implementation was really helpful.

  • @henrywong741
    @henrywong741 ปีที่แล้ว +2

    Could you please explain the paper "High Resolution Image Synthesis With Latent Diffusion Models" and its implementations? Your explanations are exceptionally crystal.

  • @jamesfogwill1455
    @jamesfogwill1455 4 หลายเดือนก่อน +1

    Roughly how long does an Epoch take for you? I am using rtx3060 mobile and achieving an epoch every 24 minutes. Also i cannot work with a batch size greater than 8 and a img size greater than 64 because it overfills my GPUs 6gb memory. I thought this was excessive for such small batch and img size?

  • @talktovipin1
    @talktovipin1 2 ปีที่แล้ว

    Looking forward for some video on Classifier Guidance as well. Thanks.

  • @LeeYuanZ
    @LeeYuanZ ปีที่แล้ว

    Thank you so much for this amazing video! In mention that the first DDPM paper show no necessary of lower bound formulation, could you tell me the specific place in the paper? thanks!

  • @rachelgardner1799
    @rachelgardner1799 ปีที่แล้ว

    Fantastic video!

  • @sweetautumnfox
    @sweetautumnfox 9 หลายเดือนก่อน

    With this training method, wouldn't there be a possibility of some timesteps not being trained in an epoch? wouldn't it be better to shuffle the whole list of timesteps and then sample sequentially with every batch?

  • @gordondou2286
    @gordondou2286 ปีที่แล้ว

    Can you please explain how to use Woodfisher technique to approximate second-order gradients? Thanks

  • @LMonty-do9ud
    @LMonty-do9ud ปีที่แล้ว

    Thank you very much, it has solved my urgent need

  • @doctorshadow2482
    @doctorshadow2482 ปีที่แล้ว

    Thank you for the review. So, what is the key to make a step from text description to image? Can you please pinpoint where it is explained?

  • @yazou3896
    @yazou3896 ปีที่แล้ว

    It's definitely cool and helpful! Thanks!!!

  • @pedrambazrafshan9598
    @pedrambazrafshan9598 2 หลายเดือนก่อน

    Could you also make a video on how to implement DDIM? Or make a GitHub repository about it?

  • @susdoge3767
    @susdoge3767 10 หลายเดือนก่อน

    having hard time to understand the mathematical and code aspect of diffusion model although i have a good high level understanding...any good resource i can go through? id appreciate it

  • @ankanderia4999
    @ankanderia4999 8 หลายเดือนก่อน

    `
    x = torch.randn((n, 3, self.img_size, self.img_size)).to(self.device)
    predicted_noise = model(x, t)
    `
    in the deffusion class why you create an noise and pass that noise into the model to predict noise ... please explain

  • @signitureDGK
    @signitureDGK ปีที่แล้ว

    Very cool. How would DDIM models be different? Do they use a deterministic denoising sampler?

    • @outliier
      @outliier  11 หลายเดือนก่อน

      yes indeed

  • @talktovipin1
    @talktovipin1 2 ปีที่แล้ว

    Very nicely explained. Thanks.

  • @Sherlock14-d6x
    @Sherlock14-d6x 5 หลายเดือนก่อน

    Why is the bias off in the initial convolutional block?

  • @nez2884
    @nez2884 2 ปีที่แล้ว

    awesome implementation!

  • @ParhamEftekhar
    @ParhamEftekhar 6 หลายเดือนก่อน

    Awesome video.

  • @janevirahman9904
    @janevirahman9904 10 หลายเดือนก่อน

    Hi , I want to use a single underwater image dataset what changes do i have to implement on the code?

  • @cryoemenjoyer
    @cryoemenjoyer 2 ปีที่แล้ว

    6:57 Why the formula is ... + torch.sqrt(beta) instead of calculated posterior variance like in paper?

    • @outliier
      @outliier  2 ปีที่แล้ว

      Which paper are you referring to? In the first paper, you would just set the variance to beta and since you add the std * noise you take the sqrt(beta)

  • @orestispapanikolaou9798
    @orestispapanikolaou9798 2 ปีที่แล้ว

    Great video!! You make coding seem like playing super mario 😂😂

  • @wizzy1996pl
    @wizzy1996pl ปีที่แล้ว

    last self attention layer (64, 64) changes my training type from 5 minutes to hours per epoch, do you know why?
    training on a single rtx 3060 TI gpu

  • @Kooshiar
    @Kooshiar ปีที่แล้ว

    best diffusion youtube

  • @khangvutien2538
    @khangvutien2538 10 หลายเดือนก่อน

    People in Earth Observation know that images from Synthetic Aperture Radar have random speckles. People have tried removing the speckles using wavelets. I wonder how Denoising Diffusion would fare. The difficulty that I see is the need for x0 the un-noised image.
    What do you think?

  • @xuefengdu6926
    @xuefengdu6926 2 ปีที่แล้ว

    thanks for your amazing efforts!

  • @junghunkim8467
    @junghunkim8467 ปีที่แล้ว

    it is very helpful!! You are a genius.. :) thank you!!

  • @versusFliQq
    @versusFliQq ปีที่แล้ว

    Really nice video! I also enjoyed your explanation video - great work in general :)
    However, I noticed at around 5:38, you are defining sample_timesteps with low=1. I am pretty sure that this is wrong, as Python indexes at 0 meaning you skip the first noising step every time you access alpha, alpha_cumprod etc. Correct me if I am wrong but all the other implementations also utilise zero-indexing.

    • @arpanpoudel
      @arpanpoudel ปีที่แล้ว

      this function sample the timesteps of the denoising step. selecting time=0 is the original image itself. there is no point in taking 0 timestep.

  • @luchaoqi
    @luchaoqi 2 ปีที่แล้ว +1

    Awesome! How did you type Ɛ in code?

  • @pedrambazrafshan9598
    @pedrambazrafshan9598 ปีที่แล้ว

    @outliier Do you think there is a way to run the code with a 3060 GPU on personal desktop? I get the error message: CUDA out of memory.

    • @MrScorpianwarrior
      @MrScorpianwarrior 6 หลายเดือนก่อน

      Random person 6 months later, but you could try decreasing the batch size during training. Your results may not look like what he got in the video though!

  • @Laszer271
    @Laszer271 ปีที่แล้ว

    There is a slight bug at 19:11
    it should be
    uncond_predicted_noise = model(x, t, None)
    and not
    uncond_predicted_noise = model(x, labels, None)

    • @outliier
      @outliier  ปีที่แล้ว

      Yes correct. Good catch

  • @UnbelievableRam
    @UnbelievableRam 8 หลายเดือนก่อน

    Hi! Can you please explain why the output is getting two stitched images?

    • @outliier
      @outliier  8 หลายเดือนก่อน

      What do you mean with two stitched images?

  • @colintsang-ww6mz
    @colintsang-ww6mz ปีที่แล้ว

    Thank you very much for this very easy-to-understand implementation. I have one question: I don't understand the function def noise_images.
    Assume that we have img_{0}, img_{1}, ..., img_{T}, which are obtained from adding the noise iteratively. I understand that img{t} is given by the formula "sqrt_alpha_hat * img_{0} + sqrt_one_minus_alpha_hat * Ɛ".
    However, I don't understand the function "def noise_images(self, x, t)" in [ddpm.py].
    It return Ɛ, where Ɛ = torch.randn_like(x). So, this is just a noise signal draw directly from the normal distribution. I suppose this random noise is not related to the input image? It is becasue randn_like() returns a tensor with the same size as input x that is filled with random numbers from a normal distribution with mean 0 and variance 1
    In training, the predicted noise is compared to this Ɛ (line 80 in [ddpm.py]).
    Why we are predicting this random noise? Shouldn't we predict the noise added at time t, i.e. "img_{t} - img_{t-1}"?

    • @Laszer271
      @Laszer271 ปีที่แล้ว +1

      I had the same misconception before. It was actually explained by "AI Coffee Break with Letitia" channel in a video titled "How does Stable Diffusion work? - Latent Diffusion Models EXPLAINED".
      Basically, the model tries to predict the WHOLE noise added to the image to go from noised image to a fully denoised image in ONE STEP. Because it's a hard task to do, the model does not excel at that so at inference we denoise it iteratively, each time subtracting only a small fraction of the noise predicted by the model. In this way, the model produces much better quality samples. At least that's how I understood it :P

    • @rikki146
      @rikki146 ปีที่แล้ว

      @@Laszer271 While I understand it predicts the "whole noise", this "whole noise" is newly generated and I suppose the ground truth is (img_{t} - img_{0)).. still can't wrap my head around it.

  • @Soso65929
    @Soso65929 9 หลายเดือนก่อน

    So the process of adding noise and removing it happens in a loop

  • @anonymousperson9757
    @anonymousperson9757 ปีที่แล้ว +1

    Thank you so much for this amazing video! You mention that changing the original DDPM to a conditional model should be as simple as adding in the condition at some point during training. I was just wondering if you had any experience with using DDPM to denoise images? I was planning on conditioning the model on the input noisy data by concatenating it to yt during training. I am going to try and play around with your github code and see if I can get something to work with denoising. Wish me luck!

  • @WendaoZhao
    @WendaoZhao 6 หลายเดือนก่อน +1

    one CRAZY thing to take from this code (and video)
    GREEK LETTERS ARE CAN BE USED AS VARIABLE NAME IN PYTHON

  • @spyrosmarkesinis443
    @spyrosmarkesinis443 2 ปีที่แล้ว

    Amazing stuff!

  • @mic9657
    @mic9657 ปีที่แล้ว

    great video. please can you list the creators of the other helpful videos at 00:52? thanks

    • @outliier
      @outliier  ปีที่แล้ว

      There are from Yannick Kilcher (on the right side), the one in the lower left is from AICoffeeBreak, the one in the top right corner is the first video that comes when you google „diffusion models explained“ and I forgot the middle one sorry. But shouldnt be hard to find

  • @egoistChelly
    @egoistChelly ปีที่แล้ว

    I think your code bugs when adjust image_size?

  • @homataha5626
    @homataha5626 2 ปีที่แล้ว

    Thank you for the video.
    How can we use diffusion model for inpainting?

  • @houbenbub
    @houbenbub 2 ปีที่แล้ว

    This is GOLD

  • @kerenye955
    @kerenye955 ปีที่แล้ว

    Great video!

  • @agiengineer
    @agiengineer ปีที่แล้ว

    Can you please tell me how much time was need to train this 3000 image for 500 Epoch?

  • @rawsok
    @rawsok ปีที่แล้ว

    You do not use any LR scheduler. Is this intentional? My understanding is that EMA is a functional equivalent of LR scheduler, but then I do not see any comparison between EMA vs e.g. cosine LR scheduler. Can you elaborate more on that?

  • @maybritt-sch
    @maybritt-sch 2 ปีที่แล้ว +1

    Great videos on diffusion models, very understandable explanations! For how many hours did you train it? I tried adjusting your conditional model and train with a different dataset, but it seems to take forever :D

    • @outliier
      @outliier  2 ปีที่แล้ว +1

      Yea it took quite long. On the 3090 it trained a couple days (2-4 days I believe)

    • @maybritt-sch
      @maybritt-sch 2 ปีที่แล้ว

      @@outliier Thanks for the feedback. Ok seems like I didn't do a mistake, but only need more patience!

    • @outliier
      @outliier  2 ปีที่แล้ว

      @@maybritt-sch Yea. Let me know how it goes or if you need help

  • @nomaannafi7561
    @nomaannafi7561 ปีที่แล้ว

    How can i increase the size of the generated image here?

  • @muhammadawais2173
    @muhammadawais2173 ปีที่แล้ว

    Hi Sir, Good afternoon. i wanna run the ddpm_conditional for my ultrasound images dataset having 5 classes and all the images have equal sizes 256*256 and also images are greyscale images. but i am encountering this error. " RuntimeError: Given groups=1, weight of size [256, 1, 3, 3], expected input[4, 3, 256, 256] to have 1 channels, but got 3 channels instead". i already had a changing regarding the channel and the size

    • @outliier
      @outliier  ปีที่แล้ว +1

      Hey, can you post your code on github and give the error?

  • @andonso
    @andonso ปีที่แล้ว

    How can i increase the img size to 128 pixels square?

  • @muhammadawais2173
    @muhammadawais2173 ปีที่แล้ว

    thanks for the easiest implementation. could you plz tell us how to find FID and IS score for these images?

    • @outliier
      @outliier  ปีที่แล้ว +1

      I think you would just sample 10-50k images from the trained model and then take 10-50k images from the original dataset and then calculate the FID and IS

    • @muhammadawais2173
      @muhammadawais2173 ปีที่แล้ว

      @@outliier thanks

  • @remmaria
    @remmaria 2 ปีที่แล้ว

    Your videos are a blessing. Thank you very much!!! Have you tried using DDIM to accelerate predictions? Or any other idea to decrease the number of steps needed?

    • @outliier
      @outliier  ปีที่แล้ว +1

      I have not tried any speedups in any way. But feel free to try it out and tell me / us what works best. In the repo I do linked a fork which implements a couple additions which make the training etc. faster. You can check that out too here: github.com/tcapelle/Diffusion-Models-pytorch

    • @remmaria
      @remmaria ปีที่แล้ว

      @@outliier Thank you! I will try it for sure.

  • @khyatinkadam8032
    @khyatinkadam8032 5 หลายเดือนก่อน

    hey can we use an image as a condition

  • @marcotommasini5600
    @marcotommasini5600 2 ปีที่แล้ว

    Great video, thanks for making it. I started working with diffusion models very recently and I used you implementation as base for my model. I am currently facing a problem that the MSE loss starts very close to 1 and continues like that but varying between 1.0002 and 1.0004, for this reason the model is not training properly. Did you face any issue like this one? I am using the MNIST dataset to train the network, I wanted to first test it with some less complex dataset.

    • @justinsong3506
      @justinsong3506 ปีที่แล้ว

      I am facing similar problems. I did the experiment on CIFAR10 dataset. The mse loss starts descresing normally but at some points the loss increse to 1 and never descrese again.

  • @mcpow6614
    @mcpow6614 ปีที่แล้ว +2

    Can you do one for tensorflow too btw very good explaination

  • @4_alokk
    @4_alokk ปีที่แล้ว +1

    How did you learn do much?

    • @outliier
      @outliier  ปีที่แล้ว +1

      I read a lot of papers and watched a lot of tutorials

  • @ovrava
    @ovrava 2 ปีที่แล้ว

    Great Video,
    On what Data did you train your model again?

  • @sandravu1541
    @sandravu1541 2 ปีที่แล้ว

    great video, you got one new subscriber

  • @chemaguerra1635
    @chemaguerra1635 2 ปีที่แล้ว

    This video is priceless.

  • @zedtarwu3074
    @zedtarwu3074 2 ปีที่แล้ว

    Great video! How long did it take to train the models?

    • @outliier
      @outliier  2 ปีที่แล้ว

      About 3-4 days on an rtx 3090.

  • @김남형산업공학과한양
    @김남형산업공학과한양 2 ปีที่แล้ว

    Thank you for sharing!

  • @mathkernel5136
    @mathkernel5136 2 ปีที่แล้ว

    Hey, I am getting an error when i try to use one channel
    "RuntimeError: Given groups=1, weight of size [64, 1, 3, 3], expected input[4, 3, 64, 64] to have 1 channels, but got 3 channels instead"
    What can I do?

    • @outliier
      @outliier  2 ปีที่แล้ว

      You need to change the input and output channels in the unet code

  • @rajroy2426
    @rajroy2426 ปีที่แล้ว

    Can we use diffusion to a neural architecture for classification

    • @outliier
      @outliier  ปีที่แล้ว

      I think people have done that to. But I don’t remember the papers. But maybe just look for „diffusion models for classification“

    • @rajroy2426
      @rajroy2426 ปีที่แล้ว

      @@outliier thanks, I figured it out myself.

  • @chyldstudios
    @chyldstudios 2 ปีที่แล้ว +2

    Where is the link to the code?

    • @outliier
      @outliier  2 ปีที่แล้ว +2

      sorry I totally forgot to put the link in the description. I updated it now, but here is the link too: github.com/dome272/Diffusion-Models-pytorch

    • @chyldstudios
      @chyldstudios 2 ปีที่แล้ว

      @@outliier There are Diffusion implementations out there that are a lot longer but it also makes it harder to understand what is happening. You removing all the unnecessary parts and just focusing on the absolute minimum is much better in my opinion. Well done.

  • @鍾凱凱-y2c
    @鍾凱凱-y2c ปีที่แล้ว

    is anyone find the DDPM Unet architecture figure, I can't find it