Autoencoders Made Easy! (with Convolutional Autoencoder)

Поділитися
Вставка
  • Опубліковано 29 лис 2024

КОМЕНТАРІ • 48

  • @ThefamousMrcroissant
    @ThefamousMrcroissant 3 роки тому +10

    This is an unusually well structured video. Not only do you go over the "what and why?", but you also provide a demonstration, visualisation and notebook file in case you wish to look it up yourself. Excellent work.

  • @sabazainab1524
    @sabazainab1524 3 роки тому +2

    Great content. Watched your video just for the sake of Convolutional Autoencoders but you didn't define it clearly and not made any video further on it. Btw you teach amazingly in a very easy way. Love from Pk

  • @pranavgupta7518
    @pranavgupta7518 3 роки тому +3

    Hi, you mentioned Autoencoders as Jack of Trades, could you give an example of feature selection or dimensionality reduction algorithm which outshines Autoencoders?
    Thank you

  • @kaveh3480
    @kaveh3480 2 роки тому +1

    Love the way you explain. Thanks!

  • @theankitkurmi
    @theankitkurmi 4 роки тому +3

    we can surely upscale the generated cat images using super resolution techniques. great video

    • @NormalizedNerd
      @NormalizedNerd  4 роки тому +1

      Yes of course! Just remember the super resolution won't produce the exact image.

  • @new_beginning2571
    @new_beginning2571 3 роки тому +2

    you said It is self-supervised learning, but can i used Annotated data with this CNN autoencoder?
    I have to do sematic segmentation, and the output is also an image.
    input are image and few sensor data. and i have annotated the features in the image.
    What model do you think i should use.?

    • @NormalizedNerd
      @NormalizedNerd  3 роки тому

      As far as I know, autoencoders can't be used for annotated data.

  • @zakiamahmoudi5753
    @zakiamahmoudi5753 3 роки тому

    thank you for this 'rich' and amazing video.

  • @Waterlmelon
    @Waterlmelon 2 роки тому

    Thanks for this great video!

  • @ellisiverdavid7978
    @ellisiverdavid7978 4 роки тому +1

    I’m just wondering-after we obtained the most important features from the bottleneck of our trained neural network, is it possible to implement the denoising capability of the autoencoder to a live feed video that is somewhat highly correlated to the training images? For instance, CCTVs?
    Will this be better, or even recommended, instead of using traditional denoising filters of OpenCV for real-time videos?
    I’d love to learn more from your expertise and advices as I explore this topic further.
    Anyway, thank you so much for the insightful explanation and demo by the way! This is undoubtedly one of the most in-depth and easy-to-digest explanations out there. I do like your high energy and enthusiasm, and also the fresh and flexible implementation using the cat dataset instead of the usual MNIST dataset. Great work! 💯
    Subscribed :)

    • @NormalizedNerd
      @NormalizedNerd  4 роки тому +1

      Thanks for subscribing! Denoising video with CNN in real-time is still a big challenge. I'm not an expert; however, I guess it's better to go for a GAN instead of using an autoencoder for this purpose.

  • @gopikasnair2813
    @gopikasnair2813 4 роки тому +2

    please do a video on calculating mse and anomaliy detetction

  • @kaveeshasenanayake5399
    @kaveeshasenanayake5399 3 роки тому

    Very well explained. Thank you so much.

  • @pranayreddy2190
    @pranayreddy2190 4 роки тому

    Very well explained!

  • @boira_dani
    @boira_dani 3 роки тому

    Great video and explanation, thank you! :)

  • @fpgamachine
    @fpgamachine 3 роки тому

    Excellent, thanks!

  • @mehdiorouji6282
    @mehdiorouji6282 3 роки тому

    Thanks for the tutorial! You mentioned conv2Dtranspose is the same as conv2D if the padding is the same. If so why you are you using conv2Dtranspose? And why the last layer of CAE is Conv2D and not Conv2Dtranspose?

  • @shriyanarayan6619
    @shriyanarayan6619 3 роки тому

    Sir is there anyway to implement this to moving objects like movement is 360

  • @kurmapuhymavathi2089
    @kurmapuhymavathi2089 3 роки тому +1

    how to access the dataset?

  • @yashmore3525
    @yashmore3525 4 роки тому +3

    Hii this is great! Can you also explain variational autoencoders!!?

  • @DanielRobertoCassar
    @DanielRobertoCassar 4 роки тому

    Great video, thanks!

  • @moviebuzz7266
    @moviebuzz7266 3 роки тому

    Well done bro👌

  • @aarushigoyal5833
    @aarushigoyal5833 4 роки тому

    Thank You So Much!!

  • @pranavkushare5109
    @pranavkushare5109 3 роки тому

    Could you please tell me which are better models than autoencoders for the same task ?

    • @NormalizedNerd
      @NormalizedNerd  3 роки тому

      For example, we can perform noise reduction using GANs instead of autoencoders.

  • @159_vivekpatel5
    @159_vivekpatel5 3 роки тому

    Thonks ❤️

  • @moumitamoitra1829
    @moumitamoitra1829 3 роки тому

    suppose i have 200 training image then can I use autoencoder?

    • @NormalizedNerd
      @NormalizedNerd  3 роки тому +1

      200 is really a low number. You can try data augmentation.

    • @moumitamoitra1829
      @moumitamoitra1829 3 роки тому

      @@NormalizedNerd thank you for your reply

    • @moumitamoitra1829
      @moumitamoitra1829 3 роки тому

      Is there any other technique to work with small number of images?

  • @zebcode
    @zebcode 3 роки тому

    It would have been much better if you'd built the network as you went instead of just showing to finished article. Seeing mistakes is often more valuable.

  • @belhafsiabdeldjalil5739
    @belhafsiabdeldjalil5739 3 роки тому

    I want to adapt your code on my 79by79 images

    • @NormalizedNerd
      @NormalizedNerd  3 роки тому +1

      Feel free to use the code. If you are gonna publish/distribute just mention my channel's name :)

    • @belhafsiabdeldjalil5739
      @belhafsiabdeldjalil5739 3 роки тому

      @@NormalizedNerd I'll proudly do, thank you sir !
      but I have a probleme dealing with odd numbers !

    • @NormalizedNerd
      @NormalizedNerd  3 роки тому +1

      The easiest way to resolve this is to change the dimension of your images to an even number (try to pick a number that has many factors) greater than 79. Remember, you'll need to set the number of conv. layers and dimension of conv. layers accordingly.

    • @belhafsiabdeldjalil5739
      @belhafsiabdeldjalil5739 3 роки тому

      @@NormalizedNerd and that's what I did, down to 72 !
      please, one more question :
      The accuracy in this case, what does it mean?, we're not in a classification problem !

    • @NormalizedNerd
      @NormalizedNerd  3 роки тому +1

      @@belhafsiabdeldjalil5739 We don't use accuracy here. We use loss. It's calculated bases on the difference in pixel values between original image and generated image.

  • @hejarshahabi114
    @hejarshahabi114 4 роки тому

    For a sec I thought an IS member is on youtube, for god sake take off that hair. anyway, thanks for the video it is helpful.

  • @redfruit1993z
    @redfruit1993z 3 роки тому

    omg balance your sound volume! that thing is exploding my hear drums more than Piper Perry on couch with 5 blacks.