The forum on this site is closed for new comments and posts. Continue the conversation in the new forum, and learn more here.

[SOLVED] Error in style transfer notebook

  • As I see you have lack of memory, and folks suggesting reduce batch size

    What exact environment do you use to run it?


    Comment actions Permalink

    Hi Pavel Antonenko,

    Thanks for answering me!

    My computer is an Intel(R) Celeron(R) CPU G1840.

    And I'm using Google colab

    Comment actions Permalink
  • Hi Maxime,

    This error means that the GPU your notebooks uses is running is out of memory. There are a few ways to possibly resolve this issue:

    1. Normally setting the

    BATCH_SIZE = 16             # number of images per batch

    to a smaller value should work. Alternatively, you can try reduce the dimension of your input image, too.

    2. If that fails, try cleaning GPU memory used by your Google Colab by clicking `Runtime` and `Factory reset runtime`

    3. If none of that works, we can still run the notebook using CPU but at slower training speed:

    DEVICE = torch.device('cpu')
    Comment actions Permalink
  • Hey Eric Hu,

    Thank you for your help !

    Effectively by reducing the value of Batch_Size, I can do style transfer again!
    Thanks again!

    Comment actions Permalink
  • Hi Maxime,

    Can you say how much value you reduced in Batch_Size?

    Thanks in advance!

    Comment actions Permalink
  • Maxime,

    Could you also confirm that you haven't changed anything in notebook when you experienced "CUDA out of memory" error? So the only change was using new style image, and fixing batch size, after it was suggested by Eric?

    Thank you,

    Comment actions Permalink
  • Hi Pavel,

    I confirm I only changed the style image and the batch size, that's all!

    Thank you for your help !

    Comment actions Permalink
  • Hi Nikita Ramesh,

    I changed the batch size to 11.
    I did not test the 13 to 15.
    If you want I can test it.

    Comment actions Permalink
  • how do i even change the batch size i cant find it 


    Comment actions Permalink
  • i can find batch number but not the size

    Comment actions Permalink
  • Hi j.patn,

    If you look at the Style Transfer notebook, under Global variables for training, you can change INPUT_HEIGHT and INPUT_WIDTH accordingly. Default is set as 512x256.

    Comment actions Permalink

We're here to help! We just need a little bit of information...

What system are you using?

Have you downloaded the latest version of Lens Studio?

Please download the latest version of Lens Studio. If you still run into this issue, please come back and report it!

Is this issue causing Lens Studio to crash?

What system do you run Lens Studio on?



Follow the next steps to help us solve your issue:

  • Copy and paste this text into your TerminalCommand Window
    open ~/Library/Preferences/Snap/Lens\ Studio/ %LOCALAPPDATA%\Snap\Lens Studio Copy Text
  • Press ReturnEnter to run the command. The Lens Studio folder will automatically open
  • Prepare to upload your files: zip the "Log" Folder by right-clicking and choosing "compress."
    Locate the Log.txt file right above it.

    Attach a screenshot of the issue:



What is this most relevant to?

Please enter a brief description of your issue:

Thanks for submitting this issue.

Unfortunately, it's likely due to the operating system or hardware you're using – since they don't meet the system requirements for Lens Studio.

Still, we hear you loud and clear, and are logging the issue in case there's ever a workaround we can provide!

Minimum Requirements

Operating System: Windows 10 (64 bit); MacOS 10.11+

Hardware: Minimum of Intel Core i3 2.5Ghz or AMD Phenom II 2.6Ghz with 4 GB RAM; Intel HD Graphics 4000 / Nvidia GeForce 710 / AMD Radeon HD 6450 or better; screen resolution of 1280x768 or higher

We'll try to resolve this issue as soon as possible. Thanks for letting us know about it!

Keep an eye out for a followup email from us. We may have a couple more questions for you, or we might already have a solution to offer.

Happy creating!