Mark Strefford

icon indicating a website link timelapsai.com icon indicating an email [email protected]

icon company Timelaps AI icon location Cheshire, UK icon location Technology Leadership, Strategy and Delivery | Lead Architect | AI and Data Strategy | Conference Speaker | Aspiring Racing Driver Crypto

Results 7 comments of Mark Strefford

A run error occurred after modifying the network layer！

Yes it seems that the GPU doesn’t have enough memory for the new network architecture you are using. > > On 28 Dec 2019, at 06:52, 15732031137 wrote: > >...

Update for Pytorch 1.7

Thanks for this @Clefspear99 @tamarott one of the issues with the original code is the version of Torch doesn't work on more recent GPUs, such as the RTX30xx series. I...

Update for Pytorch 1.7

For those that want a version that works on more recent Pytorch versions (with the caveats above around not guaranteeing the exact same results), you can find it here https://github.com/Clefspear99/SinGAN...

RuntimeError: CUDA out of memory

You’re GPU doesn’t have enough memory for this, so either train a smaller image or move to a bigger GPU. > On 16 Dec 2019, at 04:43, Ahmadxon wrote: >...

CMake error - Couldn't find CUDA library root

Have you installed cudnn? And is CUDA_HOME set in your environment?

How do you generate samples on a trained sagemaker model?

Let me look into it. How urgent is this @NoahDolev?

Windows 10 w/ VS2019 and torch cpu only

Thanks for this. There's a couple of changes for me: 1) The file vcvars64.bat was at a different location (I'm not using the Enterprise version of VS) 2) I used...