SANSA AWS Informal Settlements in South Africa by #ZindiWeekendz
'%3e%3cpath fill='%23001489' d='M0 0v6h9V0z'/%3e%3cpath fill='%23e03c31' d='M0 0v3h9V0z'/%3e%3cg stroke='%23fff' stroke-width='2'%3e%3cpath id='d' d='m0 0 4.5 3L0 6m4.5-3H9'/%3e%3cuse xlink:href='%23b' stroke='%23ffb81c' clip-path='url(%23c)'/%3e%3c/g%3e%3cuse xlink:href='%23d' fill='none' stroke='%23007749' stroke-width='1.2'/%3e%3c/g%3e%3c/svg%3e)
Helping South Africa
$1 000 USD
Completed (almost 6 years ago)
Classification
Earth Observation
182 joined
77 active
Start
Jun 12, 20
Close
Jun 14, 20
Reveal
Jun 14, 20
'%3e%3ccircle r='20' fill='%23008'/%3e%3ccircle r='17.5' fill='%23fff'/%3e%3ccircle r='3.5' fill='%23008'/%3e%3cg id='d'%3e%3cg id='c'%3e%3cg id='b'%3e%3cg id='a' fill='%23008'%3e%3ccircle r='.875' transform='rotate(7.5 -8.75 133.5)'/%3e%3cpath d='M0 17.5.6 7 0 2l-.6 5L0 17.5z'/%3e%3c/g%3e%3cuse xlink:href='%23a' transform='rotate(15)'/%3e%3c/g%3e%3cuse xlink:href='%23b' transform='rotate(30)'/%3e%3c/g%3e%3cuse xlink:href='%23c' transform='rotate(60)'/%3e%3c/g%3e%3cuse xlink:href='%23d' transform='rotate(120)'/%3e%3cuse xlink:href='%23d' transform='rotate(-120)'/%3e%3c/g%3e%3c/svg%3e){kind=small}
CUDA out of memory
Data · 13 Jun 2020, 02:28 · 1
I tried to run the densenet model which result in an error.
RuntimeError: CUDA out of memory. Tried to allocate 60.00 MiB (GPU 0; 11.17 GiB total capacity; 10.64 GiB already allocated; 51.31 MiB free; 10.78 GiB reserved in total by PyTorch)
Then I tried using the previous model resnet which was successfully working but it also started showing the same result.
This happens when your GPU ram is full. Restarting the kernel should empty the GPU ram (you can check with '!nvidia-smi' in Jupyter). Then to avoid the error, the easiest way is to use a smaller batch size, especially when training a large model like densenet. I hope that helps :)