Closed

RuntimeError: CUDA out of memory. -- 2

I am trying to use Detectron2 and almost done. Detection is going well now but training gets this Error:

RuntimeError: CUDA out of memory. Tried to allocate 12.00 MiB (GPU 0; 1.95 GiB total capacity; 1.30 GiB already allocated; 1.56 MiB free; 1.34 GiB reserved in total by PyTorch)

Environment:

Ubuntu 18.04

Cuda 10.1.243

Conda ( python 3.7.6)

PyTorch 1.5.0a0+e70c288 (compiled from source)

Detectron2 (latest version)

Anyone can solve it? Please bid with one sentence showing your idea.

I want to choose one and share my pc for him using AnyDesk or TeamView.

Thanks.

Skills: CUDA, Python, Pytorch, Ubuntu, Machine Learning (ML)

See more: runtimeerror: cuda out of memory fastai, runtimeerror: cuda out of memory. tried to allocate, runtimeerror: cuda out of memory colab, cuda out of memory. tried to allocate pytorch, cuda out of memory pytorch, runtimeerror: cuda out of memory google colab, runtimeerror: cuda error: out of memory pytorch, runtimeerror cuda out of memory. tried to allocate pytorch, inventory management 2 dinein takeaway or delivery orders 3 live onmap tracking for customers deliveries, sze3 c code canoak version 2, 127.0 0.1 apache 2.4 17 win32 openssl 1.0 2d php 5.5 30, academic ielts version 2.1, android version 4.1.2, android version 4.2.2, error creating control radajaxloadingpanel1failed to create designer telerik web ui radajaxloadingpanel telerik web ui version 2, facebook password finder 2.6 5, freelancer 2 latest game version, freelancer app version 2.5, freelancer bootstrap version 2, freelancer patch 2.7 6

About the Employer:
( 2 reviews ) Shenyang, China

Project ID: #24491970

9 freelancers are bidding on average $114 for this job

kamalchhirang

i never used Detectorn2. But try to use lower batch size/image size or buy a GPU with more vRAM. I use EfficientDet

$125 USD in 7 days
(26 Reviews)
5.5
mza5ab8dc9be9a8c

Note: I can help you to fix this error. This work is really matching with my experience and I have done a lot of projects like this. Please let me talk further through chat so we will move forward and I will give you a More

$100 USD in 1 day
(58 Reviews)
5.4
GreenTower

I can help you to fix this issue, it's due to out of memory. It need to modify some code change to fix this one. I had faced one issue similar to this, so I can help you to fix.

$100 USD in 1 day
(7 Reviews)
3.1
eduardhal

Hi, I have ever met similar problem on my work and have resolved it. feel free to contact me any time Eduard

$100 USD in 1 day
(2 Reviews)
2.7
kgm1995

Special Offer! Working at minimum price for my first 10 projects on freelancer. Hi, I have trained several models using detectron2. I have even deployed them for clients. I understand the working of detectron2. Durin More

$100 USD in 7 days
(2 Reviews)
1.9
rehanalan

Hi I have 3 years of experience in linux ubuntu os,cuda,GPU , troubleshootinh I can solve your issue lets discuss more about it With Regards Rehan

$150 USD in 1 day
(5 Reviews)
1.6
EduwardDementyev

I am expert at Machine Learning and Deep Learning. I have experiences in solving this error. I am good at Tensorflow, Keras, PyTorch and openCV.

$150 USD in 1 day
(1 Review)
1.1
zeucindia

The error, which you has provided is shown, because you ran out of memory on your GPU. A way to solve it is to reduce the batch size until the code will run without this error. When perform validation not training, the More

$100 USD in 7 days
(0 Reviews)
0.0
abhisheksingh10

It's not able to allocate enough space in the GPU required to run your program. Idea is to feed fewer samples in batch during training to GPU :) I have worked as a research scholar in the field of machine learning/dee More

$100 USD in 1 day
(0 Reviews)
0.0