RuntimeError: CUDA out of memory.

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)


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.


Skills: Python, Pytorch, CUDA, Ubuntu

See more: code using python 3 on ubuntu for computer security, code using python 3, diffiehellman key exchange code using python 3 on ubuntu, python 3, flask python 3, google app engine python 3, python 3 online, python 3 tutorial for beginners, scipy python 3, freelance python 3, looking for python 2.7 6 python 3833 gtk warn, new to python programming want ide for python 3.5, practical programming an introduction to computer science using python 3, programming in python 3, programming in python 3 pdf, python 3.4 online interpreter, python 3.5 freelance, python 3 object oriented programming, python 3 object oriented programming pdf, python web programming assignment 5

About the Employer:
( 2 reviews ) Shenyang, China

Project ID: #24491658

4 freelancers are bidding on average $106 for this job


Hi. I am an expert in the field of Python(PyTorch), Cuda, Machine Learning and Deep Learning. I have pretty much knowledge as not only practical but also theoretical for Machine Learning, very familiar with Computer More

$100 USD in 2 days
(8 Reviews)

Hi there, This problem may be caused by your GPU memory isn't enough for distribute parameters of the network. Have you tried to reduce batch_size ?

$100 USD in 1 day
(3 Reviews)

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)

hi the problem can be tackled mainly by reducing the batch size or the size of images being used. Resizing images to same size or setting it in config may solve this.

$75 USD in 2 days
(2 Reviews)