Why I running into GPU out of memory when using Segnet?

3 views (last 30 days)
The segnet works well when we input 3000 224*224 RGB images(1800 for training,900 for validation and 300 for testing). However, when we input more than 3000 224*224 RGB images, the GPU out of memory from the start of the training process, even the value of MiniBatchSize is 1. My GPU is 8GB GTX1080, and the screenshot is shown as follows.
Thank you very much for the help and looking forward to the reply!

Answers (0)


Find more on Deep Learning in Parallel and in the Cloud in Help Center and File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by