search

jzbontar / mc-cnn

Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches
BSD 2-Clause "Simplified" License
707 stars 232 forks source link

About the memory of GPU for running the data set #38

Open SuperYuYi opened 7 years ago

SuperYuYi commented 7 years ago

Thank you for sharing this code. I have a question about the memory of NVIDIA GPU for processing Middlebury data set. Can we use a NVIDIA GPU with memory of 11G (like GeForce 1080Ti) to run the Middlebury data set? Will this memory capacity end up with out-of-memory exception? or just make the runtime slower?

Thanks so much!

GoodStudyDayUpUp commented 7 years ago

Hi, have you tried the middleburry data? Do you also have the problem that the left several columns of 'disp.bin' are totally white?

TrackingBird commented 6 years ago

@GoodStudyDayUpUp I have met the same problem. Have you ever finished it？ Thanks.

rain2050 commented 5 years ago

@TrackingBird Hello, my Middlebury dataset can't train the network, and when I run the Middlebury dataset error rate, I also get an error. Do you know what's going on?