Open ghost opened 6 years ago
@shobitkishore Can you provide your system specs, GPU model?
I'm running it on AWS EC2 instance - g3.4xlarge (122 GB memory)
@shobitkishore did you managed to increase the speed of the inference? I'm facing the same problem on a google cloud vm -> see comment here https://github.com/matterport/Mask_RCNN/issues/985#issuecomment-466283995
Hi everyone! Thanks for the awesome work and resources. I have been trying to use Matterport's Mask_RCNN for a tiny project. I'm running this on GPU but model.detect is taking upwards of 30 seconds to yield results. Input images are larger than 500 x 500 x 3 and usually ~ 800 x 800 x 3. Has anyone else experienced this?