-
Notifications
You must be signed in to change notification settings - Fork 27
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
using faster rcnn model #8
Comments
Hi Michael,
What phone are you using? It could be memory. Can you post a console log? I just tried that model on my iPhone 6s and it ran without crashing, although admittedly, it wasn’t anywhere near real-time; I was only processing a frame every 24 seconds or so. I will probably remove that model from the next push for this reason. There are others in the Tensorflow Model Zoo <https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md> that should perform better and though I haven’t tested them all you should be able to use any of the models that give boxes.
… On Jun 5, 2018, at 5:38 AM, Michael Ben ami ***@***.***> wrote:
Hi. Thanks for sharing your repo.
I try to use the faster rcnn model
I use
NSString *model = @"op_inference_graph_rcnn";
in the TensorflowGraph.mm file
but when u load the app its crash when its try to detect
you know what can cause this?
Thanks!
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub <#8>, or mute the thread <https://github.com/notifications/unsubscribe-auth/ALvHeRrCkh66Utp4PyeLwLmy6u9jPR5qks5t5nvfgaJpZM4Uavhj>.
|
I have iPhone 6.. |
Hi @csharpseattle when I try to replace the model. I got an error:
on iPhone 6 iOS 11.3.1 Build tensorflow iOS comand: by the way.. with tensorflow 1.5 it's working (not so real time but working ) |
I've seen that when I have built the iOS Tensorflow libs and forgotten to set I stayed on |
Another thing to try is to use the -g flag to |
Hi. Thanks for sharing your repo.
I try to use the faster rcnn model
I use
in the
TensorflowGraph.mm
filebut when u load the app its crash when its try to detect
you know what can cause this?
Thanks!
The text was updated successfully, but these errors were encountered: