Closed lucbettaieb closed 7 years ago
Copying the images, while inefficient, is not to blame for the holdup.
tensorflow::Status run_status = g_tf_session_ptr_->Run({{InputName, input_image}}, {OutputName}, {}, &finalOutput);
is the culprit
Seems to be that running BIG tensors through the graph built using BIG tensors (1x307200) from a 640x480 video frame is bad.
It works, but is just slow!
I should now get reduced size training data and then use the image downsize node to run things nicely.
Also, seems as if I can't run images through the network that aren't of the same size...?
No, if you use the published weights of the Inception model, you can't change the size of the input image.
You could try tensorboard to check the running graph.
I'm going to test my hypothesis because I'm getting errors that seem to be indicating what I'm thinking o be correct. After retraining the network on 640x480 images, it will error if I try to run a different size image through the graph.
Stopped using TF
When running a graph, the C++ code runs very slowly. This must be due to inefficient code somewhere in the graph running area.
[x] Compile for release and see if that speeds things up