sigfrid696

@nietras hi nietras ed everyone! New v7 functions are capable of giving back more than 10 algos... The old functions accepted a parameter to filter size but the new don't......

With the aim of keeping alive CNTK project, I made in the last months some more changes to the original repo. I think this could be the place to further...

I admit, I'm not so expert using git-hub. I would continue with the fork I did from your master I believe...the same of the previous PR

I updated to the latest `nietras/master`, and made PR from my branch frcnn-gpu.

Hello, I tried you solution, but if I move CloseWhenReady() in main function at the end, then the list is always empty after the call to GetImages method. Then I...

> CloseWhenReady is used to tell the library to finish whatever it is doing and then quit. It can be used to hold the main thread off until the requests...

> The point with asynchronous programming is not to wait. You get the result inside the lambda, and while the request is pending, your threads are free to do away...

I did some tests after porting the implementation to my library...the implementation seems ok because it produces the same results as obtained by the proposal layer done fully on CPU....

Sorry I accidentally closed the issue...After doing some tests I found that only gpu nms processing of the proposal layer makes the overall process faster, the other parts of the...

Ok , thanks for the reply. After studying a bit the code, it doesn't seem related to the fact that is not an optimized algorithm. Probably some parts of the...