Henok's profile - activity

The best workaround has been the following setup: Once the network is transformed I used the call dnn::blobFromImage(i

Inception V3 retrained model incorrect predictions after using optimize_for_inference and graph_transform tools Ladies a

Inception V3 retrained model incorrect predictions after using optimize_for_inference and graph_transform tools Ladies a

I would think yes. Most plugins are written this way (not my expertise however - had to get more help from others). Basi

Here is a solution that worked for me using boost.extension extensiblity library which is long deprecated but had it at

Thanks my friend. I'm pretty much using what you have, except I need char* instead of vector<float>. Cross fingers

Thanks a bunch for your help. What you described above, option 2, is what I'm leaning towards as well. I'll be expecting

Mixing opencv 2.4.x and 3.3.x in one application (single process) Hi, thank you in advance for your help. I am in a si