2018-06-01 02:34:33 -0600 | received badge | ● Enthusiast |
2018-05-17 04:35:02 -0600 | received badge | ● Supporter (source) |
2018-05-17 04:35:01 -0600 | marked best answer | dnn openpose sample - expected image resolution In the dnn/openpose.cpp using the network definition from CMU at prototxt link the input layer shape is given as [1,3,368,368]. Does it mean that the network is expecting a square image as an input? What happens if an image is given in its original aspect ratio? The current implementation of the openpose library defines the input layer shape at runtime: prototxt link, is it possible to do something similar with opencv? |
2018-05-17 04:35:01 -0600 | received badge | ● Scholar (source) |
2018-05-17 04:15:35 -0600 | commented answer | dnn openpose sample - expected image resolution Thank you. From the blobFromImage() definition and leaving the default parameters, it looks like the image will be first |
2018-05-17 03:59:08 -0600 | edited question | dnn openpose sample - expected image resolution dnn openpose sample - expected image resolution In the dnn/openpose.cpp using the network definition from CMU at prototx |
2018-05-17 02:02:00 -0600 | received badge | ● Editor (source) |
2018-05-17 02:02:00 -0600 | edited question | dnn openpose sample - expected image resolution dnn openpose sample - expected image resolution In the dnn openpose.cpp using the network definition from CMU at prototx |
2018-05-17 02:01:38 -0600 | asked a question | dnn openpose sample - expected image resolution dnn openpose sample - expected image resolution In the dnn openpose.cpp using the network definition from CMU at prototx |
2017-01-18 22:59:01 -0600 | asked a question | OpenCV for iOS development on Windows I generally develop opencv-based applications on windows in c++ with VS and have done for a number of years. Recently I have been tasked with developing an iphone app that would require the opencv library. Is there any way to do this on windows or should I change development platform? |