Ask Your Question

Revision history [back]

click to hide/show revision 1
initial version

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?

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?

click to hide/show revision 3
retagged

updated 2018-05-17 02:34:05 -0500

berak gravatar image

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?

dnn openpose sample - expected image resolution

In the dnn openpose.cpp 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?