11478 2017-05-08 12:51:49 +0000 Move caffe from meta-refkit-extra to meta-refkit 2017-06-29 09:43:04 +0000 1 1 6 Yocto Project Subprojects IoT Reference OS Kit intel-iot-refkit-profile-computer-vision 2.4 x86 x86_64 RESOLVED FIXED Medium enhancement 2.4 M1 1 ismo.puustinen ismo.puustinen matti-pekka.sivosuo --- --- Don't know oldest_to_newest 73113 0 ismo.puustinen 2017-05-08 12:51:49 +0000 Make Caffe a first-class citizen in Refkit. Work with the recipes (Caffe + its dependencies) and make them nicer. Separate Caffe-based demos from Caffe itself. 73466 1 ismo.puustinen 2017-05-24 11:28:26 +0000 One way forward might be to enable OpenCV DNN module. It can read Caffe models and implements a subset of Caffe layers. http://docs.opencv.org/trunk/d5/de7/tutorial_dnn_googlenet.html http://docs.opencv.org/3.1.0/d6/d0f/group__dnn.html DNN module needs to be tried out in practice first and possibly benchmarked against real Caffe. If it works well enough, it might be enough to solve the Caffe classification issues for most of the users. Real Caffe could then be used only for complex or non-standard models and non-cv use cases, and might continue living in meta-refkit-extra. 73670 2 ismo.puustinen 2017-06-05 08:15:52 +0000 DNN build fix is in meta-openembedded master-next now. https://patchwork.openembedded.org/patch/140142/ 74139 3 ismo.puustinen 2017-06-14 12:02:01 +0000 PR for this feature: https://github.com/intel/intel-iot-refkit/pull/186 74631 4 ismo.puustinen 2017-06-29 09:43:04 +0000 The DNN module is now enabled and a test is added to Refkit. The test downloads an ImageNet Caffe model (the same used in the meta-refkit-extra Caffe demos) and uses it to classify an image without enabling meta-refkit-extra layer. In the future the caffe recipe could be changed to use the caffe-reference-bvlc recipe for downloading the test data.