https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/VGG-based-Face-Embeddings-takes-a-long-time/m-p/704546#M5638 <P>@gauravmoon Hey, how did you make it work. While compiling, I am getting this error:</P><P>&nbsp;</P>"mvNCCompile VGG_FACE_deploy.prototxt -w VGG_FACE.caffemodel -s 12"<P>&nbsp;</P>[Error 20] Toolkit Error: Input Layer must be in an input_shape construct.<P>&nbsp;</P><P>Can you please guide me with this. Thanks :)</P> Fri, 29 Dec 2017 17:20:18 GMT idata 2017-12-29T17:20:18Z https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/VGG-based-Face-Embeddings-takes-a-long-time/m-p/704544#M5636 <P>I am trying to run this network for face recognition. <A href="http://www.robots.ox.ac.uk/~vgg/software/vgg_face/">http://www.robots.ox.ac.uk/~vgg/software/vgg_face/</A></P><P>&nbsp;</P>The inference time is 750ms which seems too high. What can be the issue here?<P>&nbsp;</P><CODE>Network Summary Detailed Per Layer Profile Bandwidth time # Name MFLOPs (MB/s) (ms) =============================================================================================================================== 0 conv1_1 173.4 304.2 8.510 1 conv1_2 3699.4 663.1 83.248 2 pool1 3.2 832.7 7.356 3 conv2_1 1849.7 421.7 33.017 4 conv2_2 3699.4 474.0 58.752 5 pool2 1.6 923.1 3.318 6 conv3_1 1849.7 171.7 43.405 7 conv3_2 3699.4 177.9 83.779 8 conv3_3 3699.4 178.0 83.765 9 pool3 0.8 932.3 1.643 10 conv4_1 1849.7 136.6 41.684 11 conv4_2 3699.4 172.4 66.082 12 conv4_3 3699.4 172.6 65.987 13 pool4 0.4 926.7 0.826 14 conv5_1 924.8 317.1 19.627 15 conv5_2 924.8 316.9 19.634 16 conv5_3 924.8 314.6 19.780 17 pool5 0.1 880.9 0.217 18 fc6 205.5 2157.2 90.881 19 fc7 33.6 2138.0 14.971 20 fc8 21.5 2106.5 9.728 21 prob 0.0 10.9 0.458 ------------------------------------------------------------------------------------------------------------------------------- Total inference time 756.67 ------------------------------------------------------------------------------------------------------------------------------- </CODE> Sun, 19 Nov 2017 02:32:49 GMT https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/VGG-based-Face-Embeddings-takes-a-long-time/m-p/704544#M5636 idata 2017-11-19T02:32:49Z https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/VGG-based-Face-Embeddings-takes-a-long-time/m-p/704545#M5637 <P>@AshwinVijayakumar can you assist here? Why is it taking too long</P> Mon, 20 Nov 2017 14:30:04 GMT https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/VGG-based-Face-Embeddings-takes-a-long-time/m-p/704545#M5637 idata 2017-11-20T14:30:04Z https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/VGG-based-Face-Embeddings-takes-a-long-time/m-p/704546#M5638 <P>@gauravmoon Hey, how did you make it work. While compiling, I am getting this error:</P><P>&nbsp;</P>"mvNCCompile VGG_FACE_deploy.prototxt -w VGG_FACE.caffemodel -s 12"<P>&nbsp;</P>[Error 20] Toolkit Error: Input Layer must be in an input_shape construct.<P>&nbsp;</P><P>Can you please guide me with this. Thanks :)</P> Fri, 29 Dec 2017 17:20:18 GMT https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/VGG-based-Face-Embeddings-takes-a-long-time/m-p/704546#M5638 idata 2017-12-29T17:20:18Z https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/VGG-based-Face-Embeddings-takes-a-long-time/m-p/704547#M5639 <P>@sri_mash Please visit <A href="https://movidius.github.io/ncsdk/Caffe.html">https://movidius.github.io/ncsdk/Caffe.html</A> and take notice that there is a specific input format that we support. The input for the prototxt file should be in this format: </P><P>&nbsp;</P>name: "GoogleNet" <P>&nbsp;</P>input: "data"<P>&nbsp;</P> input_shape <P>&nbsp;</P>{ dim:1 dim:3 dim:224 dim:224 } Mon, 01 Jan 2018 06:34:01 GMT https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/VGG-based-Face-Embeddings-takes-a-long-time/m-p/704547#M5639 idata 2018-01-01T06:34:01Z https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/VGG-based-Face-Embeddings-takes-a-long-time/m-p/704548#M5640 <P>@Tome_at_Intel Thanks a lot! :)</P> Tue, 02 Jan 2018 15:38:33 GMT https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/VGG-based-Face-Embeddings-takes-a-long-time/m-p/704548#M5640 idata 2018-01-02T15:38:33Z