2016-04-27 11:00:29 -0600 | received badge | ● Editor (source) |
2016-04-27 10:58:50 -0600 | commented question | Concatenate failing check for #axes? Oops, you're right. My mind completely blanked - this is a Caffe question. Revised to reflect a parallel path I'm pursuing with OpenCV. |
2016-04-27 10:52:37 -0600 | asked a question | Concatenate failing check for #axes? Using OpenCV, I am trying to classify an image. The neural network I used to train it takes in an image and hand-crafted features and late fuses them at the fully-connected layers before classification. I know the image classification only pipeline works properly because I was successfully able to take a trained network and apply it to just images. As a dummy example... this doesn't seem to run The prototxt file looks like below. I want to reiterate that I trained using the prototxt file and modified the top and bottom to create a deploy.prototxt so I know that these layers work together when to train a caffe model. I am getting this error: It seems related to the size of the inputs, so I've tried modifying the shape of featBlobMat to be 1x20 and 20x1, and changed the input_dims in all possible ways. [1 1 1 20], [1 1 20 1], [1 20], [20 1], and nothing seems to work. Any pointers? EDIT: Accidentally posted something meant for the Caffe question board... Oops! Revised. |