I know Jeff Donahue worked on LSTM models using Caffe. He also gave a nice tutorial during CVPR 2015. He has a pull-request with RNN and LSTM. Update: there is a new PR by Jeff Donahue including RNN and LSTM. This PR was merged on June 2016 to master.
Answer to this question’s title: The HDF5 file should have two dataset in root, named “data” and “label”, respectively. The shape is (data amount, dimension). I’m using only one-dimension data, so I’m not sure what’s the order of channel, width, and height. Maybe it does not matter. dtype should be float or double. A sample … Read more
Here’s a nice function that converts a caffe net to a python list of dictionaries, so you can pickle it and read it anyway you want: import caffe def shai_net_to_py_readable(prototxt_filename, caffemodel_filename): net = caffe.Net(prototxt_filename, caffemodel_filename, caffe.TEST) # read the net + weights pynet_ = [] for li in xrange(len(net.layers)): # for each layer in the … Read more
The weight_decay meta parameter govern the regularization term of the neural net. During training a regularization term is added to the network’s loss to compute the backprop gradient. The weight_decay value determines how dominant this regularization term will be in the gradient computation. As a rule of thumb, the more training examples you have, the … Read more
In order to set these values in a meaningful manner, you need to have a few more bits of information regarding your data: 1. Training set size the total number of training examples you have, let’s call this quantity T. 2. Training batch size the number of training examples processed together in a single batch, … Read more
The installation of CuDNN is just copying some files. Hence to check if CuDNN is installed (and which version you have), you only need to check those files. Install CuDNN Step 1: Register an nvidia developer account and download cudnn here (about 80 MB). You might need nvcc –version to get your cuda version. Step … Read more
The problem It seems like there is indeed a conflict with the order of elements in arrays: matlab arranges the elements from the first dimension to the last (like fortran), while caffe and hdf5 stores the arrays from last dimension to first: Suppose we have X of shape nxcxhxw then the “second element of X” … Read more
I think the most straight forward way to transfer data from Matlab to caffe is via HDF5 file. First, save your data in Matlab in an HDF5 file using hdf5write. I assume your training data is stored in a variable name X of size 300-by-30 and the labels are stored in y a 300-by-1 vector: … Read more
At first glance you can see this log section divided into two: [Forward] and [Backward]. Recall that neural network training is done via forward-backward propagation: A training example (batch) is fed to the net and a forward pass outputs the current prediction. Based on this prediction a loss is computed. The loss is then derived, … Read more
1. Is there any tutorial/example on the usage of InfogainLoss layer?: A nice example can be found here: using InfogainLoss to tackle class imbalance. 2. Should the input to this layer, the class probabilities, be the output of a Softmax layer? Historically, the answer used to be YES according to Yair’s answer. The old implementation … Read more