cmds/run_RBM.py -- Training Stacked Restricted Boltzmann Machines ----------------------------------------------------------------------------------------------------------------------- Arguments     argument                meaning default value / comment --train-data training data specification required --nnet-spec --nnet-spec="d:h(1):h(2):...:h(n):s"        Eg.250:1024:1024:1024:1024:1920 required. d-input dimension; h(i)-size of the i-th hidden layers; s-number of targets --wdir working directory required     --param-output-file path to save model parameters in the PDNN format by default "": doesn't output PDNN-formatted model --cfg-output-file path to save model config by default "": doesn't output model config --kaldi-output-file path to save the Kaldi-formatted model by default "": doesn't output Kaldi-formatted model     --learning-rate learning rate for Bernoulli-Bernoulli RBM by default 0.08 --gbrbm-learning-rate learning rate for Gaussian-Bernoulli RBM by default 0.005 --epoch-number number of epochs by default 10                         --batch-size mini-batch size during training by default 128 --momentum momentum string with the format "init:final:init_epochs" E.g.: "0.5:0.9:5" by default 0.5:0.9:5, it has 3 fields: init -- initial momentum final -- final momentum init_epochs -- for how many epochs we use initial_momentum --ptr-layer-number number of layers to be trained by default train all the hidden layers     --first-layer-type type for the first layer; either "bb" (Bernoulli-Bernoulli) or "gb" (Gaussian-Bernoulli) by default "gb" Example python pdnn/cmds/run_RBM.py --train-data "train.pickle.gz,partition=600m,stream=true,random=true" \                             --nnet-spec "330:1024:1024:1024:1024:1901" \                             --wdir ./ --ptr-layer-number 4 \                             --epoch-number 10 --batch-size 128 \                             --learning-rate 0.08 --gbrbm-learning-rate 0.005 \                             --momentum 0.5:0.9:5 --first_layer_type gb \                             --param-output-file rbm.mdl Your application may not have targets, for example, unsupervised training. In this case, you still need to specify the target number (1901 in this example). However, you can specify a fake target number. The layers which will be trained are decided by --ptr-layer-number. For instance, this example only trains the first 4 hidden layers and ignores the final softmax layer.