cmds/run_Extract_Feats.py  --  Feature Extraction with a Trained Model
----------------------------------------------------------------------------------------------------------------------

Arguments

argument
meaning
default value
--data        
input data specification required                    
--nnet-param path to model parameters required
--nnet-cfg
path to model config
required
--output-file
path to save the extracted features into the pickle format
required
--layer-index    
the index of the layer from which features are generated. Layers are 0-based indexed, starting from the first hidden layer. Set it to "-1" when you want to do classification. That is, we extract features from the final softmax layer.
required
--batch-size the size of mini-batches by which data are fed into the network required


Example

python cmds/run_Extract_Feats.py --data "test.pickle.gz" \
                                 --nnet-param dnn.param --nnet-cfg dnn.cfg \
                                 --output-file "dnn.classify.pickle.gz" --layer-index -1 \
                                 --batch-size 100