from util import dnn_load_data import numpy as np for tv in ['train', 'valid']: X1 = dnn_load_data('../feature/%s1M.fbank'%tv) X2 = dnn_load_data('../feature/%s1M.mfcc'%tv) X = np.concatenate((X1, X2), axis=1) print "Save ../feature/%s1M.fm" %tv np.savetxt('../feature/%s1M.fm'%tv, X, fmt='%7f')
import numpy as np from util import dnn_load_data, dnn_save_data from sklearn.preprocessing import StandardScaler import os if __name__ == "__main__": data_dir = '../feature' feature = 'fbank7' filename = os.path.join(data_dir, 'train.%s'%feature) X = dnn_load_data(filename) print "Standard Normalization..." scaler = StandardScaler().fit(X) X = scaler.transform(X) filename = os.path.join(data_dir, 'train.%s.norm'%feature) dnn_save_data(filename, X) for t in ["test", 'test.old']: filename = os.path.join(data_dir, '%s.%s'%(t, feature) ) X = dnn_load_data(filename) X = scaler.transform(X) filename = os.path.join(data_dir, '%s.%s.norm'%(t, feature) ) dnn_save_data(filename, X)
frame = FRAME() fs = frame_str.split("_") frame.input = frame_str frame.ss = fs[0] + "_" + fs[1] frame.id = int(fs[2]) frame.index = index return frame fm = 5 # number of frame to merge feature_name = 'fbank' for t in ['train', 'test', 'test.old']: feature_filename = '../feature/%s.%s' % (t, feature_name) X = dnn_load_data(feature_filename) (N, D) = X.shape x_zero = np.zeros(X[0].shape) y_zero = 'zero' frame_filename = '../frame/%s.frame' % t print "Load %s" % frame_filename input_list = np.loadtxt(frame_filename, dtype='str') N = len(input_list) frame_list = [] for i in range(N): frame = make_frame(input_list[i], i) frame_list.append(frame)
str(opts.rmsprop_alpha) ) opts.model_dir = '../model/%s' % parameters # load model model_filename = os.path.join(opts.model_dir, 'epoch%d.model' % opts.epoch) dnn = dnn_load_model(model_filename) # output layer = 3 fv_out = '%s.%s_nn%s_%s_drop%s.L%d' \ %(opts.feature, \ opts.data_size, \ "_".join( str(h) for h in opts.hidden), \ opts.label_type, \ opts.dropout_prob, \ layer) output_dir = '../../hw2/hw1_feature' for t in ["train", "test", "test.old"]: filename = '../feature/%s.%s' % (t, opts.feature) X = dnn_load_data(filename) print "Extract dnn feature..." feature = dnn.get_hidden_feature(X, layer) output_filename = os.path.join(output_dir, '%s.%s' % (t, fv_out)) dnn_save_data(output_filename, feature)
opts.update_grad, \ str(opts.rmsprop_alpha) ) if( opts.pretrain ): parameters += '_RBMpretrain' if( opts.data_size == 'all' ): train_filename = '../feature/train.%s' %(opts.feature) train_labelname = '../label/train.%s.index' %(opts.label_type) else: train_filename = '../feature/train%s.%s' %(opts.data_size, opts.feature) train_labelname = '../label/train%s.%s.index' %(opts.data_size, opts.label_type) X_train, Y_train = dnn_load_data(train_filename, train_labelname, opts.N_class) if( opts.data_size == 'all' ): valid_filename = '../feature/valid1M.%s' %(opts.feature) valid_labelname = '../label/valid1M.%s.index' %(opts.label_type) else: valid_filename = '../feature/valid%s.%s' %(opts.data_size, opts.feature) valid_labelname = '../label/valid%s.%s.index' %(opts.data_size, opts.label_type) X_valid, Y_valid = dnn_load_data(valid_filename, valid_labelname, opts.N_class) (N_data, N_dim) = X_train.shape opts.structure = [N_dim] + opts.hidden + [opts.N_class]
str(opts.momentum), \ str(opts.weight_decay), \ str(opts.dropout_prob), \ opts.update_grad, \ str(opts.rmsprop_alpha) ) opts.model_dir = '../model/%s' %parameters # load model model_filename = os.path.join(opts.model_dir, 'epoch%d.model'%epoch) dnn = dnn_load_model(model_filename) # testing (old data) test_filename = '../feature/test.old.%s' %opts.feature X_test = dnn_load_data(test_filename) output_filename = '../pred/%s_epoch%d.old.csv' %(parameters, epoch) Y_pred = dnn.predict(X_test) dnn_save_label('../frame/test.old.frame', output_filename, Y_pred, opts.label_type) # testing (final data) test_filename = '../feature/test.%s' %opts.feature X_test = dnn_load_data(test_filename) output_filename = '../pred/%s_epoch%d.csv' %(parameters, epoch) Y_pred = dnn.predict(X_test)