delay=delay, learning_rate=0.01, ) dbn_tadbn.pretrain( batchdata, plot_interval=5, static_epochs=80, save_interval=10, ae_epochs=80, all_epochs=50, batch_size=5, seqlen=seqlen, ) generated_series = dbn_tadbn.generate(batchdata, n_samples=300)[0, :, :] output = open("output/gen_" + savednamed + ".pkl", "wb") cPickle.dump([generated_series, test_data, delay, hidden_layers_sizes, invD, mu, sigma], output) output.close() output = open("trained_models/" + savednamed + ".pkl", "wb") cPickle.dump(dbn_tadbn, output) output.close() recon.main(generated_series, test_data, invD, mu, sigma, savednamed, delay, hidden_layers_sizes, plotting=True) # =============================================================================== # plt.figure() # plt.subplot(211) # plt.plot(test_data[:generated_series.shape[1]])
batchdata = numpy.asarray(test_data, dtype=theano.config.floatX) delay = 0 numpy_rng = numpy.random.RandomState(123) n_dim = [test_data.shape[1]] dbn_tadbn = TADBN(numpy_rng=numpy_rng, n_ins=[n_dim], hidden_layers_sizes=[100], sparse=0.0, delay=delay, learning_rate=0.01) dbn_tadbn.pretrain(batchdata, plot_interval=5, static_epochs=50, save_interval=10, ae_epochs=0, all_epochs=0, batch_size=5) up = dbn_tadbn.propup(batchdata, static=True) up = np.array(up) print up generated_series = dbn_tadbn.generate(batchdata, n_samples=40) plt.figure() plt.subplot(211) plt.plot(test_data[:generated_series.shape[1]]) plt.subplot(212) plt.plot(generated_series[0]) plt.show()