s = stats.cd_stats(rbm, initial_vmap, visible_units=[rbm.v], hidden_units=[rbm.h], k=k, mean_field_for_stats=[rbm.v], mean_field_for_gibbs=[rbm.v]) umap = {} for var in rbm.variables: pu = var + (learning_rate / float(mb_size)) * updaters.CDUpdater( rbm, var, s) umap[var] = pu print ">> Compiling functions..." t = trainers.MinibatchTrainer(rbm, umap) m = monitors.reconstruction_mse(s, rbm.v) m_data = s['data'][rbm.v] m_model = s['model'][rbm.v] e_data = rbm.energy(s['data']).mean() e_model = rbm.energy(s['model']).mean() # train = t.compile_function(initial_vmap, mb_size=32, monitors=[m], name='train', mode=mode) train = t.compile_function(initial_vmap, mb_size=mb_size, monitors=[m, e_data, e_model], name='train', mode=mode) evaluate = t.compile_function(initial_vmap, mb_size=mb_size, monitors=[m, m_data, m_model, e_data, e_model],
def morbrun1(f1=1, f2=1, v1=1, v2=1, kern=1): test_set_x = np.array(eval_print1).flatten(2) valid_set_x = np.array(eval_print3).flatten(2) train_set_x = np.array(eval_print2).flatten(2) train_set_x = train_set_x.reshape( np.array(eval_print2).shape[0] * batchm, kern, v1, v2) valid_set_x = valid_set_x.reshape( np.array(eval_print3).shape[0] * batchm, kern, v1, v2) test_set_x = test_set_x.reshape( np.array(eval_print1).shape[0] * batchm, kern, v1, v2) visible_maps = kern hidden_maps = neuron # 100 # 50 filter_height = f1 # 7 # 8 filter_width = f2 # 30 # 8 mb_size = batchm # 1 minibatch print ">> Constructing RBM..." fan_in = visible_maps * filter_height * filter_width """ initial_W = numpy.asarray( self.numpy_rng.uniform( low = - numpy.sqrt(3./fan_in), high = numpy.sqrt(3./fan_in), size = self.filter_shape ), dtype=theano.config.floatX) """ numpy_rng = np.random.RandomState(123) initial_W = np.asarray(numpy_rng.normal(0, 0.5 / np.sqrt(fan_in), size=(hidden_maps, visible_maps, filter_height, filter_width)), dtype=theano.config.floatX) initial_bv = np.zeros(visible_maps, dtype=theano.config.floatX) initial_bh = np.zeros(hidden_maps, dtype=theano.config.floatX) shape_info = { 'hidden_maps': hidden_maps, 'visible_maps': visible_maps, 'filter_height': filter_height, 'filter_width': filter_width, 'visible_height': v1, #45+8, 'visible_width': v2, #30, 'mb_size': mb_size } # rbms.SigmoidBinaryRBM(n_visible, n_hidden) rbm = morb.base.RBM() rbm.v = units.BinaryUnits(rbm, name='v') # visibles rbm.h = units.BinaryUnits(rbm, name='h') # hiddens rbm.W = parameters.Convolutional2DParameters(rbm, [rbm.v, rbm.h], theano.shared(value=initial_W, name='W'), name='W', shape_info=shape_info) # one bias per map (so shared across width and height): rbm.bv = parameters.SharedBiasParameters(rbm, rbm.v, 3, 2, theano.shared(value=initial_bv, name='bv'), name='bv') rbm.bh = parameters.SharedBiasParameters(rbm, rbm.h, 3, 2, theano.shared(value=initial_bh, name='bh'), name='bh') initial_vmap = {rbm.v: T.tensor4('v')} # try to calculate weight updates using CD-1 stats print ">> Constructing contrastive divergence updaters..." s = stats.cd_stats(rbm, initial_vmap, visible_units=[rbm.v], hidden_units=[rbm.h], k=5, mean_field_for_stats=[rbm.v], mean_field_for_gibbs=[rbm.v]) lr_cd = 0.001 if indk == -1: lr_cd = 0 umap = {} for var in rbm.variables: pu = var + lr_cd * updaters.CDUpdater(rbm, var, s) umap[var] = pu print ">> Compiling functions..." t = trainers.MinibatchTrainer(rbm, umap) m = monitors.reconstruction_mse(s, rbm.v) e_data = rbm.energy(s['data']).mean() e_model = rbm.energy(s['model']).mean() # train = t.compile_function(initial_vmap, mb_size=32, monitors=[m], name='train', mode=mode) train = t.compile_function(initial_vmap, mb_size=mb_size, monitors=[m, e_data, e_model], name='train', mode=mode) # TRAINING epochs = epoch_cd print ">> Training for %d epochs..." % epochs for epoch in range(epochs): monitoring_data_train = [ (cost, energy_data, energy_model) for cost, energy_data, energy_model in train({rbm.v: train_set_x}) ] mses_train, edata_train_list, emodel_train_list = zip( *monitoring_data_train) #print rbm.W.var.get_value().shape lay1w = rbm.W.var.get_value() Wl = theano.shared(lay1w) lay1bh = rbm.bh.var.get_value() bhl = theano.shared(lay1bh) #print Wl.get_value().shape return [Wl, bhl]