def build_CompressModel(): print 'STEP 1 start...' dataset = Nikkei(dataset_type=params['experiment_type'], brandcode=params['STEP3']['brandcode']) # pdb.set_trace() index = T.lscalar() # index to a [mini]batch x = T.matrix('x') # the data is presented as rasterized images if params['STEP1']['model'] == 'rbm': model = RBM(input=x, n_visible=dataset.phase1_input_size, n_hidden=params['STEP1']['n_hidden'], reg_weight=params['STEP1']['beta']) train_rbm(input=x, model=model, dataset=dataset, learning_rate=params['STEP1']['learning_rate'], outdir=model_dirs['STEP1']) else: model = SparseAutoencoder(input=x, n_visible=dataset.phase1_input_size, n_hidden=params['STEP1']['n_hidden'], beta=params['STEP1']['beta']) train_sae(input=x, model=model, dataset=dataset, learning_rate=params['STEP1']['learning_rate'], outdir=model_dirs['STEP1'])
def build_CompressModel(): print "STEP 1 start..." dataset = Nikkei(dataset_type=params["experiment_type"], brandcode=params["STEP3"]["brandcode"]) # pdb.set_trace() index = T.lscalar() # index to a [mini]batch x = T.matrix("x") # the data is presented as rasterized images if params["STEP1"]["model"] == "rbm": model = RBM( input=x, n_visible=dataset.phase1_input_size, n_hidden=params["STEP1"]["n_hidden"], reg_weight=params["STEP1"]["beta"], ) train_rbm( input=x, model=model, dataset=dataset, learning_rate=params["STEP1"]["learning_rate"], outdir=model_dirs["STEP1"], ) else: model = SparseAutoencoder( input=x, n_visible=dataset.phase1_input_size, n_hidden=params["STEP1"]["n_hidden"], beta=params["STEP1"]["beta"], ) train_sae( input=x, model=model, dataset=dataset, learning_rate=params["STEP1"]["learning_rate"], outdir=model_dirs["STEP1"], )
def build_CompressModel(): print 'STEP 1 start...' dataset = Nikkei(dataset_type=params['dataset_type'], brandcode=params['STEP3']['brandcode']) # pdb.set_trace() index = T.lscalar() # index to a [mini]batch x = T.matrix('x') # the data is presented as rasterized images if params['STEP1']['model'] == 'rbm': model = RBM(input=x, n_visible=dataset.phase1_input_size, n_hidden=params['STEP1']['n_hidden'], reg_weight=params['STEP1']['reg_weight'], corruption_level=params['STEP1']['corruption_level']) train_rbm(input=x, model=model, dataset=dataset, learning_rate=params['STEP1']['learning_rate'], outdir=model_dirs['STEP1'], batch_size=params['STEP1']['batch_size']) elif params['STEP1']['model'] == 'sda': sda_params = { 'dataset' : dataset, 'hidden_layers_sizes' : [params['STEP1']['n_hidden'], params['STEP1']['n_hidden'] / 2], 'pretrain_lr' : params['STEP1']['learning_rate'], 'pretrain_batch_size' : params['STEP1']['batch_size'], 'pretrain_epochs' : 5, 'corruption_levels' : [0.5, 0.5], 'k' : None, 'y_type' : 0, 'sparse_weight' : params['STEP1']['reg_weight'] } model = SdA.compress(sda_params) pre_params = get_model_params(model) while(True): try: f_out = open(model_dirs['STEP1'], 'w') f_out.write(cPickle.dumps(model, 1)) f_out.close() break except: pdb.set_trace() else: model = SparseAutoencoder(input=x, n_visible=dataset.phase1_input_size, n_hidden=params['STEP1']['n_hidden'], reg_weight=params['STEP1']['reg_weight'], corruption_level=params['STEP1']['corruption_level']) train_sae(input=x, model=model, dataset=dataset, learning_rate=params['STEP1']['learning_rate'], outdir=model_dirs['STEP1'], batch_size=params['STEP1']['batch_size'])
def retrain_CompressModel(): print 'STEP 1 start...' dataset = Nikkei(dataset_type=params['dataset_type'], brandcode=params['STEP3']['brandcode']) index = T.lscalar() # index to a [mini]batch x = T.matrix('x') # the data is presented as rasterized images if params['STEP1']['model'] == 'rbm': model = load_model(model_type='rbm', input=x, params_dir=model_dirs['STEP1']) train_rbm(input=x, model=model, dataset=dataset, learning_rate=params['STEP1']['learning_rate'], batch_size=params['STEP1']['batch_size'], outdir=model_dirs['STEP1']) # elif params['STEP1']['model'] == 'sda': # presae_dir = '%s/%s/h%d_lr%s_b%s_c%s.%s' % (default_model_dir, 'STEP1', params['STEP1']['n_hidden'], str(params['STEP1']['learning_rate']), str(params['STEP1']['reg_weight']), str(params['STEP1']['corruption_level']), 'sae') # x2 = T.matrix('x') # pre_model = load_model(model_type='sae', input=x, params_dir=presae_dir) # model = SparseAutoencoder(input=x2, n_visible=params['STEP1']['n_hidden'], n_hidden=params['STEP1']['n_hidden'], reg_weight=params['STEP1']['reg_weight'], corruption_level=params['STEP1']['corruption_level']) # train_sae2(input=x, model=model, pre_model=pre_model, dataset=dataset, learning_rate=params['STEP1']['learning_rate'], outdir=model_dirs['STEP1']) else: model = load_model(model_type='sae', input=x, params_dir=model_dirs['STEP1']) train_sae(input=x, model=model, dataset=dataset, learning_rate=params['STEP1']['learning_rate'], batch_size=params['STEP1']['batch_size'], outdir=model_dirs['STEP1'])
def retrain_CompressModel(): print 'STEP 1 start...' dataset = Nikkei(dataset_type=params['experiment_type'], brandcode=params['STEP3']['brandcode']) index = T.lscalar() # index to a [mini]batch x = T.matrix('x') # the data is presented as rasterized images if params['STEP1']['model'] == 'rbm': model = load_model(model_type='rbm', input=x, params_dir=model_dirs['STEP1']) train_rbm(input=x, model=model, dataset=dataset, learning_rate=params['STEP1']['learning_rate'], outdir=model_dirs['STEP1']) else: model = load_model(model_type='sae', input=x, params_dir=model_dirs['STEP1']) train_sae(input=x, model=model, dataset=dataset, learning_rate=params['STEP1']['learning_rate'], outdir=model_dirs['STEP1'])
def retrain_CompressModel(): print "STEP 1 start..." dataset = Nikkei(dataset_type=params["experiment_type"], brandcode=params["STEP3"]["brandcode"]) index = T.lscalar() # index to a [mini]batch x = T.matrix("x") # the data is presented as rasterized images if params["STEP1"]["model"] == "rbm": model = load_model(model_type="rbm", input=x, params_dir=model_dirs["STEP1"]) train_rbm( input=x, model=model, dataset=dataset, learning_rate=params["STEP1"]["learning_rate"], outdir=model_dirs["STEP1"], ) else: model = load_model(model_type="sae", input=x, params_dir=model_dirs["STEP1"]) train_sae( input=x, model=model, dataset=dataset, learning_rate=params["STEP1"]["learning_rate"], outdir=model_dirs["STEP1"], )
def build_CompressModel(): print 'STEP 1 start...' dataset = Nikkei(dataset_type=params['dataset_type'], brandcode=params['STEP3']['brandcode']) # pdb.set_trace() index = T.lscalar() # index to a [mini]batch x = T.matrix('x') # the data is presented as rasterized images if params['STEP1']['model'] == 'rbm': model = RBM(input=x, n_visible=dataset.phase1_input_size, n_hidden=params['STEP1']['n_hidden'], reg_weight=params['STEP1']['reg_weight'], corruption_level=params['STEP1']['corruption_level']) train_rbm(input=x, model=model, dataset=dataset, learning_rate=params['STEP1']['learning_rate'], outdir=model_dirs['STEP1'], batch_size=params['STEP1']['batch_size']) elif params['STEP1']['model'] == 'sda': sda_params = { 'dataset': dataset, 'hidden_layers_sizes': [params['STEP1']['n_hidden'], params['STEP1']['n_hidden'] / 2], 'pretrain_lr': params['STEP1']['learning_rate'], 'pretrain_batch_size': params['STEP1']['batch_size'], 'pretrain_epochs': 5, 'corruption_levels': [0.5, 0.5], 'k': None, 'y_type': 0, 'sparse_weight': params['STEP1']['reg_weight'] } model = SdA.compress(sda_params) pre_params = get_model_params(model) while (True): try: f_out = open(model_dirs['STEP1'], 'w') f_out.write(cPickle.dumps(model, 1)) f_out.close() break except: pdb.set_trace() else: model = SparseAutoencoder( input=x, n_visible=dataset.phase1_input_size, n_hidden=params['STEP1']['n_hidden'], reg_weight=params['STEP1']['reg_weight'], corruption_level=params['STEP1']['corruption_level']) train_sae(input=x, model=model, dataset=dataset, learning_rate=params['STEP1']['learning_rate'], outdir=model_dirs['STEP1'], batch_size=params['STEP1']['batch_size'])