def test_sql(): log = Log("Smoketest", "no data", {'zen':"perspective",'nothing':"everything"} ) log.result(100,{}) return "OK"
def test_SdA(args): """ Demonstrates how to train and test a stochastic denoising autoencoder. This is demonstrated on MNIST. :type learning_rate: float :param learning_rate: learning rate used in the finetune stage (factor for the stochastic gradient) :type pretraining_epochs: int :param pretraining_epochs: number of epoch to do pretraining :type pretrain_lr: float :param pretrain_lr: learning rate to be used during pre-training :type n_iter: int :param n_iter: maximal number of iterations ot run the optimizer :type dataset: string :param dataset: path the the pickled dataset """ finetune_lr = args.get('finetune_lr',0.1, type=float) pretraining_epochs = args.get('pretraining_epochs', 15, type=int) pretrain_lr = args.get('pretrain_lr', 0.001, type=float) training_epochs = args.get('training_epochs', 1000, type=int) n_ins = math.pow(args.get('n_ins', 28, type=int),2) hidden_layer_size = args.get('hidden_layer_size', 1000, type=int) n_outs = args.get('n_outs', 10, type=int) dataset='mnist.pkl.gz' batch_size=1 log = Log("SdA", dataset, args ) datasets = load_data(dataset) train_set_x, train_set_y = datasets[0] valid_set_x, valid_set_y = datasets[1] test_set_x, test_set_y = datasets[2] # compute number of minibatches for training, validation and testing n_train_batches = train_set_x.get_value(borrow=True).shape[0] n_train_batches /= batch_size # numpy random generator # start-snippet-3 numpy_rng = numpy.random.RandomState(89677) log.trace('... building the model') # construct the stacked denoising autoencoder class sda = SdA( numpy_rng = numpy_rng, n_ins = n_ins, hidden_layers_sizes = [hidden_layer_size, hidden_layer_size, hidden_layer_size], n_outs = n_outs ) # end-snippet-3 start-snippet-4 ######################### # PRETRAINING THE MODEL # ######################### log.trace('... getting the pretraining functions') pretraining_fns = sda.pretraining_functions(train_set_x=train_set_x, batch_size=batch_size) log.trace('... pre-training the model') start_time = timeit.default_timer() ## Pre-train layer-wise corruption_levels = [.1, .2, .3] for i in xrange(sda.n_layers): # go through pretraining epochs for epoch in xrange(pretraining_epochs): # go through the training set c = [] for batch_index in xrange(n_train_batches): c.append(pretraining_fns[i](index=batch_index, corruption=corruption_levels[i], lr=pretrain_lr)) log.trace('Pre-training layer %i, epoch %d, cost ' % (i, epoch)) log.trace(numpy.mean(c)) end_time = timeit.default_timer() log.trace('The pretraining code for file ' + os.path.split(__file__)[1] + ' ran for %.2fm' % ((end_time - start_time) / 60.)) # end-snippet-4 ######################## # FINETUNING THE MODEL # ######################## # get the training, validation and testing function for the model log.trace('... getting the finetuning functions') train_fn, validate_model, test_model = sda.build_finetune_functions( datasets=datasets, batch_size=batch_size, learning_rate=finetune_lr ) log.trace('... finetunning the model') # early-stopping parameters patience = 10 * n_train_batches # look as this many examples regardless patience_increase = 2. # wait this much longer when a new best is # found improvement_threshold = 0.995 # a relative improvement of this much is # considered significant validation_frequency = min(n_train_batches, patience / 2) # go through this many # minibatche before checking the network # on the validation set; in this case we # check every epoch best_validation_loss = numpy.inf test_score = 0. start_time = timeit.default_timer() done_looping = False epoch = 0 while (epoch < training_epochs) and (not done_looping): epoch = epoch + 1 for minibatch_index in xrange(n_train_batches): minibatch_avg_cost = train_fn(minibatch_index) iter = (epoch - 1) * n_train_batches + minibatch_index if (iter + 1) % validation_frequency == 0: validation_losses = validate_model() this_validation_loss = numpy.mean(validation_losses) log.trace('epoch %i, minibatch %i/%i, validation error %f %%' % (epoch, minibatch_index + 1, n_train_batches, this_validation_loss * 100.)) # if we got the best validation score until now if this_validation_loss < best_validation_loss: #improve patience if loss improvement is good enough if ( this_validation_loss < best_validation_loss * improvement_threshold ): patience = max(patience, iter * patience_increase) # save best validation score and iteration number best_validation_loss = this_validation_loss best_iter = iter # test it on the test set test_losses = test_model() test_score = numpy.mean(test_losses) log(test_score, {epoch:epoch, minibatch_index:minibatch_index}) log.trace(('epoch %i, minibatch %i/%i, test error of best model %f %%') % (epoch, minibatch_index + 1, n_train_batches, test_score * 100.)) if patience <= iter: done_looping = True break end_time = timeit.default_timer() # log.trace( # ( # 'Optimization complete with best validation score of %f %%, ' # 'on iteration %i, ' # 'with test performance %f %%' # ) # % (best_validation_loss * 100., best_iter + 1, test_score * 100.) # ) log.trace('The training code for file ' + os.path.split(__file__)[1] + ' ran for %.2fm' % ((end_time - start_time) / 60.))