Thank you. El viernes, 22 de julio de 2016, 19:59:30 (UTC+2), nouiz escribió: > > I can't help you. But I remember that Pylearn2 allowed to train SVM on top > of a Theano model. Maybe you can look there. > > Note, Pylearn2 don't have developer anymore. > > Fred > > On Fri, Jul 22, 2016 at 12:11 PM, Beatriz G. <[email protected] > <javascript:>> wrote: > >> Hi Everyone. I am trying to use SVM classifier in Lenet instead of >> logistic regresion. I know how SVM (from sklearn) works and how to train >> and test with SVM because I have done it in others pattern recognition >> problems. >> >> My problem is that I do not know how to train and test SVM in Lenet. I do >> not where I have to train and test. >> >> I have separated train and test in Lenet, in order to train and test the >> SVM sepparately, but I still don't know how to mix SVM and CNN. >> >> Anyone could guide me? >> >> >> Regards. >> >> >> Here is my code: >> >> >> >> >> class LeNetConvPoolLayer(object): >> """Pool Layer of a convolutional network """ >> >> def __init__(self, rng, input, filter_shape, image_shape, poolsize=(2, >> 2)): >> """ >> Allocate a LeNetConvPoolLayer with shared variable internal >> parameters. >> :type rng: numpy.random.RandomState >> :param rng: a random number generator used to initialize weights >> :type input: theano.tensor.dtensor4 >> :param input: symbolic image tensor, of shape image_shape >> :type filter_shape: tuple or list of length 4 >> :param filter_shape: (number of filters, num input feature maps, >> filter height, filter width) >> :type image_shape: tuple or list of length 4 >> :param image_shape: (batch size, num input feature maps, >> image height, image width) >> :type poolsize: tuple or list of length 2 >> :param poolsize: the downsampling (pooling) factor (#rows, #cols) >> """ >> >> assert image_shape[1] == filter_shape[1] >> #El numero de feature maps sea igual en ambas variables >> self.input = input >> >> # there are "num input feature maps * filter height * filter width" >> # inputs to each hidden unit >> fan_in = numpy.prod(filter_shape[1:]) >> #el numero de neuronas en la capa anterio >> # each unit in the lower layer receives a gradient from: >> # "num output feature maps * filter height * filter width" / >> # pooling size >> >> fan_out = (filter_shape[0] * numpy.prod(filter_shape[2:]) / >> #El numero de neuronas de salida: numero de filtros*alto*ancho del >> filtro/poolsize(tam*tam) >> numpy.prod(poolsize)) >> # initialize weights with random weights >> >> # initialize weights with random weights >> W_bound = numpy.sqrt(6. / (fan_in + fan_out)) >> self.W = theano.shared( >> numpy.asarray( >> rng.uniform(low=-W_bound, high=W_bound, size=filter_shape), >> # Se calcula asi el W_bound por la funcion de activacion >> tangencial. >> # Los pesos dependen del tamanyo del filtro(neuronas) >> >> dtype=theano.config.floatX # Para que sea valido en gpu >> ), >> borrow=True >> ) >> >> # the bias is a 1D tensor -- one bias per output feature map >> b_values = numpy.zeros((filter_shape[0],), >> dtype=theano.config.floatX) >> self.b = theano.shared(value=b_values, borrow=True) >> >> # convolve input feature maps with filters >> conv_out = conv.conv2d( >> input=input, >> filters=self.W, >> filter_shape=filter_shape, >> image_shape=image_shape >> ) >> >> # downsample each feature map individually, using maxpooling >> pooled_out = downsample.max_pool_2d( >> input=conv_out, >> ds=poolsize, >> ignore_border=True >> ) >> >> print pooled_out >> >> # add the bias term. Since the bias is a vector (1D array), we first >> # reshape it to a tensor of shape (1, n_filters, 1, 1). Each bias >> will >> # thus be broadcasted across mini-batches and feature map >> # width & height >> self.output = theano.tensor.nnet.relu((pooled_out + >> self.b.dimshuffle('x', 0, 'x', 'x')) , alpha=0) >> >> >> # store parameters of this layer >> self.params = [self.W, self.b] >> >> # keep track of model input >> self.input = input >> >> self.conv_out=conv_out >> self.pooled_out=pooled_out >> >> self.salidas_capa = [self.conv_out, self.pooled_out, self.output] >> >> >> >> def evaluate_lenet5(learning_rate=0.001, n_epochs=100, nkerns=[48, 96], >> batch_size=20): >> """ Demonstrates lenet on MNIST dataset >> >> :type learning_rate: float >> :param learning_rate: learning rate used (factor for the stochastic >> gradient) >> >> :type n_epochs: int >> :param n_epochs: maximal number of epochs to run the optimizer >> >> :type dataset: string >> :param dataset: path to the dataset used for training /testing (MNIST >> here) >> >> :type nkerns: list of ints >> :param nkerns: number of kernels on each layer >> """ >> >> rng = numpy.random.RandomState(2509) >> >> train_set_x, test_set_x, train_set_y, test_set_y, valid_set_x, >> valid_set_y = Load_casia_Data1() >> >> train_set_x = theano.shared(numpy.array(train_set_x, dtype='float64',)) >> test_set_x = theano.shared(numpy.array(test_set_x, dtype='float64')) >> train_set_y = theano.shared(numpy.array(train_set_y, dtype='int32')) >> test_set_y = theano.shared(numpy.array(test_set_y, dtype='int32')) >> valid_set_x = theano.shared(numpy.array(valid_set_x, dtype='float64')) >> valid_set_y = theano.shared(numpy.array(valid_set_y, dtype='int32')) >> >> print("n_batches:") >> >> # compute number of minibatches for training, validation and testing >> n_train_batches = train_set_x.get_value(borrow=True).shape[0] >> n_valid_batches = valid_set_x.get_value(borrow=True).shape[0] >> n_test_batches = test_set_x.get_value(borrow=True).shape[0] >> print("n_train_batches: %d" % n_train_batches) >> print("n_valid_batches: %d" % n_valid_batches) >> print("n_test_batches: %d" % n_test_batches) >> >> n_train_batches /= batch_size >> n_valid_batches /= batch_size >> n_test_batches /= batch_size >> >> # allocate symbolic variables for the data >> index = T.lscalar() # index to a [mini]batch >> >> # start-snippet-1 >> x = T.matrix('x') # the data is presented as rasterized images >> y = T.ivector('y') # the labels are presented as 1D vector of >> # [int] labels >> >> ###################### >> # BUILD ACTUAL MODEL # >> ###################### >> print '... building the model' >> >> # Reshape matrix of rasterized images of shape (batch_size, 28 * 28) >> # to a 4D tensor, compatible with our LeNetConvPoolLayer >> # (28, 28) is the size of MNIST images. >> layer0_input = x.reshape((batch_size, 3, 104, 52)) >> >> # Construct the first convolutional pooling layer: >> # filtering reduces the image size to (28-5+1 , 28-5+1) = (24, 24) >> # maxpooling reduces this further to (24/2, 24/2) = (12, 12) >> # 4D output tensor is thus of shape(batch_size, nkerns[0], 12, 12) >> layer0 = LeNetConvPoolLayer( >> rng, >> input=layer0_input, >> image_shape=(batch_size, 3, 104, 52), >> filter_shape=(nkerns[0], 3, 5, 5), >> poolsize=(2, 2) >> ) >> >> salidas_capa0 = theano.function( >> [index], >> layer0.salidas_capa, >> givens={ >> x: test_set_x[index * batch_size: (index + 1) * batch_size], >> } >> ) >> >> >> # Construct the second convolutional pooling layer >> # filtering reduces the image size to (12-5+1, 12-5+1) = (8, 8) >> # maxpooling reduces this further to (8/2, 8/2) = (4, 4) >> # 4D output tensor is thus of shape (batch_size, nkerns[1], 4, 4) >> layer1 = LeNetConvPoolLayer( >> rng, >> input=layer0.output, >> image_shape=(batch_size, nkerns[0], 50, 24), >> filter_shape=(nkerns[1], nkerns[0], 5, 5), >> poolsize=(2, 2) >> ) >> >> salidas_capa1 = theano.function( >> [index], >> layer1.salidas_capa, >> givens={ >> x: test_set_x[index * batch_size: (index + 1) * batch_size], >> } >> ) >> >> # the HiddenLayer being fully-connected, it operates on 2D matrices of >> # shape (batch_size, num_pixels) (i.e matrix of rasterized images). >> # This will generate a matrix of shape (batch_size, nkerns[1] * 4 * 4), >> # or (500, 50 * 4 * 4) = (500, 800) with the default values. >> layer2_input = layer1.output.flatten(2) >> >> # construct a fully-connected sigmoidal layer >> layer2 = HiddenLayer( >> rng, >> input=layer2_input, >> n_in=nkerns[1] * 23 * 10, >> n_out=100, >> activation=T.nnet.relu >> ) >> >> >> >> # classify the values of the fully-connected sigmoidal layer >> svm = SVC() >> >> >> layer3 = LogisticRegression(input=layer2.output, n_in=100, n_out=2) >> >> # the cost we minimize during training is the NLL of the model >> cost = layer3.negative_log_likelihood(y) >> >> # create a function to compute the mistakes that are made by the model >> test_model = theano.function( >> [index], >> layer3.errors(y), >> givens={ >> x: test_set_x[index * batch_size: (index + 1) * batch_size], >> #Los given son algo para la gpu >> y: test_set_y[index * batch_size: (index + 1) * batch_size] >> } >> ) >> >> validate_model = theano.function( >> [index], >> layer3.errors(y), >> givens={ >> x: valid_set_x[index * batch_size: (index + 1) * batch_size], >> y: valid_set_y[index * batch_size: (index + 1) * batch_size] >> } >> ) >> >> # create a list of all model parameters to be fit by gradient descent >> params = layer3.params + layer2.params + layer1.params + layer0.params >> >> # create a list of gradients for all model parameters >> grads = T.grad(cost, params) >> >> # train_model is a function that updates the model parameters by >> # SGD Since this model has many parameters, it would be tedious to >> # manually create an update rule for each model parameter. We thus >> # create the updates list by automatically looping over all >> # (params[i], grads[i]) pairs. >> updates = [ >> (param_i, param_i - learning_rate * grad_i) >> for param_i, grad_i in zip(params, grads) >> ] >> >> train_model = theano.function( >> [index], >> cost, >> updates=updates, >> givens={ >> x: train_set_x[index * batch_size: (index + 1) * batch_size], >> y: train_set_y[index * batch_size: (index + 1) * batch_size] >> } >> ) >> # end-snippet-1 >> >> >> ############### >> # TRAIN MODEL # >> ############### >> print '... training' >> # early-stopping parameters >> patience = 10000 # 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 >> best_iter = 0 >> test_score = 0. >> start_time = timeit.default_timer() >> >> lista_coste = [] >> >> epoch = 0 >> done_looping = False >> >> # save_file = >> open('/home/beaa/PycharmProjects/TFM/LearningTheano/salidas0.pkl', 'wb') >> # save_file1 = >> open('/home/beaa/PycharmProjects/TFM/LearningTheano/wb0.pkl', 'wb') >> # save_file2 = >> open('/home/beaa/PycharmProjects/TFM/LearningTheano/salidas1.pkl', 'wb') >> # save_file3 = >> open('/home/beaa/PycharmProjects/TFM/LearningTheano/wb1.pkl', 'wb') >> >> print 'n_train_batches' >> print n_train_batches >> while (epoch < n_epochs) and (not done_looping): >> epoch = epoch + 1 >> for minibatch_index in range(n_train_batches): >> >> iter = (epoch - 1) * n_train_batches + minibatch_index >> >> if iter % 100 == 0: >> print('training @ iter = ', iter) >> cost_ij = train_model(minibatch_index) >> >> if (iter + 1) % validation_frequency == 0: >> >> # compute zero-one loss on validation set >> validation_losses = [validate_model(i) for i >> in range(n_valid_batches)] >> this_validation_loss = numpy.mean(validation_losses) >> print('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 >> >> w0_test = layer0.W.get_value() >> b0_test = layer0.b.get_value() >> >> w1_test = layer1.W.get_value() >> b1_test = layer1.b.get_value() >> >> w2_test = layer2.W.get_value() >> b2_test = layer2.b.get_value() >> >> >> >> >> if patience <= iter: >> done_looping = True >> break >> >> >> ############################### >> ### TESTING MODEL ### >> ############################### >> #Aqui se tiene que cargar la red >> >> layer0.W.set_value(w0_test) >> layer0.b.set_value(b0_test) >> >> layer1.W.set_value(w1_test) >> layer1.b.set_value(b1_test) >> >> layer2.W.set_value(w2_test) >> layer2.b.set_value(b2_test) >> >> # test it on the test set >> test_losses = [test_model(i) >> for i in range(n_test_batches) >> ] >> test_score = numpy.mean(test_losses) >> >> print((' test error of best model %f %%') % (test_score * 100.)) >> >> >> end_time = timeit.default_timer() >> print('Optimization complete.') >> print('Best validation score of %f %% obtained at iteration %i, ' >> 'with test performance %f %%' % >> (best_validation_loss * 100., best_iter + 1, test_score * 100.)) >> >> print("start time: %d" % start_time) >> print("end_time: %d" % end_time) >> >> # print(('The code for file ' + >> # os.path.split(__file__)[1] + >> # ' ran for %.2fm' % ((end_time - start_time) / 60.)), >> file=sys.stderr) >> >> >> >> >> if __name__ == '__main__': >> evaluate_lenet5() >> >> >> def experiment(state, channel): >> evaluate_lenet5(state.learning_rate, dataset=state.dataset) >> >> -- >> >> --- >> You received this message because you are subscribed to the Google Groups >> "theano-users" group. >> To unsubscribe from this group and stop receiving emails from it, send an >> email to [email protected] <javascript:>. >> For more options, visit https://groups.google.com/d/optout. >> > >
-- --- You received this message because you are subscribed to the Google Groups "theano-users" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. For more options, visit https://groups.google.com/d/optout.
