Which version of them do you use? Can you try with the dev version of Theano?
Le 27 juil. 2016 11:54, "Beatriz G." <[email protected]> a écrit : > Hi guays, > > I am having a similar problem, I am trying to compile the following theano > function: > > layer3 = LogisticRegression(input=layer2.output, n_in=100, n_out=4) > > > salidas_capa3 = theano.function( > [index], > layer3.y_pred, > givens={ > x: test_set_x[index * batch_size: (index + 1) * batch_size] > } > ) > > > > Which I call in the test part: > > > for i in range(n_test_batches): > test_losses = [test_model(i)] > y_pred_test = salidas_capa3[test_model(i)] > print y_pred_test > test_score = numpy.mean(test_losses) > > > > And I am getting the next error: > > > Traceback (most recent call last): > File "/home/beaa/Escritorio/Theano/Separando_Lenet.py", line 416, in > <module> > evaluate_lenet5() > File "/home/beaa/Escritorio/Theano/Separando_Lenet.py", line 392, in > evaluate_lenet5 > y_pred_test = salidas_capa3[test_model(i)] > File > "/home/beaa/.local/lib/python2.7/site-packages/theano/compile/function_module.py", > line 545, in __getitem__ > return self.value[item] > File > "/home/beaa/.local/lib/python2.7/site-packages/theano/compile/function_module.py", > line 480, in __getitem__ > s = finder[item] > TypeError: unhashable type: 'numpy.ndarray' > > > > > Anyone could guide me? > > > 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=2, 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_Data2() > > 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=4) > > > salidas_capa3 = theano.function( > [index], > layer3.y_pred, > givens={ > x: test_set_x[index * batch_size: (index + 1) * batch_size] > } > ) > > # 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 > for i in range(n_test_batches): > test_losses = [test_model(i)] > y_pred_test = salidas_capa3[test_model(i)] > print y_pred_test > 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) > > > > > > > Thanks in advance. > > > Regards. > > > > > > > > El martes, 28 de mayo de 2013, 23:56:29 (UTC+2), Pascal Lamblin escribió: >> >> On Wed, May 29, 2013, Анатолий wrote: >> > That's how i define test values: >> > >> > ishape = (288, 384) >> > batch_size = numpy.int16(batch_size) >> > index = T.lscalar().tag.test_value = numpy.int16(0) >> > x = T.matrix('x').tag.test_value = numpy.random.rand(batch_size, >> > numpy.prod(ishape)).astype(dtype=theano.config.floatX) >> > y = T.ivector('y').tag.test_value = numpy.random.randint(0,2, >> > size=batch_size).astype(dtype=numpy.int16) >> >> In fact, as Olivier Delalleau pointed it, here is your problem. Here, >> you assign the test value to the name 'x', rather than assigning the >> symbolic variable. You should do the following instead: >> >> # In two different statements: >> # first create 'index' as a symbolic variable >> index = T.lscalar() >> # then assign a test value to it >> index.tag.test_value = numpy.int16(0) >> >> # same thing for the other variables: >> x = T.matrix('x') >> x.tag.test_value = numpy.random.rand(batch_size, >> numpy.prod(ishape)).astype(dtype=theano.config.floatX) >> >> y = T.ivector('y') >> y.tag.test_value = numpy.random.randint(0, 2, >> size=batch_size).astype(dtype=numpy.int16) >> >> Hope this helps, >> -- >> Pascal >> > -- > > --- > 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. > -- --- 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.
