theano

In numpy, if I have a boolean array, I can use it to select elements of another array: >>> import numpy as np >>> x = np.array([1, 2, 3]) >>> idx = np.array([True, False, True]) >>> x[idx] array([1, 3]) I need to do this in theano. This is what I tried, but I got an unexpected result. >>> from theano import tensor as T >>> x = T.vector() >>> idx = T.ivector() >>> y = x[idx] >>> y.eval({x: np.array([1,2,3]), idx: np.array([True, False, True])}) array([ 2., 1., 2.]) Can someone explain the theano result and suggest how to get the numpy result? I need to know how to do this in order to properly

When running theano, I get an error: not enough memory. See below. What are some possible actions that can be taken to free up memory? I know I can close applications etc, but I just want see if anyone has other ideas. For example, is it possible to reserve memory? THEANO_FLAGS=mode=FAST_RUN,device=gpu,floatX=float32 python conv_exp.py Using gpu device 0: GeForce GT 650M Trying to run under a GPU. If this is not desired, then modify network3.py to set the GPU flag to False. Error allocating 156800000 bytes of device memory (out of memory). Driver report 64192512 bytes free and 1073414144 bytes

In Keras, we can define the network as follows. Are there any way to output the shape after each layer. For instance, I want to print out the shape of inputs after the line defining inputs , then print out the shape of conv1 after the line defining conv1 , etc. inputs = Input((1, img_rows, img_cols)) conv1 = Convolution2D(64, 3, 3, activation='relu', init='lecun_uniform', W_constraint=maxnorm(3), border_mode='same')(inputs) conv1 = Convolution2D(64, 3, 3, activation='relu', init='lecun_uniform', W_constraint=maxnorm(3), border_mode='same')(conv1) pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)

I'm currently trying to follow the example here using a dataset I generated by myself. The back end is run using Theano. The directory structure is exactly the same: image_sets/ dogs/ dog001.jpg dog002.jpg ... cats/ cat001.jpg cat002.jpg ... validation/ dogs/ dog001.jpg dog002.jpg ... cats/ cat001.jpg Here is my code for the keras convolutional neural network. img_width, img_height = 150, 150 img_width, img_height = 150, 150 train_data_dir = './image_sets' validation_data_dir = './validation' nb_train_samples = 267 print nb_train_samples #number of validation images I have nb_validation

I just started playing around with Theano but have a strange problem in Eclipse. I am trying to import the config module to run some example code. The import works fine and I can see what's in the module. Here is the simple code I am trying: from theano import config print config This works fine and I get an output like: floatX (('float64', 'float32')) Doc: Default floating-point precision for python casts Value: float32 ... and some more lines like that. Unfortunately if I use the following code, I get an "undefined variable from import"-error for the floatX: from theano import config print

I have a Theano function that is called several times, each time with different shared variables. The way it is implemented now, the Theano function gets redefined every time it is run. I assume, that this make the whole program slow, because every time the Theano functions gets defined the graph is rebuild. def sumprod_shared(T_shared_array1, T_shared_array2): f = theano.function([], (T_shared_array1 * T_shared_array2).sum(axis=0)) return f() for factor in range(10): m1 = theano.shared(factor * array([[1, 2, 4], [5, 6, 7]])) m2 = theano.shared(factor * array([[1, 2, 4], [5, 6, 7]])) print

I am currently trying to visualize the output of an intermediate layer in Keras 1.0 (which I could do with Keras 0.3) but it does not work anymore. x = model.input y = model.layers[3].output f = theano.function([x], y) But I get the following error: MissingInputError: ("An input of the graph, used to compute DimShuffle{x,x,x,x}(keras_learning_phase), was not provided and not given a value.Use the Theano flag exception_verbosity='high',for more information on this error.", keras_learning_phase) Prior to Keras 1.0, with my graph model, I could just do: x = graph.inputs['input'].input y = graph

I'm currently facing an issue while trying to fit my GRU model with my training data. After a quick look on StackOverflow, I found this post to be quite similar to my issue : Simplest Lstm training with Keras io My own model is as follow : nn = Sequential() nn.add(Embedding(input_size, hidden_size)) nn.add(GRU(hidden_size_2, return_sequences=False)) nn.add(Dropout(0.2)) nn.add(Dense(output_size)) nn.add(Activation('linear')) nn.compile(loss='mse', optimizer="rmsprop") history = History() nn.fit(X_train, y_train, batch_size=30, nb_epoch=200, validation_split=0.1, callbacks=[history]) And the