theano

Perhaps too general a question, but can anyone explain what would cause a Convolutional Neural Network to diverge? Specifics: I am using Tensorflow's iris_training model with some of my own data and keep getting ERROR:tensorflow:Model diverged with loss = NaN. Traceback... tensorflow.contrib.learn.python.learn.monitors.NanLossDuringTrainingError: NaN loss during training. Traceback originated with line: tf.contrib.learn.DNNClassifier(feature_columns=feature_columns, hidden_units=[300, 300, 300], #optimizer=tf.train.ProximalAdagradOptimizer(learning_rate=0.001, l1_regularization_strength=0

I'm trying to do binary LSTM classification using theano. I have gone through the example code however I want to build my own. I have a small set of "Hello" & "Goodbye" recordings that I am using. I preprocess these by extracting the MFCC features for them and saving these features in a text file. I have 20 speech files(10 each) and I am generating a text file for each word, so 20 text files that contains the MFCC features. Each file is a 13x56 matrix. My problem now is: How do I use this text file to train the LSTM? I am relatively new to this. I have gone through some literature on it as

I tried to switch Backend with Keras (from TensorFlow to Theano) but did not manage. I followed the temps described here but it doesn't work. I created a keras.json in the keras' directory (as it did not exist) but it doesn't change anything when I import it from Python. Create a .keras (note the . in front) folder in you home directory and put the keras.json file there. For example, /home/DaniPaniz/.keras/keras.json (or ~/.keras/keras.json in short) if you are on a UNIX like system (MacOS X, Linux, *BSD). On Windows you want to create the folder %USERPROFILE%/.keras and put the JSON file

I understand that the Theano support for Windows 8.1 is at experimental stage only but I wonder if anyone had any luck with resolving my issues. Depending on my config, I get three distinct types of errors. I assume that the resolution of any of my errors would solve my problem. I have installed Python using WinPython 32-bit system, using MinGW as described here . The contents of my .theanorc file are as follows: [global] openmp=False device = gpu [nvcc] flags=-LC:\TheanoPython\python-2.7.6\libs compiler_bindir=C:\Program Files (x86)\Microsoft Visual Studio 10.0\VC\bin\ [blas] ldflags = When I

I have a data matrix in "one-hot encoding" (all ones and zeros) with 260,000 rows and 35 columns. I am using Keras to train a simple neural network to predict a continuous variable. The code to make the network is the following: model = Sequential() model.add(Dense(1024, input_shape=(n_train,))) model.add(Activation('relu')) model.add(Dropout(0.1)) model.add(Dense(512)) model.add(Activation('relu')) model.add(Dropout(0.1)) model.add(Dense(256)) model.add(Activation('relu')) model.add(Dropout(0.1)) model.add(Dense(1)) sgd = SGD(lr=0.01, nesterov=True); #rms = RMSprop() #model.compile(loss=

edit September, 2, 2017, 1pm I eventually managed to build a .exe with pyinstaller after many episodes. Unfortunately I failed to deal with the ‘theano’ module (that is required in my case by the ‘pymc3’ module) and I had to modify the .py files and give up part of the application. My description below has two aims: first it may help; second could anyone help me building a .exe for windows 7+, with the ‘theano’ module ? reminder: My python 3 script opens a simple GUI made with Qt Designer in a ‘.ui’ file and imports pyqtgraph (with pyqt5), pymc3 (and thus theano that is required by pymc3),

I am getting an import error when trying to import the Keras module Nadam: >>> from keras.optimizers import Nadam Traceback (most recent call last): File "<stdin>", line 1, in <module> ImportError: cannot import name Nadam I can import and use SGD, Adam, etc, just not this optimizer. Any help appreciated. I installed Keras using: git clone https://github.com/fchollet/keras.git sudo python2.7 setup.py install I have just found that, if I try to import it using the shell immediately after installation, the Nadam import works. But Nadam won't import in my script. So it's a path issue? ivan