Python Developer

I am trying to create a simple CNN to classify images in MNIST dataset. The model achieved an accep… Read more Why The Model Is Training On Only 1875 Training Set Images If There Are 60000 Images In The Mnist Dataset?

I am currently working on a CNN network, in which i want to apply a 2d kernel on a image, but it on… Read more Performing 1d Convolution Using 2d Kernel In Keras

I can't load all of my dataset at once, so I used tf.keras.preprocessing.image_dataset_from_dir… Read more How To Split Dataset Into K-fold Without Loading The Whole Dataset At Once?

I am trying to replicate VGG16 model in keras, the following is my code: model = Sequential() model… Read more Keras Maxpooling2d Layer Gives Valueerror

I am writing just a simple loss function in which I have to convert the tensor to numpy array(it… Read more Keras Custom Loss Function Not Printing Value Of Tensor

I am trying to distribute Keras training on a cluster and use Elephas for that. But, when running t… Read more Elephas Not Loaded In Pyspark: No Module Named Elephas.spark_model

I have the following model def get_model(): epochs = 100 learning_rate = 0.1 decay_rate = learning_… Read more Cnn Loss With Multiple Outputs?

I have TensorFlow 1.9 and Keras 2.0.8 on my machine. When training a neural network with some toy d… Read more Different Behaviour Between Same Implementations Of Tensorflow And Keras

Or, more specific: what is the difference between ConvLSTM2D and ConvLSTM2DCell? What is the diffe… Read more What Is A "cell Class" In Keras?

I have successfully implemented and run an autoencoder on image data (MNIST digits). I use Spyder t… Read more Python Code Using Keras Crashes On Call To Model.fit With No Error Code

I am using Windows 10, Python 3.5, and tensorflow 1.1.0. I have the following script: import tensor… Read more How Do I Get The Weights Of A Layer In Keras?

I'm trying to save and load my keras model. It trains, evaluates, and saves fine (using .h5 to … Read more How To Fix ''valueerror: Input 0 Is Incompatible With Layer Flatten: Expected Min_ndim=3, Found Ndim=2" Error When Loading Model

I am using 3d kernel of size 3x3x3 for the convoution layer and would like to plot the weights of … Read more Weight Visualization Of 3d Convolutional Kernel

i'm running a CNN with keras sequential on google colab. i'm getting the following error: V… Read more On Colab - Class_weight Is Causing A Valueerror: The Truth Value Of An Array With More Than One Element Is Ambiguous. Use A.any() Or A.all()

I am slightly confused on the different ways to apply dropout to my Sequential model in Keras. My m… Read more Does Applying A Dropout Layer After The Embedding Layer Have The Same Effect As Applying The Dropout Through The Lstm Dropout Parameter?

As an input a have a float 1.0 or 0.0. When I try to predict with my model and the sparse_categoric… Read more How Should I Interpret The Output Of The Sparse_categorical_crossentropy Function?

If i have a dataset consisting by a list of images each associated with a series of features; there… Read more How To Generate New Image Using Deep Learning, From New Features

The following code shows one way that works and the other that fails. The BatchNorm on axis=0 shoul… Read more Keras Batchnormalization Only Works For Constant Batch Dim When Axis=0?

I am switching from tensorflow to keras on my Anaconda distribution and am having some problems wit… Read more Keras Breaks Anaconda Prompt

For a model that I intend to spontaneously generate sequences I find that training it sample by sam… Read more On Training Lstms Efficiently But Well, Parallelism Vs Training Regime