Python Tutorial for Beginners

Is it possible to set model.loss in a callback without re-compiling model.compile(...) after (since… Read more Change Loss Function Dynamically During Training In Keras, Without Recompiling Other Model Properties Like Optimizer

I'm trying to train a CNN on a set of images. There are 2 folders: training_set and test_set, e… Read more How To Load And Evaluate A Cnn Using A Test Set In Tensorflow?

Keras and PyTorch use different arguments for padding: Keras requires a string to be input, while P… Read more Converting Keras (tensorflow) Convolutional Neural Networks To Pytorch Convolutional Networks?

My project partner and I are currently facing a problem in our latest university project. Our missi… Read more Neural Network Does Not Learn (loss Stays The Same)

I was doing Multi-class Classification using Keras.It contained 5 classes of Output. I converted th… Read more Coverting Back One Hot Encoded Results Back To Single Column In Python

I am trying to solve a binary classification problem with the sequential model from Keras and have … Read more Balanced Error Rate As Metric Function

I am using a Keras sequential model, a prediction output is of the shape (1, 5) (5 features). I hav… Read more Which Loss Function To Use In Keras Sequential Model

I am using Keras with tensorflow-gpu in backend, I don't have tensorflow (CPU - version) instal… Read more Why Tensorflow-gpu Is Still Using Cpu

I'm trying to reproduce the architecture of the network proposed in this publication in tensorF… Read more How To Access All Outputs From A Single Custom Loss Function In Keras

I have tokenized data in the form of a list of unequally shaped arrays: array([array([1179, 6, … Read more Converting A List Of Unequally Shaped Arrays To Tensorflow 2 Dataset: Valueerror: Can't Convert Non-rectangular Python Sequence To Tensor

I'm trying to use Conv1D for the first time for multiclass classification of time series data a… Read more Expected Dense_1 To Have 2 Dimensions, But Got Array With Shape (308, 1, 6)

I have trained a Keras-based autoencoder model with the following input layer: depth = 1 width = he… Read more Why Is Keras Complaining About Incompatible Input Shape In This Case?

I have a neural network that takes in an RGB colour image of 500px by 500px and will also output an… Read more Keras Output Shape Has An Extra Dimension

(x_train, y_train), (x_test, y_test) = tf.keras.datasets.fashion_mnist.load_data() x_train = x_trai… Read more Keras Input Shape Throws Value Error Expected 4d But Got An Array With Shape (60000, 28,28)

I am just a novice in area of deep learning. I made my first basic attempt with Keras Conv1D. Not … Read more Keras Conv1d For Time Series

I'm trying to solve classification problem. I don't know why I'm getting this error: At… Read more Python : Attributeerror: 'str' Object Has No Attribute 'keys'

I have dataset containing water samples collected from different locations. For example, ABC1 water… Read more Timeseries Input To An Lstm

When Keras 2.x removed certain metrics, the changelog said it did so because they were 'Batch-b… Read more Keras Metrics With Tf Backend Vs Tensorflow Metrics

I got that error when trying to implement this lines of code Shape must be rank 2 but is rank 3 for… Read more Shape Must Be Rank 2 But Is Rank 3 For 'matmul_46' (op: 'matmul') With Input Shapes: [100,100], [?,15,100]

I am using ImageDataGenerator to generate new augmented images and extract bottleneck features fro… Read more Predict_generator And Class Labels