Category "machine-learning"

Number of distinct clusters in KMeans is less than n_clusters?

I have some food images stored in a single folder. All the images are unlabeled, nor are they stored into separate folder such as "pasta" or "meat". My current

Why the initialization of weights in darknet?

there! I am studying Mr. Redmon's darknet code from https://github.com/pjreddie/darknet I found the initialization of weights of a connected layer is like below

Why the initialization of weights in darknet?

there! I am studying Mr. Redmon's darknet code from https://github.com/pjreddie/darknet I found the initialization of weights of a connected layer is like below

How to Setup Adaptive Learning Rate in Keras

Below is my code: model = Sequential([ Dense(32, input_shape=(32,), activation = 'relu'), Dense(100, activation='relu'), Dense(65, input_shape=(65

How do you read Tensorboard files programmatically?

How can you write a python script to read Tensorboard log files, extracting the loss and accuracy and other numerical data, without launching the GUI tensorboar

Plotting learning curve in keras gives KeyError: 'val_acc'

I was trying to plot train and test learning curve in keras, however, the following code produces KeyError: 'val_acc error. The official document <https://k

Identify author name, book name from a string obtained with OCR

After using tess4j(OCR library) on a photo of a book preface, i obtain the text from the image. Now, i want to identify author name, book name from that string.

R neuralnet package: Can't train neural network

I'm trying to use the neuralnet package to train a model on this data set. However, I'm getting the following error which I can't understand: Error: the err

logits and labels must be broadcastable error in Tensorflow RNN

I am new to Tensorflow and deep leaning. I am trying to see how the loss decreases over 10 epochs in my RNN model that I created to read a dataset from kaggle w

returning cov and std from sklearn gaussian process?

I can return the covariance or the standard deviation from a GP using sklearn, like: y, cov = gp.predict(Xpredict,return_cov=True) y, std = gp.predict(Xpredict,

Plot PCA loadings and loading in biplot in sklearn (like R's autoplot)

I saw this tutorial in R w/ autoplot. They plotted the loadings and loading labels: autoplot(prcomp(df), data = iris, colour = 'Species', loadings =

Can we use Normal Equation for Logistic Regression ?

Just like we use the Normal Equation to find out the optimum theta value in Linear Regression, can/can't we use a similar formula for Logistic Regression ? If n

Correct Implementation of Dice Loss in Tensorflow / Keras

I've been trying to experiment with Region Based: Dice Loss but there have been a lot of variations on the internet to a varying degree that I could not find tw

How to get the location of all text present in an image using OpenCV?

I have this image that contains text (numbers and alphabets) in it. I want to get the location of all the text and numbers present in this image. Also I want to

Multi-output neural network combining regression and classification

If you have both a classification and regression problem that are related and rely on the same input data, is it possible to successfully architect a neural net

Neural Network for Regression with tflearn

My question is about coding a neural network which does regression (and NOT classification) using tflearn. Dataset: fixed acidity volatile acidity citric acid

which algorithm does google keyboard uses for automatic suggestions (personal vocab included)?

I am confused since google cannnot train their text generation models with each individuals personal vocabulary. I was trying to develop something similar but

Balanced Accuracy Score in Tensorflow

I am implementing a CNN for an highly unbalanced classification problem and I would like to implement custum metrics in tensorflow to use the Select Best Model

multivariate xgboost time series

I implemented a univariate xgboost time series using the following code, def series_to_supervised(data, n_in=1, n_out=1, dropnan=True): n_vars = 1 if type(d

My text classifier model doens't improve with multiple classes

I'm trying to train a model for a text classification and the model take a list of maximum 300 integer embedded from articles. The model trains without problem