Data Science Questions, Problems & Solutions : TransWikia.com ~ Page 50

Is it possible to use a different metric in early_stopping and ModelCheckpoint?

I'm using the tensorflow functions checkpoint and early stopping. Can I use 'val accuracy' in checkpoint to and 'val loss' in early stopping? or Should I use the same metric...

Asked on 08/18/2021

0 answer

larger batches decrease learning rate because of a technical artifact?

I'm training a neural network for a classification task and experimenting with different batch sizes. I'm using the negative log likelihood loss averaged over the samples in the batch. I...

Asked on 08/18/2021

0 answer

Training data for image digit recognition

I am creating a digit image recognition algorithm. For this I would like to collect sample data to train the model. Does python have any inbuilt libraries for this? Where...

Asked on 08/17/2021

0 answer

CNN memory consumption

I'd like to be able to estimate whether a proposed model is small enough to be trained on a GPU with a given amount of memory If I have a...

Asked on 08/17/2021

3 answer

How to quantify ‘compute cost’ of training of xgboost model?

I want to quantify compute cost of hyper-parameter search for xgboost model. One way can be to measure training time with one particular hyper parameter configuration chosen for training and...

Asked on 08/17/2021 by hasanfarooq

1 answer

How can I weight each point in one-class SVM?

I want to give weights to some data points Specifically, these are points related to anomalies (I'm implementing one-class SVM for anomaly detection) Exactly, I want to consider some data...

Asked on 08/17/2021

1 answer

Choropleth Map with plotly.express doesn't show map, just legend

I copied the "Indexing by GeoJSON Properties" example as seen on the Choropleth Maps in Python page. The code was executed with no error but there was...

Asked on 08/17/2021 by Almog

1 answer

Same model/same data different results in Keras/TF

So first to mention I used for all models the identical dataset (just in different shapes). I started with a binary classification based on text following the tutorial from ...

Asked on 08/17/2021 by user116997

0 answer

Sampling trying to keep as much multivariate variance as possible

I was thinking if anyone considered a sampling technique that would try to aim keeping as much of the variance as possible (e.g. as many unique values, or very widely...

Asked on 08/17/2021 by PascalVKooten

1 answer

What is Monte Carlo dropout?

I understand how to use MC dropout from this answer, but I don't understand how MC dropout works, what its purpose is, and how it differs from normal dropout....

Asked on 08/17/2021 by Haramoz

1 answer

Ask a Question

Get help from others!

Data Science : Recent Questions and Answers (Page 50)

Ask a Question