2 votes

Sklearn vs Pytorch vs Tensorflow vs Keras

The scikit-learn is a library that is used most often when working with the more traditional non neural network models, whereas the other three are more focused on ...
  • 6,169
2 votes

How to predict the quality (as a classification) of a regression?

In general this idea isn't bad BUT you need to collect new data for this to work. Modeling isn't suspect to p-hacking but this would be quite similiar. 50% of predicted outcomes not within tolerance ...
  • 1,683
2 votes
Accepted

Improve CNN classification accuracy

95% is very good, I'm not sure if improving that result would not alter the result in production: Keeping an error margin might be helpful to avoid overfitting, but it may not be your case. ...
1 vote

About improving the classifier when using a pre-trained model

Both of your models (with and with no extra layer) have high train accuracy but much lower scores on test data which indicates that both models overfit, i.e. they suffer from high variance (using the ...
  • 5,065
1 vote

Training Neural Network using TensorFlow on Large Video Dataset for Human Activity Recognition

At an early stage, you don't have to use all the data, but rather build a first model with a reasonable amount of data (ex: 4Gb) for 3 reasons: 1- The learning time is much shorter, so you can apply a ...
1 vote

Use tensorflow Dataset to extract slices based on array of known indices

I figured it out. Dataset.from_generator() is what I was looking for. ...
  • 111
1 vote

How to increase FER2013 dataset validation_accuracy for only 3 classes i.e, happy,sad,neutral?

Several Approaches: Firstly I would remove vertical flip, I couldnt see any images that were upside down in your dataset. More augmentation including brightness, CLAHE, cutouts Cross Validation Bring ...
  • 168
1 vote

Modelling Player Impact on English Premier League

Lots of different approaches, you could instead of 1 or 0 you could have more granular information of their time on the pitch (if your data supports it). I think number of goals is a bad feature to ...
  • 168
1 vote
Accepted

Hello guys, is dimension reduction required for tensorflow?

Dimensionality reduction is not related to TensorFlow's CNN training: Dimensionality reduction is for unsupervised data clustering and classification. Not sure if you will cluster expressions clearly ...
1 vote

How can I fine tune a model to detect digits, used to detect denominations of currency notes

What you're looking for is called Optical Character Recognition. A really good example of using CNNs to do OCR in keras is here.
  • 21

Only top scored, non community-wiki answers of a minimum length are eligible