Data Science Stack Exchange is a question and answer site for Data science professionals, Machine Learning specialists, and those interested in learning more about the field. It only takes a minute to sign up.

Sign up to join this community

Anybody can ask a question

Anybody can answer

The best answers are voted up and rise to the top

Explore our Questions

more tags

Active 2 Bountied Hot Week Month

0

votes

1

answer

8

views

A Loss of 55.2164 with a sparse_categorical_crossentropy in a sequential neural network?

machine-learning neural-network keras categorical-data

answered 1 hour ago Oxbowerce 519

0

votes

0

answers

9

views

Load training data sequentially to avoid memory error

python deep-learning keras tensorflow

modified 2 hours ago ebrahimi 1,067

19

votes

1

answer

33k

views

How does the validation_split parameter of Keras' fit function work?

keras data cross-validation

modified 16 hours ago charlie 1

0

votes

1

answer

17

views

What methods are used to determine acceptable loss levels for autoencoders?

keras tensorflow

modified 16 hours ago Community♦ 1

2

votes

2

answers

585

views

How to define a custom metric function in R for Keras?

keras r

modified yesterday Community♦ 1

3

votes

2

answers

131

views

Keypoint detection from an image using a neural network

neural-network keras tensorflow cnn image-recognition

modified yesterday Community♦ 1

0

votes

0

answers

10

views

How can I change the loss function when the shape of my data changes?

python neural-network deep-learning keras tensorflow

modified 2 days ago Anan Srivastava 1

0

votes

0

answers

7

views

How to feed multiple asymmetric inputs to LSTM layer?

keras lstm autoencoder

asked 2 days ago muruD 11

1

vote

1

answer

216

views

While retraining a pretrained model, getting: ValueError: Input 0 is incompatible with layer flatten_1: expected min_ndim=3, found ndim=2

neural-network deep-learning keras

modified 2 days ago Community♦ 1

0

votes

1

answer

33

views

Retraining EfficientNet on only 2 classes out of 4

keras tensorflow image-classification supervised-learning

modified 2 days ago Community♦ 1

0

votes

0

answers

6

views

Projected gradient descent in keras

keras tensorflow gradient-descent pytorch

asked 2 days ago Red Floyd 111

0

votes

1

answer

3k

views

Keras stateful LSTM returns NaN for validation loss

keras lstm multilabel-classification

modified 2 days ago Community♦ 1

0

votes

1

answer

338

views

Keras: extreme spike in loss during training

python keras regression lstm accuracy

modified Mar 24 at 19:01 Community♦ 1

0

votes

1

answer

29

views

How to get a output of a hidden layer of a single-layer LSTM

deep-learning keras r lstm rstudio

modified Mar 24 at 18:02 Community♦ 1

Browse more Questions

Data Science Stack Exchange works best with JavaScript enabled