Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

TCN for Time Series Image Classification #229

Closed
Vishu26 opened this issue Mar 15, 2022 · 3 comments
Closed

TCN for Time Series Image Classification #229

Vishu26 opened this issue Mar 15, 2022 · 3 comments
Labels
question Further information is requested

Comments

@Vishu26
Copy link

Vishu26 commented Mar 15, 2022

I want to classify images where the features (channels) represent each time step. So, the input to TCN would have input_shape=(None, timesteps, height, width). The idea here is to incorporate spatial and temporal information for classification at the same time.

Is there a possibility I can modify TCN to use it as a ConvLSTM2D layer?

@philipperemy
Copy link
Owner

philipperemy commented Apr 24, 2022

@Vishu26 you can't do it with TCN unless if you reshape your input to (None, timesteps, height * width). Which might be perfectly fine in terms of performance and accuracy.

There's an example that can do that. It's called MNIST pixel: https://github.com/philipperemy/keras-tcn/tree/master/tasks/mnist_pixel.

You can refer to the original paper in the README to learn about the task.

@philipperemy philipperemy added the question Further information is requested label Apr 24, 2022
@Vishu26
Copy link
Author

Vishu26 commented May 11, 2022

Thank you for the reply! I found a nice paper which implements what I need - https://arxiv.org/abs/1811.10166

@philipperemy
Copy link
Owner

Good to hear!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested
Projects
None yet
Development

No branches or pull requests

2 participants