Closed Vishu26 closed 2 years ago
@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.
Thank you for the reply! I found a nice paper which implements what I need - https://arxiv.org/abs/1811.10166
Good to hear!
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?