This block can have any number of inputs that have the same shape, and merges them along a specified axis.
Concatenating can be useful to merge features coming from different parts of the model towards the end (for instance merging image features with tabular data when estimating the price of a house), or joining together multiple images that are tiles of a bigger map. The output has the same size as the sum of all sizes of the input along the axis to concatenate, and the same shape for all other axis, if any.
Axis along which to concatenate.
Stay in the know by signing up for occasional emails with tips, tricks, deep learning insights, product updates, event news and webinar invitations.
We promise not to spam you or share your email with any third party. You can change your preferences at any time. See our privacy policies.
Please check your email inbox account to confirm, set, or update your communication preferences.