The Flatten block reshapes the input, which could be a tensor of any shape, into a 1-dimensional vector.
One of its uses is to feed data coming from convolutional layers into a Dense layer, for instance in the middle of some auto-encoders. It is also useful when wanting to Concatenate a convolutional part of a model with an MLP part that has Dense layers, since Dense layers operate on 1D input.
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.