Keras - Python Deep Learning Neural Network API

with deeplizard.

Learnable parameters ("trainable params") in a Keras model

April 24, 2018 by


Let's discuss how we can quickly access and calculate the number of learnable parameters in a Keras Sequential model. We do this by inspecting and verifying the results in the “Param #” column of model.summary(). We then inspect the parameters returned from model.get_weights() and compare the output of the weights and biases to that given in model.summary(). This video builds on concepts covered in “Learnable Parameters explained,” so check that one out first! Follow deeplizard: YouTube: Twitter: Facebook: Steemit: Instagram: Support deeplizard on Patreon: Checkout products deeplizard suggests on Amazon: Support deeplizard with crypto: Bitcoin: 1AFgm3fLTiG5pNPgnfkKdsktgxLCMYpxCN Litecoin: LTZ2AUGpDmFm85y89PFFvVR5QmfX6Rfzg3 Ether: 0x9105cd0ecbc921ad19f6d5f9dd249735da8269ef Recommended books on AI: The Most Human Human: What Artificial Intelligence Teaches Us About Being Alive: Life 3.0: Being Human in the Age of Artificial Intelligence Playlists: Machine Learning - Keras - Data Science - Music: Brittle Rille by Kevin MacLeod Website: Licensed under Creative Commons: By Attribution 3.0 License