Fix the "input_dim" of the dense layer

GoogleCloudPlatform / training-data-analyst

Labs and demos for courses for GCP Training (http://cloud.google.com/training).

Apache License 2.0

7.84k stars 5.85k forks source link

Fix the "input_dim" of the dense layer #2522

Closed mostafa-asg closed 9 months ago

mostafa-asg commented 9 months ago

After adding more features, including bucketized feature and feature crosses, the number of features is no longer 8. The number of 8 comes from the first model, which only has numeric features. This is a silent error and model trains without error but the whole goal of this tutorial is to add more features and reduce the "mean squared error". After changing this line, my mse reduced from 14850733056 to 14575827968.

google-cla[bot] commented 9 months ago

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

review-notebook-app[bot] commented 9 months ago

Check out this pull request on

See visual diffs & provide feedback on Jupyter Notebooks.