关于“Performing Basic Feature Engineering in Keras”的评价

Andrea G. · 已于 over 3 years前审核

Kiana Alessandra V. · 已于 over 3 years前审核

M R. · 已于 over 3 years前审核

Mario R. · 已于 over 3 years前审核

Brandon G. · 已于 over 3 years前审核

Ang X. · 已于 over 3 years前审核

Sanjay B. · 已于 over 3 years前审核

Clive N. · 已于 over 3 years前审核

Sanjay B. · 已于 over 3 years前审核

Cheikh T. · 已于 over 3 years前审核

chhaya s. · 已于 over 3 years前审核

very difficult.

Steven S. · 已于 over 3 years前审核

Sergio Adriano L. · 已于 over 3 years前审核

Brenno M. · 已于 over 3 years前审核

Takashi D. · 已于 over 3 years前审核

Nicolo L. · 已于 over 3 years前审核

Corinna F. · 已于 over 3 years前审核

Sophie S. · 已于 over 3 years前审核

Guilherme A. · 已于 over 3 years前审核

Guilherme A. · 已于 over 3 years前审核

Sometimes methods for loading in data is confusing.

Tiego T. · 已于 over 3 years前审核

Xiaohui L. · 已于 over 3 years前审核

Mojtaba G. · 已于 over 3 years前审核

Finally got through the lab after a few attempts, the use of the min max function here, which relies on pandas functionality, is not intuitive. I would have preferred if we instead used a normalization layer which is native to tensorflow. Furthermore, setting random seeds so the work is reproducible/verifiable would be helpful in quantifying the model improvements and incorporating that in the notebook. The instructions for predictions on the test dataset weren't very clear to me. I think there's a missed opportunity here to do things like [(X, y)] = test_ds.take(1), model.predict(X), and likewise feature_layer(X) to help the student understand what's happening under the good. Thank you!

Pritam D. · 已于 over 3 years前审核

Samuel D. · 已于 over 3 years前审核