关于“Performing Basic Feature Engineering in Keras”的评价
10301 条评价
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
Adriana B. · 已于 over 3 years前审核
Ritish A. · 已于 over 3 years前审核
Anna Elisabetta Z. · 已于 over 3 years前审核
Snehashis J. · 已于 over 3 years前审核
Mohammad A. · 已于 over 3 years前审核
Mark M. · 已于 over 3 years前审核
Dany T. · 已于 over 3 years前审核
Victor P. · 已于 over 3 years前审核
Supratim B. · 已于 over 3 years前审核
Shivam S. · 已于 over 3 years前审核
Alexander K. · 已于 over 3 years前审核
Alexander K. · 已于 over 3 years前审核
The instructions around get_scal are not clear, possibly not correct. It says get_scal takes a list of features. In your solution, it takes only one feature. The minmax function hardcodes train[feature]. Given what's previously taught in the class, I was expecting the use of tf.keras.layers.Normalization for this normalization. I think the language/solution could be improved upon. I'm going to try and do this lab on my own to try and get to the end solution. Thank you!
Pritam D. · 已于 over 3 years前审核
Ayan D. · 已于 over 3 years前审核
Liu S. · 已于 over 3 years前审核
GAYATHRI D. · 已于 over 3 years前审核
The lab is just copy and paste from the video
Santiago C. · 已于 over 3 years前审核
Hyungil K. · 已于 over 3 years前审核
我们无法确保发布的评价来自已购买或已使用产品的消费者。评价未经 Google 核实。