bdd246bf07
Fixing wide-and-deep to use normalized inputs
...
Thanks for this great book/repo. I noticed the wide and deep example is using non-normalized inputs which leads to performance degradation.
2022-06-27 09:27:51 -05:00
a2f8391951
Upgrade to TensorFlow 2.8
2022-03-01 11:41:27 +13:00
85171acd17
Require Python 3.7+
2022-02-19 23:03:20 +13:00
0a28fab583
Add notebook outputs
2022-02-19 22:24:54 +13:00
b63019fd28
Sync notebook with book's code examples, and better identify extra code
2022-02-19 18:17:36 +13:00
3552690321
Remove redundant comment
2021-12-08 15:16:42 +13:00
146e6fc062
Big update of chapter 10 for 3rd edition
2021-12-08 11:58:36 +13:00
a2c05861f3
Move notebooks again as the SVM chapter is added back
2021-11-23 13:41:17 +13:00
ce4fccf74c
Large change: Chapter 5 on SVMs moves online
2021-10-15 21:59:45 +13:00
fa1ae51184
Large change: replace os.path with pathlib, move to Python 3.7
2021-10-15 21:46:27 +13:00
108fe1fa53
Replace lr with learning_rate in Keras optimizers, fixes #456
2021-08-31 20:54:35 +12:00
1b96533668
Replace 'Open in Colab' button
2021-05-26 07:40:58 +12:00
3b45ac2f2b
Update 10_neural_nets_with_keras.ipynb
...
fix link
2021-05-25 11:16:28 -07:00
856f2fe56f
Update 10_neural_nets_with_keras.ipynb
...
add Open in Kaggle badge
2021-05-24 19:59:45 -07:00
4e915ba6c2
Merge branch 'master' into changes-chap10
2021-03-02 12:21:32 +13:00
670873843d
Update libraries to latest version, including TensorFlow 2.4.1 and Scikit-Learn 0.24.1
2021-02-14 15:02:09 +13:00
30d160f8be
Remove useless code cell
2020-09-14 09:35:42 -04:00
af0c959d07
Remove soon-to-be-deprecated method
...
Warning: THIS FUNCTION IS DEPRECATED. It will be removed after 2021-01-01. Instructions for updating: Please use instead: np.argmax(model.predict(x), axis=-1), if your model does multi-class classification (e.g. if it uses a softmax last-layer activation).
2020-09-14 07:52:07 -04:00
2f7ab70295
Update notebooks to latest nbformat
2020-04-06 19:13:12 +12:00
0c2c80d89e
Add warning about Keras issue 13586
2020-03-12 12:16:18 +13:00
4e57c9f686
Add solutions to chapter 10 code exercises
2020-01-27 11:37:04 +13:00
f810964f51
Make notebooks 10 and 11 runnable in Colab without changes
2019-11-06 11:38:13 +08:00
8f7a2c355b
Display Fashion MNIST
2019-07-13 11:31:17 +02:00
b6306b7d48
Update ch. 10 code to latest TF nightly version, eg. default SGD learning rate is now 0.001
2019-06-08 11:43:48 +08:00
a758ea50b0
Rename the figure paths from *_diagram.png to *_plot.png
2019-05-09 16:25:40 +08:00
df100ffa9a
Rename figure
2019-05-06 13:15:15 +08:00
52afcf4290
Crop long outputs so they show up nicer on github.com
2019-04-16 00:06:57 +08:00
e938df8fb9
Add kwargs to constructor of custom model
2019-02-28 19:48:50 +08:00
8d6a55f32c
TensorFlow 2 preview is now has tf.__version__ >= "2.0"
2019-02-12 20:32:58 +08:00
b546b743be
Create image directory and check for sklearn >= 0.20 and TensorFlow >= 2.0-preview
2019-01-21 18:13:10 +08:00
6b8dff91d0
Update all notebooks assuming we are all in the future now: sklearn 0.20+, python 3.5+, TF 2.0 preview
2019-01-18 23:08:37 +08:00
ca6eb8c147
Add chapter 10 - neural nets with Keras
2019-01-16 23:37:12 +08:00
GarrettJenkinson