Aurélien Geron
|
01784d2f98
|
Do not use a layer as an activation function, especially with weights
|
2019-06-09 20:08:53 +08:00 |
|
Aurélien Geron
|
0023162fc5
|
bst_n_estimators should be argmin + 1
|
2019-06-08 21:59:55 +08:00 |
|
Aurélien Geron
|
e9ae4997a5
|
Update requirements, e.g. add tf-agents, tf serving api, etc.
|
2019-06-08 12:01:58 +08:00 |
|
Aurélien Geron
|
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 |
|
Aurélien Geron
|
0615a6f0a1
|
LayerNormalization is not experimental anymore
|
2019-06-06 11:06:13 +08:00 |
|
Aurélien Geron
|
fb47fab0c8
|
Update docker image for 2nd edition
|
2019-06-04 16:43:14 +08:00 |
|
Aurélien Geron
|
f680e49ea2
|
Replace SGD with SVC in OvA vs OvO section
|
2019-05-28 15:21:49 +08:00 |
|
Aurélien Geron
|
efa16f02ec
|
Add breakout.gif
|
2019-05-28 09:31:22 +08:00 |
|
Aurélien Geron
|
4c3b7b9b06
|
Save agent's breakout performance to an animated gif
|
2019-05-28 09:30:16 +08:00 |
|
Aurélien Geron
|
3ef350ab4c
|
Fix figure name and clarify a couple code examples
|
2019-05-27 20:35:00 +08:00 |
|
Aurélien Geron
|
c5f4b41cf5
|
Fix breakout plot
|
2019-05-26 23:56:49 +08:00 |
|
Aurélien Geron
|
2edbb6e9d4
|
Add Reinforcement Learning notebook
|
2019-05-26 23:30:39 +08:00 |
|
Aurélien Geron
|
80279c4477
|
Make notebook 09 deterministic, and avoid non-convergence warnings
|
2019-05-19 16:19:29 +07:00 |
|
Aurélien Geron
|
c702bfbcab
|
Fix ladybug.png so imageio can load it without chunk_eXIf issues
|
2019-05-19 15:03:42 +07:00 |
|
Aurélien Geron
|
73a36f335f
|
Add warning about TF issue regarding DenseFeatures and the Functional API, fixes #6
|
2019-05-15 20:23:24 +08:00 |
|
Aurélien Geron
|
ec3136f59f
|
Add index=housing.index when wrapping array in a DataFrame, fixes #426
|
2019-05-12 21:28:56 +08:00 |
|
Aurélien Geron
|
f0f83903bd
|
Fix the transformer (use final encoder outputs)
|
2019-05-10 21:30:18 +08:00 |
|
Aurélien Geron
|
7b1c890195
|
Stop using learning_phase: it's a global variable, and currently broken anyway
|
2019-05-09 16:26:38 +08:00 |
|
Aurélien Geron
|
a758ea50b0
|
Rename the figure paths from *_diagram.png to *_plot.png
|
2019-05-09 16:25:40 +08:00 |
|
Aurélien Geron
|
8e08319781
|
Rename the figure paths from *_diagram.png to *_plot.png
|
2019-05-09 16:25:26 +08:00 |
|
Aurélien Geron
|
d4d15a9c59
|
Clarify figure 4-19
|
2019-05-09 16:24:17 +08:00 |
|
Aurélien Geron
|
107b90d9b3
|
Do not use learning_phase anymore, just set training=True/False
|
2019-05-09 10:39:02 +08:00 |
|
Aurélien Geron
|
df100ffa9a
|
Rename figure
|
2019-05-06 13:15:15 +08:00 |
|
Aurélien Geron
|
dd5e648c62
|
Rename figure
|
2019-05-06 13:15:01 +08:00 |
|
Aurélien Geron
|
22eb374304
|
Rename figure
|
2019-05-06 13:14:50 +08:00 |
|
Aurélien Geron
|
4941749b60
|
Fix typo in figure name
|
2019-05-06 13:14:23 +08:00 |
|
Aurélien Geron
|
aa648067a9
|
Change notebook title to Autoencoders and GANs
|
2019-05-06 09:38:47 +08:00 |
|
Aurélien Geron
|
4e155bc23b
|
Rename 17 to Autoencoders and GANs
|
2019-05-06 09:37:56 +08:00 |
|
Aurélien Geron
|
42f24fa44f
|
Add GANs
|
2019-05-06 09:34:45 +08:00 |
|
Aurélien Geron
|
fd1e088dab
|
Add 1cycle scheduling
|
2019-05-05 12:42:08 +08:00 |
|
Aurélien Geron
|
d2a518cdb1
|
Add more chapters to index.ipynb
|
2019-04-30 15:01:15 +08:00 |
|
Aurélien Geron
|
7335c9d5c0
|
Use separate joblib package rather than the one in sklearn (which is deprecated)
|
2019-04-26 21:22:15 +08:00 |
|
Aurélien Geron
|
327407501e
|
Add notebook 17 on autoencoders
|
2019-04-26 21:19:32 +08:00 |
|
Aurélien Geron
|
9925735995
|
Add the images/nlp directory
|
2019-04-23 20:06:24 +08:00 |
|
Aurélien Geron
|
6f98bc5a04
|
Stateful RNNs now support recurrent_dropout
|
2019-04-21 15:55:39 +08:00 |
|
Aurélien Geron
|
33d1894dc1
|
Update requirements to use TensorFlow 2.0 alpha0
|
2019-04-20 13:05:52 +08:00 |
|
Aurélien Geron
|
df9b91e2e8
|
Rename chapters 11 to 15 and split chapter 15 into 15 and 16
|
2019-04-16 20:39:14 +08:00 |
|
Aurélien Geron
|
61bb73074b
|
Add a basic implementation of MultiHeadAttention
|
2019-04-16 19:52:49 +08:00 |
|
Aurélien Geron
|
d24fee1576
|
Add .bak.* and datasets/titanic to .gitignore
|
2019-04-16 08:44:30 +08:00 |
|
Aurélien Geron
|
03810ea2f7
|
Add chapter 15, time series and NLP using RNNs, CNNs and Attention
|
2019-04-16 08:27:36 +08:00 |
|
Aurélien Geron
|
03c5ef896b
|
Add chapter 15 - Handling sequential data (time series and NLP with RNNs and Attention)
|
2019-04-16 00:09:43 +08:00 |
|
Aurélien Geron
|
52afcf4290
|
Crop long outputs so they show up nicer on github.com
|
2019-04-16 00:06:57 +08:00 |
|
Aurélien Geron
|
687fd71b5f
|
Add outputs for threshold_90_precision and fix comment, fixes #2
|
2019-04-05 17:06:37 +08:00 |
|
Aurélien Geron
|
6d7dcd7c80
|
Work in progress updating ch15
|
2019-04-05 17:04:38 +08:00 |
|
Aurélien Geron
|
6974508cf7
|
Remove old TensorFlow chapter
|
2019-03-25 18:14:29 +08:00 |
|
Aurélien Geron
|
f0b432eb59
|
Add missing BN layer in ResNet-34 and remove bias in Conv2D
|
2019-03-25 12:19:27 +08:00 |
|
Aurélien Geron
|
3313c21723
|
No bias before BN layers
|
2019-03-25 12:03:44 +08:00 |
|
Aurélien Geron
|
1774ede668
|
Update CNN chapter
|
2019-03-24 09:06:29 +08:00 |
|
Aurélien Geron
|
7d8dfb45cf
|
Move CNN chapter out of work_in_progress
|
2019-03-16 13:59:41 +08:00 |
|
Aurélien Geron
|
5f6be6fa6f
|
Use pd.cut() for income_cat
|
2019-03-15 23:49:03 +08:00 |