24 Commits

Author SHA1 Message Date
Haesun Park
81d2ff4614 설명 보완 2018-06-15 15:52:57 +09:00
Haesun Park
a0a49d1ae1 11장 노트북 재실행 2018-05-23 16:20:09 +09:00
rickiepark
17bc85ff54 variance_scaling_initializer 수정, 텐서보드 그래프 분리, keras mnist 적용 2018-05-20 21:59:30 +09:00
Haesun Park
0bd3f4c671 텐서플로 1.8 버전으로 재실행 및 강화학습 녹화 영상 개선 2018-05-03 15:10:41 +09:00
Haesun Park
53bff95537 11장 실행 2018-04-17 16:27:14 +09:00
Haesun Park
17122a4593 11장 그래프 제목 수정 2018-03-29 11:19:34 +09:00
Haesun Park
fd58032bb8 reuse_vars_dict 삭제(4ad1d7cbd5) 2018-03-26 17:37:02 +09:00
Aurelien Geron
410b1beb74 Fix JSON formatting in new comment in the ch 11 notebook 2017-11-03 13:43:56 +01:00
Chris Qlasty
e2754cd72c Update 11_deep_learning.ipynb 2017-11-03 12:07:37 +01:00
Chris Qlasty
cbe5fb39b3 Comments fix 2017-11-03 12:04:54 +01:00
Chris Qlasty
2b76749832 0.18 version left with 0.19 suggestions commented
The previous version of the .fit( ) with the suggestion of how it should be done from the version 0.21.
2017-11-03 12:00:28 +01:00
Chris Qlasty
a2b67bda3b Scikit-learn 19.0 updates on .fit( ) arguments up.
I have left unnecessary ',' at the end of the fit_params line, sorry for that.
2017-11-02 18:54:12 +01:00
Chris Qlasty
2fd9f1e1be Scikit-learn 19.0 updates on .fit( ) arguments
Adopting code to my needs I have found that in the scikit-learn 19.0  they recommend to put params list directly into the .fit( ) methods. That also makes the code more understandable for me as now it is more clear where these values go to (fit( ) function of DNNClassifier).
Hope this makes sense.
2017-11-02 18:30:30 +01:00
Jason Rys
632a14fd66 Fix typos 2017-08-19 08:01:55 -07:00
Aurelien Geron
a877054be8 Fixes #56, bug in DNNClassifier for batch normalization 2017-07-13 11:13:37 +02:00
Aurelien Geron
b639cad9e2 Add SELU activation function example and snip out repetitive outputs 2017-06-21 15:35:47 +02:00
Aurelien Geron
ffcd8dfa8a Add exercise solutions for chapter 11 2017-06-14 09:09:23 +02:00
Aurelien Geron
6689c3a1ef Use np.random.set_seed(42) and tf.set_random_seed(42) to make notebook's output constant 2017-06-07 08:59:58 +02:00
Aurelien Geron
c58f1ed2da Sync chapter 11 notebook with the code samples in that chapter 2017-06-05 18:48:03 +02:00
Aurelien Geron
7fd688d21d Use tf.layers instead of tf.contrib.layers 2017-04-30 10:21:27 +02:00
Aurelien Geron
a9c1c20a9b Fix bug: tf.add_n([loss] + reg_losses) rather than loss + reg_losses 2017-03-04 12:36:25 +01:00
Aurelien Geron
d526403bb8 Upgrade notebooks to TensorFlow 1.0.0 2017-02-17 11:51:26 +01:00
Aurelien Geron
277df4aa1b Migrate to TensorFlow 0.11.0 2016-11-23 09:26:19 +01:00
Aurelien Geron
da638e55e4 Add notebooks for chapters 5 to 14 2016-09-27 23:31:21 +02:00