1ab5e16f37
Update 02 about urllib module attribute
...
See https://github.com/ageron/handson-ml2/issues/219
This error also occurred in 01.
There are many PRs for 01 but none for 02?
2021-01-04 21:25:46 +08:00
dad239b5a7
Fixed compatibility issue for scikit-learn 0.24
2020-12-31 17:34:26 +01:00
db6ed9d3c8
Update 01_the_machine_learning_landscape.ipynb
...
must specifically import urllib.request
2020-12-04 14:27:37 +08:00
05aca9c313
Fix bottom='off' to bottom=False in tools_matplotlib.ipynb
2020-11-27 01:59:30 +00:00
8ebdcffc6b
Work around TF Agents issue: env.step(1) => env.step(np.array(1))
2020-11-23 16:52:37 +13:00
f225f59780
Update to latest library versions
2020-11-21 12:22:42 +13:00
a55e3f3033
Fixed misspelling of 'literature'
2020-11-19 16:48:32 -07:00
4aa8c0b0d8
Updated wording from Multiple to Multiply
...
Corrected wording from "multiple $D$ by" to "multiply $D$ by"
2020-11-15 17:17:47 -05:00
98f6d26d3b
Update 01_the_machine_learning_landscape.ipynb
...
seems that new python libs used by google colab need „import urlib.request“ instead of „import urllib“
2020-11-09 19:29:00 +01:00
daf309c2bb
Install transformers library
2020-10-20 12:31:25 -04:00
2c700450b5
Change Embedding's input_dim argument
...
Wrong argument for the decoder's embedding layer.
2020-10-20 12:31:25 -04:00
e0cae0c7be
Replace deprecated method
...
See https://www.tensorflow.org/api_docs/python/tf/keras/Sequential?hl=en#predict_classes .
2020-10-20 12:31:25 -04:00
a2ffc37d2f
Modify creation of possible char list
...
I concatenated the string of all digits (+ comma and space) to the argument of function sorted ∘ set. Also, the digit '0' was written twice in the digit string.
2020-10-20 12:31:04 -04:00
7848437dc2
Correct typo
2020-10-19 12:44:33 -04:00
9d99ae9f9f
Correct small coding typo
2020-10-19 12:38:17 -04:00
80f6cb27c0
Update (small) the reinforcement learning chapter
2020-10-17 15:04:51 +01:00
08e3870053
Correct small "code typo"
2020-10-06 19:20:18 -04:00
a83d4885dc
Correct a small typo
...
One missing word.
2020-10-06 18:51:06 -04:00
c3cbfd04d5
Adding two missing words
2020-10-06 17:51:42 -04:00
cbfefe7a97
Change function argument
...
In Exercise 9, function `mnist_dataset` was called with the wrong argument.
2020-10-06 17:02:03 -04:00
5d53b561ad
updated the import
2020-10-05 23:40:19 +05:30
01464e2216
Adjust computation of steps per epoch
...
The number of steps per epoch is ceil(len(X) / batch_size) rather than floor(len(X) / batch_size). This change also means we do not have to take max(rate, self.last_rate) in the last steps of the OneCycleScheduler.
2020-09-25 08:25:17 -04:00
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
c4c4f1bac9
Update 01_the_machine_learning_landscape.ipynb
...
updated import urllib.request
to make urllib.request.urlretrieve(url, datapath + filename) work properly
2020-09-09 09:45:13 +02:00
70a515793c
Update 16_nlp_with_rnns_and_attention.ipynb
...
Exercise question 9 solution Third version decoder embedding "input_din=(len(OUTPUT_CHARS) + 2)"
2020-09-04 14:43:05 +05:30
59b9115ccb
Modify import of urllib to urllib.request
...
The import as-is will fail as changes have been made to urllib. This fix will allow the rest of the code to work as-is.
2020-08-26 07:40:19 -05:00
7111fe397a
Use object attribute instead of global constant
2020-08-17 09:26:01 -04:00
67f33429cc
Remove useless code
2020-08-15 10:08:44 -04:00
508b22e84d
Remove unnecessary code in 03_classification
2020-08-11 20:29:05 -04:00
6cec4e353c
Change rebuild target
...
* --no-cache is needed to guarantee a full rebuild from scratch
* --force-rm is not needed because rebuild calls the stop target
2020-08-11 16:23:44 +02:00
d7afbd511d
Better regex to match numbers in 03_classification
...
The previous regex would not match any decimal number where there is no "E" notation. Also added the option "+/-" sign in the "E" part.
2020-08-11 09:57:53 -04:00
a102114c62
Update 03_classification.ipynb
...
Create a function parameter for improved consistency.
2020-08-11 09:36:32 -04:00
d17126475d
Update 03_classification.ipynb
...
Use a function parameter instead of a global constant.
2020-08-11 09:33:51 -04:00
66446998a3
Update index.ipynb
2020-08-10 13:57:47 -04:00
1e81324573
Merge pull request #212 from RichaldoElias/patch-1
...
Update tools_numpy.ipynb
2020-07-29 09:16:40 +12:00
fd54bc6e8c
Update tools_numpy.ipynb
...
To create an ndarray using NumPy's `arange` function, which is similar to python's built-in `range` function
2020-07-25 18:42:30 +02:00
e90606bf69
No need to update tqdm in Colab anymore
2020-07-25 17:08:31 +12:00
05622d26b8
Fix early stopping example, fixes #190
2020-07-06 20:46:48 +12:00
df651cafb6
Merge branch 'master' of github.com:ageron/handson-ml2
2020-07-06 20:42:38 +12:00
dbfb7e8bff
Fix early stopping example, fixes #190
2020-07-06 20:42:26 +12:00
b575063c7e
Merge pull request #163 from rickiepark/upstream
...
[Chapter 2] Fix colorbar ticks
2020-07-05 18:46:48 +12:00
a5f584c021
Merge pull request #154 from Quoding/patch-1
...
Fix typo in the word "enviromnent"
2020-07-05 18:43:50 +12:00
4a48d04a1a
Add a comment about sklearn.metrics.plot_confusion_matrix, fixes #142
2020-07-05 18:35:06 +12:00
42196c4235
fix colorbar ticks
2020-05-09 11:40:30 +09:00
6585a20db6
Fix typo in the word "enviromnent"
...
"enviroment" -> "environment"
2020-04-30 13:04:34 -04:00
cdfad2d003
Link to matrix multiplication and Hadarmard product
2020-04-24 16:54:38 +12:00
8fb49ea7e0
plt.hist() normed renamed to density
2020-04-24 16:49:42 +12:00
8b00e3130d
Solution 9 version 4 requires TF 2.2 (add warning)
2020-04-22 19:59:35 +12:00
1f0bbc782a
Add more examples of TF-Addons seq2seq usage
2020-04-22 19:21:56 +12:00
hms5232