Skip to content

Commit b8e8a42

Browse files
author
Github Actions
committed
Ravin Kohli: [fix] Dropout bug fix (#247)
1 parent 8a61289 commit b8e8a42

24 files changed

+1025
-541
lines changed

‎development/_downloads/bc82bea3a5dd7bdba60b65220891d9e5/examples_python.zip

0 Bytes
Binary file not shown.

‎development/_downloads/fb625db3c50d423b1b7881136ffdeec8/examples_jupyter.zip

0 Bytes
Binary file not shown.

‎development/_images/sphx_glr_example_visualization_001.png

163 Bytes
Loading

‎development/_images/sphx_glr_example_visualization_002.png

-128 Bytes
Loading

‎development/_images/sphx_glr_example_visualization_thumb.png

760 Bytes
Loading

‎development/_sources/examples/20_basics/example_image_classification.rst.txt

Lines changed: 10 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -88,16 +88,17 @@ Image Classification
8888
________________________________________
8989
Configuration:
9090
image_augmenter:GaussianBlur:use_augmenter, Value: False
91-
image_augmenter:GaussianNoise:use_augmenter, Value: False
92-
image_augmenter:RandomAffine:rotate, Value: 139
93-
image_augmenter:RandomAffine:scale_offset, Value: 0.23068913599566782
94-
image_augmenter:RandomAffine:shear, Value: 15
95-
image_augmenter:RandomAffine:translate_percent_offset, Value: 0.3649730895991128
91+
image_augmenter:GaussianNoise:sigma_offset, Value: 2.2167939735095414
92+
image_augmenter:GaussianNoise:use_augmenter, Value: True
93+
image_augmenter:RandomAffine:rotate, Value: 32
94+
image_augmenter:RandomAffine:scale_offset, Value: 0.21992528764167255
95+
image_augmenter:RandomAffine:shear, Value: 10
96+
image_augmenter:RandomAffine:translate_percent_offset, Value: 0.3741519768349007
9697
image_augmenter:RandomAffine:use_augmenter, Value: True
97-
image_augmenter:RandomCutout:p, Value: 0.8026417457168646
98+
image_augmenter:RandomCutout:p, Value: 0.7598328080896313
9899
image_augmenter:RandomCutout:use_augmenter, Value: True
99-
image_augmenter:Resize:use_augmenter, Value: True
100-
image_augmenter:ZeroPadAndCrop:percent, Value: 0.26059070078518315
100+
image_augmenter:Resize:use_augmenter, Value: False
101+
image_augmenter:ZeroPadAndCrop:percent, Value: 0.40737331917856867
101102
normalizer:__choice__, Value: 'NoNormalizer'
102103

103104
Fitting the pipeline...
@@ -177,7 +178,7 @@ Image Classification
177178
178179
.. rst-class:: sphx-glr-timing
179180

180-
**Total running time of the script:** ( 0 minutes 6.439 seconds)
181+
**Total running time of the script:** ( 0 minutes 5.302 seconds)
181182

182183

183184
.. _sphx_glr_download_examples_20_basics_example_image_classification.py:

‎development/_sources/examples/20_basics/example_tabular_classification.rst.txt

Lines changed: 13 additions & 16 deletions
Original file line numberDiff line numberDiff line change
@@ -133,7 +133,7 @@ Search for an ensemble of machine learning algorithms
133133
.. code-block:: none
134134
135135
136-
<autoPyTorch.api.tabular_classification.TabularClassificationTask object at 0x7fe257cbbe50>
136+
<autoPyTorch.api.tabular_classification.TabularClassificationTask object at 0x7fc73f9a9cd0>
137137
138138
139139
@@ -162,7 +162,7 @@ Print the final ensemble performance
162162

163163
.. code-block:: none
164164
165-
<smac.runhistory.runhistory.RunHistory object at 0x7fe257b3a0d0> [TrajEntry(train_perf=2147483648, incumbent_id=1, incumbent=Configuration:
165+
<smac.runhistory.runhistory.RunHistory object at 0x7fc73f9a9ee0> [TrajEntry(train_perf=2147483648, incumbent_id=1, incumbent=Configuration:
166166
data_loader:batch_size, Value: 64
167167
encoder:__choice__, Value: 'OneHotEncoder'
168168
feature_preprocessor:__choice__, Value: 'NoFeaturePreprocessor'
@@ -194,7 +194,7 @@ Print the final ensemble performance
194194
scaler:__choice__, Value: 'StandardScaler'
195195
trainer:StandardTrainer:weighted_loss, Value: True
196196
trainer:__choice__, Value: 'StandardTrainer'
197-
, ta_runs=0, ta_time_used=0.0, wallclock_time=0.0010366439819335938, budget=0), TrajEntry(train_perf=0.17543859649122806, incumbent_id=1, incumbent=Configuration:
197+
, ta_runs=0, ta_time_used=0.0, wallclock_time=0.0012178421020507812, budget=0), TrajEntry(train_perf=0.17543859649122806, incumbent_id=1, incumbent=Configuration:
198198
data_loader:batch_size, Value: 64
199199
encoder:__choice__, Value: 'OneHotEncoder'
200200
feature_preprocessor:__choice__, Value: 'NoFeaturePreprocessor'
@@ -226,7 +226,7 @@ Print the final ensemble performance
226226
scaler:__choice__, Value: 'StandardScaler'
227227
trainer:StandardTrainer:weighted_loss, Value: True
228228
trainer:__choice__, Value: 'StandardTrainer'
229-
, ta_runs=1, ta_time_used=1.9255990982055664, wallclock_time=2.953387975692749, budget=5.555555555555555), TrajEntry(train_perf=0.14619883040935677, incumbent_id=2, incumbent=Configuration:
229+
, ta_runs=1, ta_time_used=1.8383204936981201, wallclock_time=2.867694139480591, budget=5.555555555555555), TrajEntry(train_perf=0.14619883040935677, incumbent_id=2, incumbent=Configuration:
230230
data_loader:batch_size, Value: 54
231231
encoder:__choice__, Value: 'OneHotEncoder'
232232
feature_preprocessor:__choice__, Value: 'NoFeaturePreprocessor'
@@ -259,29 +259,26 @@ Print the final ensemble performance
259259
trainer:MixUpTrainer:alpha, Value: 0.8559230573827334
260260
trainer:MixUpTrainer:weighted_loss, Value: True
261261
trainer:__choice__, Value: 'MixUpTrainer'
262-
, ta_runs=18, ta_time_used=170.50614953041077, wallclock_time=220.6971218585968, budget=50.0)]
262+
, ta_runs=18, ta_time_used=198.87974619865417, wallclock_time=247.5048122406006, budget=50.0)]
263263
{'accuracy': 0.861271676300578}
264264
| | Preprocessing | Estimator | Weight |
265265
|---:|:------------------------------------------------------------------|:----------------------------------------------------------------|---------:|
266-
| 0 | None | CatBoostClassifier | 0.28 |
267-
| 1 | SimpleImputer,NoEncoder,Normalizer,Nystroem | no embedding,ShapedMLPBackbone,FullyConnectedHead,nn.Sequential | 0.2 |
268-
| 2 | None | KNNClassifier | 0.1 |
269-
| 3 | SimpleImputer,OneHotEncoder,StandardScaler,NoFeaturePreprocessing | no embedding,ShapedMLPBackbone,FullyConnectedHead,nn.Sequential | 0.1 |
270-
| 4 | SimpleImputer,OneHotEncoder,StandardScaler,Nystroem | no embedding,ResNetBackbone,FullyConnectedHead,nn.Sequential | 0.06 |
271-
| 5 | None | LGBMClassifier | 0.06 |
272-
| 6 | None | RFClassifier | 0.06 |
266+
| 0 | SimpleImputer,NoEncoder,Normalizer,Nystroem | no embedding,ShapedMLPBackbone,FullyConnectedHead,nn.Sequential | 0.2 |
267+
| 1 | SimpleImputer,OneHotEncoder,StandardScaler,NoFeaturePreprocessing | no embedding,ShapedMLPBackbone,FullyConnectedHead,nn.Sequential | 0.2 |
268+
| 2 | None | CatBoostClassifier | 0.18 |
269+
| 3 | None | SVC | 0.18 |
270+
| 4 | None | RFClassifier | 0.08 |
271+
| 5 | None | ExtraTreesClassifier | 0.06 |
272+
| 6 | None | KNNClassifier | 0.06 |
273273
| 7 | SimpleImputer,OneHotEncoder,MinMaxScaler,NoFeaturePreprocessing | no embedding,ShapedMLPBackbone,FullyConnectedHead,nn.Sequential | 0.04 |
274-
| 8 | SimpleImputer,NoEncoder,NoScaler,NoFeaturePreprocessing | no embedding,ShapedMLPBackbone,FullyConnectedHead,nn.Sequential | 0.04 |
275-
| 9 | None | SVC | 0.04 |
276-
| 10 | SimpleImputer,OneHotEncoder,StandardScaler,NoFeaturePreprocessing | no embedding,ShapedMLPBackbone,FullyConnectedHead,nn.Sequential | 0.02 |
277274
278275
279276
280277
281278
282279
.. rst-class:: sphx-glr-timing
283280

284-
**Total running time of the script:** ( 5 minutes 24.537 seconds)
281+
**Total running time of the script:** ( 5 minutes 26.583 seconds)
285282

286283

287284
.. _sphx_glr_download_examples_20_basics_example_tabular_classification.py:

0 commit comments

Comments
 (0)