Skip to content

Commit 900e0fa

Browse files
author
Github Actions
committed
chico: Fix flake after rebase
1 parent 03e0170 commit 900e0fa

File tree

11 files changed

+347
-63
lines changed

11 files changed

+347
-63
lines changed

‎refactor_development_regularization_cocktails/_downloads/bc82bea3a5dd7bdba60b65220891d9e5/examples_python.zip

0 Bytes
Binary file not shown.

‎refactor_development_regularization_cocktails/_downloads/fb625db3c50d423b1b7881136ffdeec8/examples_jupyter.zip

0 Bytes
Binary file not shown.

‎refactor_development_regularization_cocktails/_sources/examples/example_image_classification.rst.txt

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -82,12 +82,12 @@ Image Classification
8282
________________________________________
8383
Configuration:
8484
image_augmenter:GaussianBlur:use_augmenter, Value: False
85-
image_augmenter:GaussianNoise:use_augmenter, Value: False
85+
image_augmenter:GaussianNoise:sigma_offset, Value: 0.06760375648487404
86+
image_augmenter:GaussianNoise:use_augmenter, Value: True
8687
image_augmenter:RandomAffine:use_augmenter, Value: False
87-
image_augmenter:RandomCutout:p, Value: 0.4491042884164836
88-
image_augmenter:RandomCutout:use_augmenter, Value: True
89-
image_augmenter:Resize:use_augmenter, Value: False
90-
image_augmenter:ZeroPadAndCrop:percent, Value: 0.1873411445843785
88+
image_augmenter:RandomCutout:use_augmenter, Value: False
89+
image_augmenter:Resize:use_augmenter, Value: True
90+
image_augmenter:ZeroPadAndCrop:percent, Value: 0.41131456158998475
9191
normalizer:__choice__, Value: 'NoNormalizer'
9292

9393
Fitting the pipeline...
@@ -167,7 +167,7 @@ Image Classification
167167
168168
.. rst-class:: sphx-glr-timing
169169

170-
**Total running time of the script:** ( 0 minutes 9.507 seconds)
170+
**Total running time of the script:** ( 0 minutes 9.811 seconds)
171171

172172

173173
.. _sphx_glr_download_examples_example_image_classification.py:

‎refactor_development_regularization_cocktails/_sources/examples/example_tabular_classification.rst.txt

Lines changed: 122 additions & 16 deletions
Original file line numberDiff line numberDiff line change
@@ -36,7 +36,7 @@ with AutoPyTorch
3636

3737
.. code-block:: none
3838
39-
<smac.runhistory.runhistory.RunHistory object at 0x7f8dc0605e80> [TrajEntry(train_perf=2147483648, incumbent_id=1, incumbent=Configuration:
39+
<smac.runhistory.runhistory.RunHistory object at 0x7f9add238610> [TrajEntry(train_perf=2147483648, incumbent_id=1, incumbent=Configuration:
4040
data_loader:batch_size, Value: 32
4141
encoder:__choice__, Value: 'OneHotEncoder'
4242
feature_preprocessor:__choice__, Value: 'NoFeaturePreprocessor'
@@ -53,6 +53,16 @@ with AutoPyTorch
5353
network_backbone:ShapedMLPBackbone:output_dim, Value: 200
5454
network_backbone:ShapedMLPBackbone:use_dropout, Value: False
5555
network_backbone:__choice__, Value: 'ShapedMLPBackbone'
56+
network_embedding:LearnedEntityEmbedding:dimension_reduction_0, Value: 0.5
57+
network_embedding:LearnedEntityEmbedding:dimension_reduction_1, Value: 0.5
58+
network_embedding:LearnedEntityEmbedding:dimension_reduction_2, Value: 0.5
59+
network_embedding:LearnedEntityEmbedding:dimension_reduction_3, Value: 0.5
60+
network_embedding:LearnedEntityEmbedding:dimension_reduction_4, Value: 0.5
61+
network_embedding:LearnedEntityEmbedding:dimension_reduction_5, Value: 0.5
62+
network_embedding:LearnedEntityEmbedding:dimension_reduction_6, Value: 0.5
63+
network_embedding:LearnedEntityEmbedding:dimension_reduction_7, Value: 0.5
64+
network_embedding:LearnedEntityEmbedding:min_unique_values_for_embedding, Value: 5
65+
network_embedding:__choice__, Value: 'LearnedEntityEmbedding'
5666
network_head:__choice__, Value: 'fully_connected'
5767
network_head:fully_connected:activation, Value: 'relu'
5868
network_head:fully_connected:num_layers, Value: 2
@@ -74,7 +84,7 @@ with AutoPyTorch
7484
trainer:StandardTrainer:use_stochastic_weight_averaging, Value: True
7585
trainer:StandardTrainer:weighted_loss, Value: True
7686
trainer:__choice__, Value: 'StandardTrainer'
77-
, ta_runs=0, ta_time_used=0.0, wallclock_time=0.002054929733276367, budget=0), TrajEntry(train_perf=0.15204678362573099, incumbent_id=1, incumbent=Configuration:
87+
, ta_runs=0, ta_time_used=0.0, wallclock_time=0.0023033618927001953, budget=0), TrajEntry(train_perf=0.19298245614035092, incumbent_id=1, incumbent=Configuration:
7888
data_loader:batch_size, Value: 32
7989
encoder:__choice__, Value: 'OneHotEncoder'
8090
feature_preprocessor:__choice__, Value: 'NoFeaturePreprocessor'
@@ -91,6 +101,16 @@ with AutoPyTorch
91101
network_backbone:ShapedMLPBackbone:output_dim, Value: 200
92102
network_backbone:ShapedMLPBackbone:use_dropout, Value: False
93103
network_backbone:__choice__, Value: 'ShapedMLPBackbone'
104+
network_embedding:LearnedEntityEmbedding:dimension_reduction_0, Value: 0.5
105+
network_embedding:LearnedEntityEmbedding:dimension_reduction_1, Value: 0.5
106+
network_embedding:LearnedEntityEmbedding:dimension_reduction_2, Value: 0.5
107+
network_embedding:LearnedEntityEmbedding:dimension_reduction_3, Value: 0.5
108+
network_embedding:LearnedEntityEmbedding:dimension_reduction_4, Value: 0.5
109+
network_embedding:LearnedEntityEmbedding:dimension_reduction_5, Value: 0.5
110+
network_embedding:LearnedEntityEmbedding:dimension_reduction_6, Value: 0.5
111+
network_embedding:LearnedEntityEmbedding:dimension_reduction_7, Value: 0.5
112+
network_embedding:LearnedEntityEmbedding:min_unique_values_for_embedding, Value: 5
113+
network_embedding:__choice__, Value: 'LearnedEntityEmbedding'
94114
network_head:__choice__, Value: 'fully_connected'
95115
network_head:fully_connected:activation, Value: 'relu'
96116
network_head:fully_connected:num_layers, Value: 2
@@ -112,19 +132,105 @@ with AutoPyTorch
112132
trainer:StandardTrainer:use_stochastic_weight_averaging, Value: True
113133
trainer:StandardTrainer:weighted_loss, Value: True
114134
trainer:__choice__, Value: 'StandardTrainer'
115-
, ta_runs=1, ta_time_used=4.633003234863281, wallclock_time=6.036682844161987, budget=5.555555555555555)]
116-
{'accuracy': 0.8670520231213873}
117-
| | Preprocessing | Estimator | Weight |
118-
|---:|:------------------------------------------------------------------|:------------------------------------------------------|---------:|
119-
| 0 | None | ExtraTreesClassifier | 0.24 |
120-
| 1 | None | RFClassifier | 0.2 |
121-
| 2 | SimpleImputer,OneHotEncoder,StandardScaler,NoFeaturePreprocessing | ShapedMLPBackbone,FullyConnectedHead,nn.Sequential | 0.18 |
122-
| 3 | None | KNNClassifier | 0.1 |
123-
| 4 | None | LGBMClassifier | 0.1 |
124-
| 5 | SimpleImputer,OneHotEncoder,NoScaler,NoFeaturePreprocessing | ShapedResNetBackbone,FullyConnectedHead,nn.Sequential | 0.06 |
125-
| 6 | None | SVC | 0.06 |
126-
| 7 | SimpleImputer,NoEncoder,Normalizer,KitchenSink | ShapedMLPBackbone,FullyConnectedHead,nn.Sequential | 0.04 |
127-
| 8 | SimpleImputer,OneHotEncoder,NoScaler,NoFeaturePreprocessing | ShapedResNetBackbone,FullyConnectedHead,nn.Sequential | 0.02 |
135+
, ta_runs=1, ta_time_used=5.061767578125, wallclock_time=6.761995077133179, budget=5.555555555555555), TrajEntry(train_perf=0.15204678362573099, incumbent_id=2, incumbent=Configuration:
136+
data_loader:batch_size, Value: 75
137+
encoder:__choice__, Value: 'OneHotEncoder'
138+
feature_preprocessor:RandomKitchenSinks:gamma, Value: 0.013010719396102707
139+
feature_preprocessor:RandomKitchenSinks:n_components, Value: 6
140+
feature_preprocessor:__choice__, Value: 'RandomKitchenSinks'
141+
imputer:categorical_strategy, Value: 'most_frequent'
142+
imputer:numerical_strategy, Value: 'most_frequent'
143+
lr_scheduler:CosineAnnealingLR:T_max, Value: 51
144+
lr_scheduler:__choice__, Value: 'CosineAnnealingLR'
145+
network_backbone:ResNetBackbone:activation, Value: 'tanh'
146+
network_backbone:ResNetBackbone:blocks_per_group_0, Value: 2
147+
network_backbone:ResNetBackbone:blocks_per_group_1, Value: 3
148+
network_backbone:ResNetBackbone:multi_branch_choice, Value: 'shake-shake'
149+
network_backbone:ResNetBackbone:num_groups, Value: 1
150+
network_backbone:ResNetBackbone:num_units_0, Value: 891
151+
network_backbone:ResNetBackbone:num_units_1, Value: 534
152+
network_backbone:ResNetBackbone:use_batch_norm, Value: False
153+
network_backbone:ResNetBackbone:use_dropout, Value: False
154+
network_backbone:ResNetBackbone:use_skip_connection, Value: True
155+
network_backbone:__choice__, Value: 'ResNetBackbone'
156+
network_embedding:__choice__, Value: 'NoEmbedding'
157+
network_head:__choice__, Value: 'fully_connected'
158+
network_head:fully_connected:activation, Value: 'tanh'
159+
network_head:fully_connected:num_layers, Value: 2
160+
network_head:fully_connected:units_layer_1, Value: 81
161+
network_init:SparseInit:bias_strategy, Value: 'Normal'
162+
network_init:__choice__, Value: 'SparseInit'
163+
optimizer:RMSpropOptimizer:alpha, Value: 0.3529523814951323
164+
optimizer:RMSpropOptimizer:lr, Value: 0.016961171655317835
165+
optimizer:RMSpropOptimizer:momentum, Value: 0.7920241884670927
166+
optimizer:RMSpropOptimizer:use_weight_decay, Value: True
167+
optimizer:RMSpropOptimizer:weight_decay, Value: 0.032552201041967745
168+
optimizer:__choice__, Value: 'RMSpropOptimizer'
169+
scaler:Normalizer:norm, Value: 'mean_squared'
170+
scaler:__choice__, Value: 'Normalizer'
171+
trainer:MixUpTrainer:Lookahead:la_alpha, Value: 0.5098588977236024
172+
trainer:MixUpTrainer:Lookahead:la_steps, Value: 9
173+
trainer:MixUpTrainer:alpha, Value: 0.9489967007329774
174+
trainer:MixUpTrainer:se_lastk, Constant: 3
175+
trainer:MixUpTrainer:use_lookahead_optimizer, Value: True
176+
trainer:MixUpTrainer:use_snapshot_ensemble, Value: True
177+
trainer:MixUpTrainer:use_stochastic_weight_averaging, Value: False
178+
trainer:MixUpTrainer:weighted_loss, Value: False
179+
trainer:__choice__, Value: 'MixUpTrainer'
180+
, ta_runs=19, ta_time_used=214.1450550556183, wallclock_time=279.02319598197937, budget=50.0), TrajEntry(train_perf=0.11695906432748537, incumbent_id=3, incumbent=Configuration:
181+
data_loader:batch_size, Value: 222
182+
encoder:__choice__, Value: 'OneHotEncoder'
183+
feature_preprocessor:Nystroem:kernel, Value: 'cosine'
184+
feature_preprocessor:Nystroem:n_components, Value: 6
185+
feature_preprocessor:__choice__, Value: 'Nystroem'
186+
imputer:categorical_strategy, Value: 'most_frequent'
187+
imputer:numerical_strategy, Value: 'most_frequent'
188+
lr_scheduler:__choice__, Value: 'NoScheduler'
189+
network_backbone:ShapedResNetBackbone:activation, Value: 'relu'
190+
network_backbone:ShapedResNetBackbone:blocks_per_group, Value: 2
191+
network_backbone:ShapedResNetBackbone:max_units, Value: 793
192+
network_backbone:ShapedResNetBackbone:multi_branch_choice, Value: 'shake-shake'
193+
network_backbone:ShapedResNetBackbone:num_groups, Value: 1
194+
network_backbone:ShapedResNetBackbone:output_dim, Value: 408
195+
network_backbone:ShapedResNetBackbone:resnet_shape, Value: 'diamond'
196+
network_backbone:ShapedResNetBackbone:use_batch_norm, Value: True
197+
network_backbone:ShapedResNetBackbone:use_dropout, Value: False
198+
network_backbone:ShapedResNetBackbone:use_skip_connection, Value: True
199+
network_backbone:__choice__, Value: 'ShapedResNetBackbone'
200+
network_embedding:__choice__, Value: 'NoEmbedding'
201+
network_head:__choice__, Value: 'fully_connected'
202+
network_head:fully_connected:activation, Value: 'relu'
203+
network_head:fully_connected:num_layers, Value: 2
204+
network_head:fully_connected:units_layer_1, Value: 342
205+
network_init:NoInit:bias_strategy, Value: 'Normal'
206+
network_init:__choice__, Value: 'NoInit'
207+
optimizer:RMSpropOptimizer:alpha, Value: 0.31508999898669854
208+
optimizer:RMSpropOptimizer:lr, Value: 0.000141083113558384
209+
optimizer:RMSpropOptimizer:momentum, Value: 0.4310565312768747
210+
optimizer:RMSpropOptimizer:use_weight_decay, Value: False
211+
optimizer:__choice__, Value: 'RMSpropOptimizer'
212+
scaler:Normalizer:norm, Value: 'mean_squared'
213+
scaler:__choice__, Value: 'Normalizer'
214+
trainer:AdversarialTrainer:epsilon, Value: 0.13573947533310454
215+
trainer:AdversarialTrainer:se_lastk, Constant: 3
216+
trainer:AdversarialTrainer:use_lookahead_optimizer, Value: False
217+
trainer:AdversarialTrainer:use_snapshot_ensemble, Value: True
218+
trainer:AdversarialTrainer:use_stochastic_weight_averaging, Value: True
219+
trainer:AdversarialTrainer:weighted_loss, Value: False
220+
trainer:__choice__, Value: 'AdversarialTrainer'
221+
, ta_runs=20, ta_time_used=233.27314519882202, wallclock_time=302.0042383670807, budget=50.0)]
222+
{'accuracy': 0.8959537572254336}
223+
| | Preprocessing | Estimator | Weight |
224+
|---:|:------------------------------------------------------------------|:-------------------------------------------------------------------|---------:|
225+
| 0 | None | CatBoostClassifier | 0.34 |
226+
| 1 | SimpleImputer,NoEncoder,Normalizer,NoFeaturePreprocessing | no embedding,ShapedResNetBackbone,FullyConnectedHead,nn.Sequential | 0.16 |
227+
| 2 | SimpleImputer,OneHotEncoder,Normalizer,Nystroem | no embedding,ShapedResNetBackbone,FullyConnectedHead,nn.Sequential | 0.16 |
228+
| 3 | SimpleImputer,OneHotEncoder,StandardScaler,TruncSVD | no embedding,ResNetBackbone,FullyConnectedHead,nn.Sequential | 0.12 |
229+
| 4 | SimpleImputer,OneHotEncoder,Normalizer,KitchenSink | no embedding,ResNetBackbone,FullyConnectedHead,nn.Sequential | 0.12 |
230+
| 5 | SimpleImputer,OneHotEncoder,StandardScaler,Nystroem | no embedding,ResNetBackbone,FullyConnectedHead,nn.Sequential | 0.04 |
231+
| 6 | None | KNNClassifier | 0.02 |
232+
| 7 | None | RFClassifier | 0.02 |
233+
| 8 | SimpleImputer,OneHotEncoder,StandardScaler,NoFeaturePreprocessing | embedding,ShapedMLPBackbone,FullyConnectedHead,nn.Sequential | 0.02 |
128234
129235
130236
@@ -216,7 +322,7 @@ with AutoPyTorch
216322
217323
.. rst-class:: sphx-glr-timing
218324

219-
**Total running time of the script:** ( 9 minutes 10.916 seconds)
325+
**Total running time of the script:** ( 9 minutes 20.536 seconds)
220326

221327

222328
.. _sphx_glr_download_examples_example_tabular_classification.py:

‎refactor_development_regularization_cocktails/_sources/examples/example_tabular_regression.rst.txt

Lines changed: 41 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -36,7 +36,7 @@ with AutoPyTorch
3636

3737
.. code-block:: none
3838
39-
<smac.runhistory.runhistory.RunHistory object at 0x7f8db89aa610> [TrajEntry(train_perf=2147483648, incumbent_id=1, incumbent=Configuration:
39+
<smac.runhistory.runhistory.RunHistory object at 0x7f9ac706ba90> [TrajEntry(train_perf=2147483648, incumbent_id=1, incumbent=Configuration:
4040
data_loader:batch_size, Value: 32
4141
encoder:__choice__, Value: 'NoEncoder'
4242
imputer:numerical_strategy, Value: 'mean'
@@ -51,6 +51,7 @@ with AutoPyTorch
5151
network_backbone:ShapedMLPBackbone:output_dim, Value: 200
5252
network_backbone:ShapedMLPBackbone:use_dropout, Value: False
5353
network_backbone:__choice__, Value: 'ShapedMLPBackbone'
54+
network_embedding:__choice__, Value: 'NoEmbedding'
5455
network_head:__choice__, Value: 'fully_connected'
5556
network_head:fully_connected:activation, Value: 'relu'
5657
network_head:fully_connected:num_layers, Value: 2
@@ -71,7 +72,7 @@ with AutoPyTorch
7172
trainer:StandardTrainer:use_snapshot_ensemble, Value: True
7273
trainer:StandardTrainer:use_stochastic_weight_averaging, Value: True
7374
trainer:__choice__, Value: 'StandardTrainer'
74-
, ta_runs=0, ta_time_used=0.0, wallclock_time=0.002081155776977539, budget=0), TrajEntry(train_perf=0.0008380038823507796, incumbent_id=1, incumbent=Configuration:
75+
, ta_runs=0, ta_time_used=0.0, wallclock_time=0.002161741256713867, budget=0), TrajEntry(train_perf=0.0023124620313044186, incumbent_id=1, incumbent=Configuration:
7576
data_loader:batch_size, Value: 32
7677
encoder:__choice__, Value: 'NoEncoder'
7778
imputer:numerical_strategy, Value: 'mean'
@@ -86,6 +87,7 @@ with AutoPyTorch
8687
network_backbone:ShapedMLPBackbone:output_dim, Value: 200
8788
network_backbone:ShapedMLPBackbone:use_dropout, Value: False
8889
network_backbone:__choice__, Value: 'ShapedMLPBackbone'
90+
network_embedding:__choice__, Value: 'NoEmbedding'
8991
network_head:__choice__, Value: 'fully_connected'
9092
network_head:fully_connected:activation, Value: 'relu'
9193
network_head:fully_connected:num_layers, Value: 2
@@ -106,8 +108,42 @@ with AutoPyTorch
106108
trainer:StandardTrainer:use_snapshot_ensemble, Value: True
107109
trainer:StandardTrainer:use_stochastic_weight_averaging, Value: True
108110
trainer:__choice__, Value: 'StandardTrainer'
109-
, ta_runs=1, ta_time_used=7.325408458709717, wallclock_time=10.74347996711731, budget=5.555555555555555)]
110-
{'r2': 0.9998081051474011}
111+
, ta_runs=1, ta_time_used=7.577795028686523, wallclock_time=11.378600358963013, budget=5.555555555555555), TrajEntry(train_perf=0.007724043300765815, incumbent_id=2, incumbent=Configuration:
112+
data_loader:batch_size, Value: 502
113+
encoder:__choice__, Value: 'NoEncoder'
114+
imputer:numerical_strategy, Value: 'most_frequent'
115+
lr_scheduler:__choice__, Value: 'NoScheduler'
116+
network_backbone:ShapedResNetBackbone:activation, Value: 'tanh'
117+
network_backbone:ShapedResNetBackbone:blocks_per_group, Value: 1
118+
network_backbone:ShapedResNetBackbone:max_dropout, Value: 0.1517368709538051
119+
network_backbone:ShapedResNetBackbone:max_units, Value: 254
120+
network_backbone:ShapedResNetBackbone:multi_branch_choice, Value: 'shake-shake'
121+
network_backbone:ShapedResNetBackbone:num_groups, Value: 7
122+
network_backbone:ShapedResNetBackbone:output_dim, Value: 126
123+
network_backbone:ShapedResNetBackbone:resnet_shape, Value: 'brick'
124+
network_backbone:ShapedResNetBackbone:use_batch_norm, Value: False
125+
network_backbone:ShapedResNetBackbone:use_dropout, Value: True
126+
network_backbone:ShapedResNetBackbone:use_skip_connection, Value: True
127+
network_backbone:__choice__, Value: 'ShapedResNetBackbone'
128+
network_embedding:__choice__, Value: 'NoEmbedding'
129+
network_head:__choice__, Value: 'fully_connected'
130+
network_head:fully_connected:num_layers, Value: 1
131+
network_init:NoInit:bias_strategy, Value: 'Normal'
132+
network_init:__choice__, Value: 'NoInit'
133+
optimizer:AdamOptimizer:beta1, Value: 0.9481379615749385
134+
optimizer:AdamOptimizer:beta2, Value: 0.975978385169487
135+
optimizer:AdamOptimizer:lr, Value: 0.01924341974264098
136+
optimizer:AdamOptimizer:use_weight_decay, Value: False
137+
optimizer:__choice__, Value: 'AdamOptimizer'
138+
scaler:__choice__, Value: 'NoScaler'
139+
trainer:MixUpTrainer:alpha, Value: 0.6106245467721916
140+
trainer:MixUpTrainer:se_lastk, Constant: 3
141+
trainer:MixUpTrainer:use_lookahead_optimizer, Value: False
142+
trainer:MixUpTrainer:use_snapshot_ensemble, Value: True
143+
trainer:MixUpTrainer:use_stochastic_weight_averaging, Value: True
144+
trainer:__choice__, Value: 'MixUpTrainer'
145+
, ta_runs=17, ta_time_used=294.1746070384979, wallclock_time=344.89423751831055, budget=50.0)]
146+
{'r2': 0.9996698482299967}
111147
112148
113149
@@ -230,7 +266,7 @@ with AutoPyTorch
230266
231267
.. rst-class:: sphx-glr-timing
232268

233-
**Total running time of the script:** ( 8 minutes 38.489 seconds)
269+
**Total running time of the script:** ( 8 minutes 35.774 seconds)
234270

235271

236272
.. _sphx_glr_download_examples_example_tabular_regression.py:

0 commit comments

Comments
 (0)