Ravin Kohli: [DOCS] Release notes v0.2.1 (#476)

Author: Github Actions

development/_downloads/bc82bea3a5dd7bdba60b65220891d9e5/examples_python.zip

@@ -33,22 +33,22 @@ Image Classification
 
     Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz
     Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz to ../datasets/FashionMNIST/raw/train-images-idx3-ubyte.gz
-      0%|          | 0/26421880 [00:00<?, ?it/s]      0%|          | 32768/26421880 [00:00<01:36, 273574.05it/s]      0%|          | 65536/26421880 [00:00<01:36, 272029.88it/s]      0%|          | 131072/26421880 [00:00<01:06, 395601.51it/s]      1%|          | 229376/26421880 [00:00<00:46, 560660.17it/s]      2%|1         | 491520/26421880 [00:00<00:22, 1140959.95it/s]      4%|3         | 950272/26421880 [00:00<00:12, 2042822.39it/s]      7%|7         | 1933312/26421880 [00:00<00:06, 4033969.41it/s]     15%|#4        | 3833856/26421880 [00:00<00:02, 7746025.35it/s]     26%|##6       | 6946816/26421880 [00:01<00:01, 13358825.50it/s]     38%|###7      | 10027008/26421880 [00:01<00:00, 17093733.49it/s]     50%|####9     | 13139968/26421880 [00:01<00:00, 19741478.86it/s]     61%|######1   | 16220160/26421880 [00:01<00:00, 21485812.46it/s]     73%|#######3  | 19333120/26421880 [00:01<00:00, 22775775.65it/s]     85%|########4 | 22446080/26421880 [00:01<00:00, 23652091.02it/s]     97%|#########6| 25559040/26421880 [00:01<00:00, 24300073.61it/s]    100%|##########| 26421880/26421880 [00:01<00:00, 14526598.00it/s]
+      0%|          | 0/26421880 [00:00<?, ?it/s]      0%|          | 65536/26421880 [00:00<01:11, 366290.45it/s]      1%|          | 163840/26421880 [00:00<00:41, 638849.88it/s]      2%|1         | 425984/26421880 [00:00<00:23, 1121398.14it/s]      5%|5         | 1343488/26421880 [00:00<00:06, 3583652.91it/s]     13%|#2        | 3375104/26421880 [00:00<00:03, 7221270.28it/s]     30%|##9       | 7798784/26421880 [00:00<00:01, 17052458.82it/s]     46%|####6     | 12222464/26421880 [00:00<00:00, 24527382.31it/s]     60%|######    | 15958016/26421880 [00:01<00:00, 24317522.28it/s]     75%|#######5  | 19857408/26421880 [00:01<00:00, 28004904.63it/s]     91%|######### | 23986176/26421880 [00:01<00:00, 31573997.04it/s]    100%|##########| 26421880/26421880 [00:01<00:00, 19482809.65it/s]
     Extracting ../datasets/FashionMNIST/raw/train-images-idx3-ubyte.gz to ../datasets/FashionMNIST/raw
 
     Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz
     Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz to ../datasets/FashionMNIST/raw/train-labels-idx1-ubyte.gz
-      0%|          | 0/29515 [00:00<?, ?it/s]    100%|##########| 29515/29515 [00:00<00:00, 243439.61it/s]    100%|##########| 29515/29515 [00:00<00:00, 242844.11it/s]
+      0%|          | 0/29515 [00:00<?, ?it/s]    100%|##########| 29515/29515 [00:00<00:00, 343239.68it/s]
     Extracting ../datasets/FashionMNIST/raw/train-labels-idx1-ubyte.gz to ../datasets/FashionMNIST/raw
 
     Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz
     Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz to ../datasets/FashionMNIST/raw/t10k-images-idx3-ubyte.gz
-      0%|          | 0/4422102 [00:00<?, ?it/s]      1%|          | 32768/4422102 [00:00<00:16, 270172.58it/s]      1%|1         | 65536/4422102 [00:00<00:16, 270051.73it/s]      3%|2         | 131072/4422102 [00:00<00:10, 392890.90it/s]      5%|5         | 229376/4422102 [00:00<00:07, 555118.43it/s]     10%|9         | 425984/4422102 [00:00<00:04, 940337.77it/s]     20%|##        | 884736/4422102 [00:00<00:01, 1905018.51it/s]     39%|###9      | 1736704/4422102 [00:00<00:00, 3572988.78it/s]     79%|#######8  | 3473408/4422102 [00:00<00:00, 6986586.93it/s]    100%|##########| 4422102/4422102 [00:00<00:00, 4540677.18it/s]
+      0%|          | 0/4422102 [00:00<?, ?it/s]      1%|1         | 65536/4422102 [00:00<00:11, 368748.32it/s]      4%|3         | 163840/4422102 [00:00<00:06, 620241.46it/s]     10%|9         | 425984/4422102 [00:00<00:03, 1127167.98it/s]     30%|##9       | 1310720/4422102 [00:00<00:00, 3413041.14it/s]     79%|#######8  | 3473408/4422102 [00:00<00:00, 7527372.13it/s]    100%|##########| 4422102/4422102 [00:00<00:00, 6146212.34it/s]
     Extracting ../datasets/FashionMNIST/raw/t10k-images-idx3-ubyte.gz to ../datasets/FashionMNIST/raw
 
     Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-labels-idx1-ubyte.gz
     Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-labels-idx1-ubyte.gz to ../datasets/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz
-      0%|          | 0/5148 [00:00<?, ?it/s]    100%|##########| 5148/5148 [00:00<00:00, 39473998.16it/s]
+      0%|          | 0/5148 [00:00<?, ?it/s]    100%|##########| 5148/5148 [00:00<00:00, 27969270.72it/s]
     Extracting ../datasets/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz to ../datasets/FashionMNIST/raw
 
     Pipeline CS:
@@ -84,26 +84,25 @@ Image Classification
      ________________________________________ 
     Configuration(values={
       'image_augmenter:GaussianBlur:use_augmenter': False,
-      'image_augmenter:GaussianNoise:sigma_offset': 2.899271560486781,
+      'image_augmenter:GaussianNoise:sigma_offset': 0.792548037014256,
       'image_augmenter:GaussianNoise:use_augmenter': True,
-      'image_augmenter:RandomAffine:rotate': 168,
-      'image_augmenter:RandomAffine:scale_offset': 0.22161745479713446,
-      'image_augmenter:RandomAffine:shear': 23,
-      'image_augmenter:RandomAffine:translate_percent_offset': 0.27323515878841953,
+      'image_augmenter:RandomAffine:rotate': 48,
+      'image_augmenter:RandomAffine:scale_offset': 0.19272327038467085,
+      'image_augmenter:RandomAffine:shear': 43,
+      'image_augmenter:RandomAffine:translate_percent_offset': 0.0386268474262987,
       'image_augmenter:RandomAffine:use_augmenter': True,
-      'image_augmenter:RandomCutout:p': 0.7562099317271191,
-      'image_augmenter:RandomCutout:use_augmenter': True,
+      'image_augmenter:RandomCutout:use_augmenter': False,
       'image_augmenter:Resize:use_augmenter': False,
-      'image_augmenter:ZeroPadAndCrop:percent': 0.007525257951395414,
-      'normalizer:__choice__': 'NoNormalizer',
+      'image_augmenter:ZeroPadAndCrop:percent': 0.15706347089750722,
+      'normalizer:__choice__': 'ImageNormalizer',
     })
 
     Fitting the pipeline...
     ________________________________________
             ImageClassificationPipeline
     ________________________________________
     0-) normalizer: 
-            NoNormalizer
+            ImageNormalizer
 
     1-) preprocessing: 
             EarlyPreprocessing
@@ -175,7 +174,7 @@ Image Classification
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 0 minutes  6.676 seconds)
+   **Total running time of the script:** ( 0 minutes  5.757 seconds)
 
 
 .. _sphx_glr_download_examples_20_basics_example_image_classification.py:

development/_downloads/fb625db3c50d423b1b7881136ffdeec8/examples_jupyter.zip

@@ -134,7 +134,7 @@ Search for an ensemble of machine learning algorithms
  .. code-block:: none
 
 
-    <autoPyTorch.api.tabular_classification.TabularClassificationTask object at 0x7fd7081a80a0>
+    <autoPyTorch.api.tabular_classification.TabularClassificationTask object at 0x7f9b36c175b0>
 
 
 
@@ -169,9 +169,9 @@ Print the final ensemble performance before refit
             Optimisation Metric: accuracy
             Best validation score: 0.8713450292397661
             Number of target algorithm runs: 27
-            Number of successful target algorithm runs: 26
+            Number of successful target algorithm runs: 25
             Number of crashed target algorithm runs: 0
-            Number of target algorithms that exceeded the time limit: 1
+            Number of target algorithms that exceeded the time limit: 2
             Number of target algorithms that exceeded the memory limit: 0
 
 
@@ -209,7 +209,7 @@ Refit the models on the full dataset.
  .. code-block:: none
 
 
-    <autoPyTorch.api.tabular_classification.TabularClassificationTask object at 0x7fd7081a80a0>
+    <autoPyTorch.api.tabular_classification.TabularClassificationTask object at 0x7f9b36c175b0>
 
 
 
@@ -252,7 +252,7 @@ Print the final ensemble performance after refit
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 6 minutes  50.005 seconds)
+   **Total running time of the script:** ( 6 minutes  50.591 seconds)
 
 
 .. _sphx_glr_download_examples_20_basics_example_tabular_classification.py:

development/_images/sphx_glr_example_plot_over_time_001.png

@@ -124,7 +124,7 @@ Search for an ensemble of machine learning algorithms
  .. code-block:: none
 
 
-    <autoPyTorch.api.tabular_regression.TabularRegressionTask object at 0x7fd79871c340>
+    <autoPyTorch.api.tabular_regression.TabularRegressionTask object at 0x7f9b36e8d220>
 
 
 
@@ -157,10 +157,10 @@ Print the final ensemble performance before refit
             Dataset name: Boston
             Optimisation Metric: r2
             Best validation score: 0.8670098636440993
-            Number of target algorithm runs: 24
+            Number of target algorithm runs: 23
             Number of successful target algorithm runs: 22
             Number of crashed target algorithm runs: 0
-            Number of target algorithms that exceeded the time limit: 2
+            Number of target algorithms that exceeded the time limit: 1
             Number of target algorithms that exceeded the memory limit: 0
 
 
@@ -200,7 +200,7 @@ Refit the models on the full dataset.
  .. code-block:: none
 
 
-    <autoPyTorch.api.tabular_regression.TabularRegressionTask object at 0x7fd79871c340>
+    <autoPyTorch.api.tabular_regression.TabularRegressionTask object at 0x7f9b36e8d220>
 
 
 
@@ -242,7 +242,7 @@ Print the final ensemble performance after refit
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 6 minutes  46.767 seconds)
+   **Total running time of the script:** ( 6 minutes  52.064 seconds)
 
 
 .. _sphx_glr_download_examples_20_basics_example_tabular_regression.py:

development/_images/sphx_glr_example_plot_over_time_thumb.png

@@ -150,7 +150,7 @@ Search for an ensemble of machine learning algorithms
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  2.712 seconds)
+   **Total running time of the script:** ( 1 minutes  1.047 seconds)
 
 
 .. _sphx_glr_download_examples_20_basics_example_time_series_forecasting.py: