Clean up legacy code

.gitignore

@@ -167,4 +167,7 @@ InnerEye-DataQuality/cifar-10-batches-py
 InnerEye-DataQuality/logs
 InnerEye-DataQuality/data
 
-!**/InnerEye/ML/Histopathology/datasets
+!**/InnerEye/ML/Histopathology/datasets
+None
+cifar-10-batches-py
+cifar-10-python.tar.gz

.vscode/settings.json

@@ -0,0 +1,8 @@
+{
+    "python.analysis.typeCheckingMode": "basic",
+    "python.testing.pytestArgs": [
+        "Tests"
+    ],
+    "python.testing.unittestEnabled": false,
+    "python.testing.pytestEnabled": true
+}

CHANGELOG.md

@@ -13,7 +13,7 @@ created.
 ## Upcoming
 
 ### Added
-
+-([#671](https://github.com/microsoft/InnerEye-DeepLearning/pull/671)) Remove sequence models and unused variables. Simplify README.
 - ([#678](https://github.com/microsoft/InnerEye-DeepLearning/pull/678)) Add function to get log level name and use it for logging.
 - ([#666](https://github.com/microsoft/InnerEye-DeepLearning/pull/666)) Replace RadIO with TorchIO for patch-based inference.
 - ([#643](https://github.com/microsoft/InnerEye-DeepLearning/pull/643)) Test for recovery of SSL job. Tracks learning rate and train

InnerEye/Azure/azure_config.py

@@ -24,8 +24,6 @@
 # The name of the "azureml" property of AzureConfig
 AZURECONFIG_SUBMIT_TO_AZUREML = "azureml"
 
-INPUT_DATA_KEY = "input_data"
-
 
 @dataclass(frozen=True)
 class GitInformation:

InnerEye/Azure/azure_runner.py

@@ -21,8 +21,6 @@
 from InnerEye.ML.common import ModelExecutionMode
 from InnerEye.ML.utils.config_loader import ModelConfigLoader
 
-SLEEP_TIME_SECONDS = 30
-
 DEFAULT_DOCKER_BASE_IMAGE = "mcr.microsoft.com/azureml/openmpi3.1.2-cuda10.2-cudnn8-ubuntu18.04"
 
 # Environment variables used for multi-node training

InnerEye/Common/Statistics/wilcoxon_signed_rank_test.py

@@ -52,8 +52,7 @@
 """
 
 from collections import defaultdict
-from itertools import filterfalse, tee
-from typing import Any, Callable, Dict, List, Optional, Tuple, Union
+from typing import Callable, Dict, List, Optional, Tuple, Union
 
 import matplotlib.pyplot as plt
 import numpy as np
@@ -67,8 +66,6 @@
 from InnerEye.Common.generic_parsing import GenericConfig
 from InnerEye.ML.visualizers.metrics_scatterplot import create_scatterplots
 
-INTERSECT = lambda l, r: np.intersect1d(l, r, False)
-
 """
 The factor by which the Wilcoxon Z value should be divided to allow for incomplete independence of the data.
 Experimentation (from comparing models built from exactly the same code and data, but different random seeds)
@@ -206,15 +203,6 @@ def compose_pairwise_result(threshold: float, results: Dict[str, Dict[str, float
     return []
 
 
-def partition_results(pred: Callable, results: List[Any]) -> Tuple[List[Any], List[Any]]:
-    """
-    Helper function to partition results into passed/failed
-    """
-    t1, t2 = tee(results)
-    map_func = lambda r: (r, results[r])
-    return list(map(map_func, filterfalse(pred, t1))), list(map(map_func, filter(pred, t2)))
-
-
 def read_data(csv_file: str, subset: str = 'all', exclude: Optional[List[str]] = None) \
         -> Dict[str, Dict[str, Dict[str, float]]]:
     """