Fix version 0.2.0-dev3 and later

In this MR, version 0.2.0-dev3 (and later) is fixed:

• We use DPIAdjusting transform as it is a key component when training on images of very different sizes
• We compute the real mean and std values on the train set (we do not use default values from ImageNet = revert a5f7b5ab)
• The padding is on the right and bottom of the image (= revert part of f57bc667 for now)
• Two parameters files are created during training: one for training details (used to reproduce/continue the experiment), one for inference (that can be directly used by Arkindex DAN worker)

dan/datasets/extract/__init__.py

@@ -40,6 +40,15 @@ def validate_probability(proba):
     return proba
 
 
+def validate_char(char):
+    if len(char) != 1:
+        raise argparse.ArgumentTypeError(
+            f"`{char}` (of length {len(char)}) is not a valid character. Must be a string of length 1."
+        )
+
+    return char
+
+
 def add_extract_parser(subcommands) -> None:
     parser = subcommands.add_parser(
         "extract",
@@ -83,7 +92,20 @@ def add_extract_parser(subcommands) -> None:
 
     # Optional arguments.
     parser.add_argument(
-        "--load-entities", action="store_true", help="Extract text with their entities."
+        "--load-entities",
+        action="store_true",
+        help="Extract text with their entities.",
+    )
+    parser.add_argument(
+        "--entity-separators",
+        type=validate_char,
+        nargs="+",
+        help="""
+            Removes all text that does not appear in an entity or in the list of given ordered characters.
+            If several separators follow each other, keep only the first to appear in the list.
+            Do not give any arguments to keep the whole text.
+        """,
+        required=False,
     )
     parser.add_argument(
         "--tokens",