bugfix: Alignment tool, auto-detect alignments

- Random linting and typing

lib/image.py

@@ -579,7 +579,7 @@ def encode_image(image: np.ndarray,
     Returns
     -------
     encoded_image: bytes
-        The image encoded into the correct file format
+        The image encoded into the correct file format as bytes
 
     Example
     -------
@@ -591,10 +591,10 @@ def encode_image(image: np.ndarray,
         raise ValueError("Metadata is only supported for .png and .tif images")
     args = tuple() if encoding_args is None else encoding_args
 
-    retval = cv2.imencode(extension, image, args)[1]
+    retval = cv2.imencode(extension, image, args)[1].tobytes()
     if metadata:
         func = {".png": png_write_meta, ".tif": tiff_write_meta}[extension]
-        retval = func(retval.tobytes(), metadata)  # type:ignore[arg-type]
+        retval = func(retval, metadata)
     return retval
 
 
@@ -624,7 +624,7 @@ def png_write_meta(image: bytes, data: PNGHeaderDict | dict[str, T.Any] | bytes)
     return retval
 
 
-def tiff_write_meta(image: bytes, data: dict[str, T.Any] | bytes) -> bytes:
+def tiff_write_meta(image: bytes, data: PNGHeaderDict | dict[str, T.Any] | bytes) -> bytes:
     """ Write Faceswap information to a tiff's image_description field.
 
     Parameters

lib/training/generator.py

@@ -57,7 +57,7 @@ def __init__(self,
                  side: T.Literal["a", "b"],
                  images: list[str],
                  batch_size: int) -> None:
-        logger.debug("Initializing %s: (model: %s, side: %s, images: %s , "  # type: ignore
+        logger.debug("Initializing %s: (model: %s, side: %s, images: %s , "
                      "batch_size: %s, config: %s)", self.__class__.__name__, model.name, side,
                      len(images), batch_size, config)
         self._config = config
@@ -243,8 +243,9 @@ def _get_images_with_meta(self, filenames: list[str]) -> tuple[np.ndarray, list[
             raw_faces = read_image_batch(filenames)
 
         detected_faces = self._face_cache.get_items(filenames)
-        logger.trace("filenames: %s, raw_faces: '%s', detected_faces: %s",  # type: ignore
-                     filenames, raw_faces.shape, len(detected_faces))
+        logger.trace(  # type:ignore[attr-defined]
+            "filenames: %s, raw_faces: '%s', detected_faces: %s",
+            filenames, raw_faces.shape, len(detected_faces))
         return raw_faces, detected_faces
 
     def _crop_to_coverage(self,
@@ -271,8 +272,8 @@ def _crop_to_coverage(self,
         batch: :class:`np.ndarray`
             The pre-allocated array to hold this batch
         """
-        logger.trace("Cropping training images info: (filenames: %s, side: '%s')",  # type: ignore
-                     filenames, self._side)
+        logger.trace(  # type:ignore[attr-defined]
+            "Cropping training images info: (filenames: %s, side: '%s')", filenames, self._side)
 
         with futures.ThreadPoolExecutor() as executor:
             proc = {executor.submit(face.aligned.extract_face, img): idx
@@ -304,7 +305,7 @@ def _apply_mask(self, detected_faces: list[DetectedFace], batch: np.ndarray) ->
         masks = np.array([face.get_training_masks() for face in detected_faces])
         batch[..., 3:] = masks
 
-        logger.trace("side: %s, masks: %s, batch: %s",  # type: ignore
+        logger.trace("side: %s, masks: %s, batch: %s",  # type:ignore[attr-defined]
                      self._side, masks.shape, batch.shape)
 
     def _process_batch(self, filenames: list[str]) -> BatchType:
@@ -333,9 +334,9 @@ def _process_batch(self, filenames: list[str]) -> BatchType:
         self._apply_mask(detected_faces, batch)
         feed, targets = self.process_batch(filenames, raw_faces, detected_faces, batch)
 
-        logger.trace("Processed %s batch side %s. (filenames: %s, feed: %s, "  # type: ignore
-                     "targets: %s)", self.__class__.__name__, self._side, filenames,
-                     feed.shape, [t.shape for t in targets])
+        logger.trace(  # type:ignore[attr-defined]
+            "Processed %s batch side %s. (filenames: %s, feed: %s, targets: %s)",
+            self.__class__.__name__, self._side, filenames, feed.shape, [t.shape for t in targets])
 
         return feed, targets
 
@@ -450,15 +451,19 @@ def _create_targets(self, batch: np.ndarray) -> list[np.ndarray]:
             List of 4-dimensional target images, at all model output sizes, with masks compiled
             into channels 4+ for each output size
         """
-        logger.trace("Compiling targets: batch shape: %s", batch.shape)  # type: ignore
+        logger.trace("Compiling targets: batch shape: %s",  # type:ignore[attr-defined]
+                     batch.shape)
         if len(self._output_sizes) == 1 and self._output_sizes[0] == self._process_size:
             # Rolling buffer here makes next to no difference, so just create array on the fly
             retval = [self._to_float32(batch)]
         else:
-            retval = [self._to_float32(np.array([cv2.resize(image, (size, size), cv2.INTER_AREA)
+            retval = [self._to_float32(np.array([cv2.resize(image,
+                                                            (size, size),
+                                                            interpolation=cv2.INTER_AREA)
                                                  for image in batch]))
                       for size in self._output_sizes]
-        logger.trace("Processed targets: %s", [t.shape for t in retval])  # type: ignore
+        logger.trace("Processed targets: %s",  # type:ignore[attr-defined]
+                     [t.shape for t in retval])
         return retval
 
     def process_batch(self,
@@ -533,7 +538,7 @@ def process_batch(self,
             feed = self._to_float32(np.array([cv2.resize(image,
                                                          (self._model_input_size,
                                                           self._model_input_size),
-                                                         cv2.INTER_AREA)
+                                                         interpolation=cv2.INTER_AREA)
                                               for image in warped]))
         else:
             feed = self._to_float32(warped)
@@ -556,8 +561,9 @@ def _get_closest_match(self, filenames: list[str], batch_src_points: np.ndarray)
         :class:`np.ndarray`
             Randomly selected closest matches from the other side's landmarks
         """
-        logger.trace("Retrieving closest matched landmarks: (filenames: '%s', "  # type: ignore
-                     "src_points: '%s')", filenames, batch_src_points)
+        logger.trace(  # type:ignore[attr-defined]
+            "Retrieving closest matched landmarks: (filenames: '%s', src_points: '%s')",
+            filenames, batch_src_points)
         lm_side: T.Literal["a", "b"] = "a" if self._side == "b" else "b"
         other_cache = get_cache(lm_side)
         landmarks = other_cache.aligned_landmarks
@@ -575,7 +581,8 @@ def _get_closest_match(self, filenames: list[str], batch_src_points: np.ndarray)
             closest_matches = self._cache_closest_matches(filenames, batch_src_points, landmarks)
 
         batch_dst_points = np.array([landmarks[choice(fname)] for fname in closest_matches])
-        logger.trace("Returning: (batch_dst_points: %s)", batch_dst_points.shape)  # type: ignore
+        logger.trace("Returning: (batch_dst_points: %s)",  # type:ignore[attr-defined]
+                     batch_dst_points.shape)
         return batch_dst_points
 
     def _cache_closest_matches(self,
@@ -648,8 +655,9 @@ def _create_samples(self,
         list
             List of 4-dimensional target images, at final model output size
         """
-        logger.trace("Compiling samples: images shape: %s, detected_faces: %s ",  # type: ignore
-                     images.shape, len(detected_faces))
+        logger.trace(  # type:ignore[attr-defined]
+            "Compiling samples: images shape: %s, detected_faces: %s ",
+            images.shape, len(detected_faces))
         output_size = self._output_sizes[-1]
         full_size = 2 * int(np.rint((output_size / self._coverage_ratio) / 2))
 
@@ -665,7 +673,7 @@ def _create_samples(self,
                         is_aligned=True).face
             for idx, face in enumerate(detected_faces)]))
 
-        logger.trace("Processed samples: %s", retval.shape)  # type: ignore
+        logger.trace("Processed samples: %s", retval.shape)  # type:ignore[attr-defined]
         return [retval]
 
     def process_batch(self,
@@ -840,8 +848,9 @@ def get_batch(self) -> tuple[list[list[np.ndarray]], ...]:
             side_feed, side_targets = next(self._feeds[side])
             if self._model.config["learn_mask"]:  # Add the face mask as it's own target
                 side_targets += [side_targets[-1][..., 3][..., None]]
-            logger.trace("side: %s, input_shapes: %s, target_shapes: %s",  # type: ignore
-                         side, side_feed.shape, [i.shape for i in side_targets])
+            logger.trace(  # type:ignore[attr-defined]
+                "side: %s, input_shapes: %s, target_shapes: %s",
+                side, side_feed.shape, [i.shape for i in side_targets])
             model_inputs.append([side_feed])
             model_targets.append(side_targets)
 

locales/es/LC_MESSAGES/tools.alignments.cli.po

@@ -6,8 +6,8 @@ msgid ""
 msgstr ""
 "Project-Id-Version: faceswap.spanish\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2024-04-12 12:10+0100\n"
-"PO-Revision-Date: 2024-04-12 12:14+0100\n"
+"POT-Creation-Date: 2024-04-19 11:28+0100\n"
+"PO-Revision-Date: 2024-04-19 11:29+0100\n"
 "Last-Translator: \n"
 "Language-Team: tokafondo\n"
 "Language: es_ES\n"
@@ -37,29 +37,29 @@ msgstr ""
 "archivo de alineación."
 
 #: tools/alignments/cli.py:43
-msgid " Must Pass in a frames folder/source video file (-fr)."
+msgid " Must Pass in a frames folder/source video file (-r)."
 msgstr ""
-" Debe indicar una carpeta de fotogramas o archivo de vídeo de origen (-fr)."
+" Debe indicar una carpeta de fotogramas o archivo de vídeo de origen (-r)."
 
 #: tools/alignments/cli.py:44
-msgid " Must Pass in a faces folder (-fc)."
-msgstr " Debe indicar una carpeta de caras (-fc)."
+msgid " Must Pass in a faces folder (-c)."
+msgstr " Debe indicar una carpeta de caras (-c)."
 
 #: tools/alignments/cli.py:45
 msgid ""
-" Must Pass in either a frames folder/source video file OR a faces folder (-"
-"fr or -fc)."
+" Must Pass in either a frames folder/source video file OR a faces folder (-r "
+"or -c)."
 msgstr ""
 " Debe indicar una carpeta de fotogramas o archivo de vídeo de origen, o una "
-"carpeta de caras (-fr o -fc)."
+"carpeta de caras (-r o -c)."
 
 #: tools/alignments/cli.py:47
 msgid ""
-" Must Pass in a frames folder/source video file AND a faces folder (-fr and -"
-"fc)."
+" Must Pass in a frames folder/source video file AND a faces folder (-r and -"
+"c)."
 msgstr ""
 " Debe indicar una carpeta de fotogramas o archivo de vídeo de origen, y una "
-"carpeta de caras (-fr y -fc)."
+"carpeta de caras (-r y -c)."
 
 #: tools/alignments/cli.py:49
 msgid " Use the output option (-o) to process results."

locales/kr/LC_MESSAGES/tools.alignments.cli.po

@@ -7,8 +7,8 @@ msgid ""
 msgstr ""
 "Project-Id-Version: \n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2024-04-12 12:10+0100\n"
-"PO-Revision-Date: 2024-04-12 12:17+0100\n"
+"POT-Creation-Date: 2024-04-19 11:28+0100\n"
+"PO-Revision-Date: 2024-04-19 11:30+0100\n"
 "Last-Translator: \n"
 "Language-Team: \n"
 "Language: ko_KR\n"
@@ -35,29 +35,29 @@ msgstr ""
 "용하거나 여러 작업을 수행할 수 있습니다."
 
 #: tools/alignments/cli.py:43
-msgid " Must Pass in a frames folder/source video file (-fr)."
+msgid " Must Pass in a frames folder/source video file (-r)."
 msgstr ""
-" 프레임들이 저장된 폴더나 원본 비디오 파일을 무조건 전달해야 합니다 (-fr)."
+" 프레임들이 저장된 폴더나 원본 비디오 파일을 무조건 전달해야 합니다 (-r)."
 
 #: tools/alignments/cli.py:44
-msgid " Must Pass in a faces folder (-fc)."
-msgstr " 얼굴 폴더를 무조건 전달해야 합니다 (-fc)."
+msgid " Must Pass in a faces folder (-c)."
+msgstr " 얼굴 폴더를 무조건 전달해야 합니다 (-c)."
 
 #: tools/alignments/cli.py:45
 msgid ""
-" Must Pass in either a frames folder/source video file OR a faces folder (-"
-"fr or -fc)."
+" Must Pass in either a frames folder/source video file OR a faces folder (-r "
+"or -c)."
 msgstr ""
 " 프레임 폴더나 원본 비디오 파일 또는 얼굴 폴더중 하나를 무조건 전달해야 합니"
-"다 (-fr and -fc)."
+"다 (-r and -c)."
 
 #: tools/alignments/cli.py:47
 msgid ""
-" Must Pass in a frames folder/source video file AND a faces folder (-fr and -"
-"fc)."
+" Must Pass in a frames folder/source video file AND a faces folder (-r and -"
+"c)."
 msgstr ""
 " 프레임 폴더나 원본 비디오 파일 그리고 얼굴 폴더를 무조건 전달해야 합니다 (-"
-"fr and -fc)."
+"r and -c)."
 
 #: tools/alignments/cli.py:49
 msgid " Use the output option (-o) to process results."

locales/ru/LC_MESSAGES/tools.alignments.cli.po

@@ -7,8 +7,8 @@ msgid ""
 msgstr ""
 "Project-Id-Version: \n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2024-04-12 12:10+0100\n"
-"PO-Revision-Date: 2024-04-12 12:13+0100\n"
+"POT-Creation-Date: 2024-04-19 11:28+0100\n"
+"PO-Revision-Date: 2024-04-19 11:31+0100\n"
 "Last-Translator: \n"
 "Language-Team: \n"
 "Language: ru\n"
@@ -38,28 +38,28 @@ msgstr ""
 "кадров."
 
 #: tools/alignments/cli.py:43
-msgid " Must Pass in a frames folder/source video file (-fr)."
-msgstr " Должен проходить в папке с кадрами/исходным видеофайлом (-fr)."
+msgid " Must Pass in a frames folder/source video file (-r)."
+msgstr " Должен проходить в папке с кадрами/исходным видеофайлом (-r)."
 
 #: tools/alignments/cli.py:44
-msgid " Must Pass in a faces folder (-fc)."
-msgstr " Должен проходить в папке с лицами (-fc)."
+msgid " Must Pass in a faces folder (-c)."
+msgstr " Должен проходить в папке с лицами (-c)."
 
 #: tools/alignments/cli.py:45
 msgid ""
-" Must Pass in either a frames folder/source video file OR a faces folder (-"
-"fr or -fc)."
+" Must Pass in either a frames folder/source video file OR a faces folder (-r "
+"or -c)."
 msgstr ""
 " Должно передаваться либо в папку с кадрами/исходным видеофайлом, либо в "
-"папку с лицами (-fr или -fc)."
+"папку с лицами (-r или -c)."
 
 #: tools/alignments/cli.py:47
 msgid ""
-" Must Pass in a frames folder/source video file AND a faces folder (-fr and -"
-"fc)."
+" Must Pass in a frames folder/source video file AND a faces folder (-r and -"
+"c)."
 msgstr ""
 " Должно передаваться либо в папку с кадрами/исходным видеофайлом И в папку с "
-"лицами (-fr и -fc)."
+"лицами (-r и -c)."
 
 #: tools/alignments/cli.py:49
 msgid " Use the output option (-o) to process results."

locales/tools.alignments.cli.pot

@@ -8,7 +8,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: PACKAGE VERSION\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2024-04-12 12:10+0100\n"
+"POT-Creation-Date: 2024-04-19 11:28+0100\n"
 "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
 "Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
 "Language-Team: LANGUAGE <[email protected]>\n"
@@ -30,23 +30,23 @@ msgid ""
 msgstr ""
 
 #: tools/alignments/cli.py:43
-msgid " Must Pass in a frames folder/source video file (-fr)."
+msgid " Must Pass in a frames folder/source video file (-r)."
 msgstr ""
 
 #: tools/alignments/cli.py:44
-msgid " Must Pass in a faces folder (-fc)."
+msgid " Must Pass in a faces folder (-c)."
 msgstr ""
 
 #: tools/alignments/cli.py:45
 msgid ""
-" Must Pass in either a frames folder/source video file OR a faces folder (-"
-"fr or -fc)."
+" Must Pass in either a frames folder/source video file OR a faces folder (-r "
+"or -c)."
 msgstr ""
 
 #: tools/alignments/cli.py:47
 msgid ""
-" Must Pass in a frames folder/source video file AND a faces folder (-fr and -"
-"fc)."
+" Must Pass in a frames folder/source video file AND a faces folder (-r and -"
+"c)."
 msgstr ""
 
 #: tools/alignments/cli.py:49

tools/alignments/cli.py

@@ -40,12 +40,12 @@ def get_argument_list() -> list[dict[str, T.Any]]:
         dict
             The argparse command line options for processing by argparse
         """
-        frames_dir = _(" Must Pass in a frames folder/source video file (-fr).")
-        faces_dir = _(" Must Pass in a faces folder (-fc).")
+        frames_dir = _(" Must Pass in a frames folder/source video file (-r).")
+        faces_dir = _(" Must Pass in a faces folder (-c).")
         frames_or_faces_dir = _(" Must Pass in either a frames folder/source video file OR a "
-                                "faces folder (-fr or -fc).")
+                                "faces folder (-r or -c).")
         frames_and_faces_dir = _(" Must Pass in a frames folder/source video file AND a faces "
-                                 "folder (-fr and -fc).")
+                                 "folder (-r and -c).")
         output_opts = _(" Use the output option (-o) to process results.")
         argument_list = []
         argument_list.append({
@@ -118,7 +118,7 @@ def get_argument_list() -> list[dict[str, T.Any]]:
             "group": _("data"),
             # hacky solution to not require alignments file if creating alignments from faces:
             "required": not any(val in sys.argv for val in ["from-faces",
-                                                            "-fr",
+                                                            "-r",
                                                             "-frames_folder"]),
             "filetypes": "alignments",
             "help": _(