Reformated files

Author: Benteng Ma

.gitignore

@@ -137,4 +137,7 @@ legacy/choosing_wait_position/src/choosing_wait_position/final_lift_key_point/mo
 
 # Python extension setup files
 .pylintrc
-mypy.ini
+mypy.ini
+
+# Pycharm extension setup files
+.idea/*

common/vision/lasr_vision_feature_extraction/src/lasr_vision_feature_extraction/__init__.py

@@ -1,3 +1,13 @@
+import json
+from os import path
+
+import cv2
+import numpy as np
+import rospkg
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+import torchvision.models as models
 from lasr_vision_feature_extraction.categories_and_attributes import (
     CategoriesAndAttributes,
     CelebAMaskHQCategoriesAndAttributes,
@@ -9,16 +19,6 @@
     ImageOfCloth,
 )
 
-import numpy as np
-import cv2
-import torch
-import rospkg
-from os import path
-import torch.nn as nn
-import torch.nn.functional as F
-import torchvision.models as models
-import json
-
 
 def X2conv(in_channels, out_channels, inner_channels=None):
     inner_channels = out_channels // 2 if inner_channels is None else inner_channels
@@ -150,7 +150,7 @@ def forward(self, x):
 
 class CombinedModel(nn.Module):
     def __init__(
-        self, segment_model: nn.Module, predict_model: nn.Module, cat_layers: int = None
+            self, segment_model: nn.Module, predict_model: nn.Module, cat_layers: int = None
     ):
         super(CombinedModel, self).__init__()
         self.segment_model = segment_model
@@ -162,7 +162,7 @@ def forward(self, x: torch.Tensor):
         seg_masks = self.segment_model(x)
         seg_masks_ = seg_masks.detach()
         if self.cat_layers:
-            seg_masks_ = seg_masks_[:, 0 : self.cat_layers]
+            seg_masks_ = seg_masks_[:, 0: self.cat_layers]
             x = torch.cat((x, seg_masks_), dim=1)
         else:
             x = torch.cat((x, seg_masks_), dim=1)
@@ -313,10 +313,10 @@ def forward(self, x):
 
 class Predictor:
     def __init__(
-        self,
-        model: torch.nn.Module,
-        device: torch.device,
-        categories_and_attributes: CategoriesAndAttributes,
+            self,
+            model: torch.nn.Module,
+            device: torch.device,
+            categories_and_attributes: CategoriesAndAttributes,
     ):
         self.model = model
         self.device = device
@@ -325,7 +325,7 @@ def __init__(
         self._thresholds_mask: list[float] = []
         self._thresholds_pred: list[float] = []
         for key in sorted(
-            list(self.categories_and_attributes.merged_categories.keys())
+                list(self.categories_and_attributes.merged_categories.keys())
         ):
             self._thresholds_mask.append(
                 self.categories_and_attributes.thresholds_mask[key]
@@ -339,7 +339,7 @@ def __init__(
     def predict(self, rgb_image: np.ndarray) -> ImageWithMasksAndAttributes:
         mean_val = np.mean(rgb_image)
         image_tensor = (
-            torch.from_numpy(rgb_image).permute(2, 0, 1).unsqueeze(0).float() / 255.0
+                torch.from_numpy(rgb_image).permute(2, 0, 1).unsqueeze(0).float() / 255.0
         )
         pred_masks, pred_classes = self.model(image_tensor)
         # Apply binary erosion and dilation to the masks
@@ -373,9 +373,9 @@ def load_face_classifier_model():
     cat_layers = CelebAMaskHQCategoriesAndAttributes.merged_categories.keys().__len__()
     segment_model = UNetWithResnetEncoder(num_classes=cat_layers)
     predictions = (
-        len(CelebAMaskHQCategoriesAndAttributes.attributes)
-        - len(CelebAMaskHQCategoriesAndAttributes.avoided_attributes)
-        + len(CelebAMaskHQCategoriesAndAttributes.mask_labels)
+            len(CelebAMaskHQCategoriesAndAttributes.attributes)
+            - len(CelebAMaskHQCategoriesAndAttributes.avoided_attributes)
+            + len(CelebAMaskHQCategoriesAndAttributes.mask_labels)
     )
     predict_model = MultiLabelResNet(
         num_labels=predictions, input_channels=cat_layers + 3
@@ -394,6 +394,7 @@ def load_face_classifier_model():
     )
     return model
 
+
 def load_cloth_classidifer_model():
     num_classes = len(DeepFashion2GeneralizedCategoriesAndAttributes.attributes)
     model = SegmentPredictorBbox(num_masks=num_classes + 4, num_labels=num_classes + 4, num_bbox_classes=4)
@@ -410,6 +411,7 @@ def load_cloth_classidifer_model():
     )
     return model
 
+
 def pad_image_to_even_dims(image):
     # Get the current shape of the image
     height, width, _ = image.shape
@@ -456,13 +458,13 @@ def extract_mask_region(frame, mask, expand_x=0.5, expand_y=0.5):
         new_w = min(frame.shape[1] - x, new_w)
         new_h = min(frame.shape[0] - y, new_h)
 
-        face_region = frame[y : y + int(new_h), x : x + int(new_w)]
+        face_region = frame[y: y + int(new_h), x: x + int(new_w)]
         return face_region
     return None
 
 
 def predict_frame(
-    head_frame, torso_frame, full_frame, head_mask, torso_mask, head_predictor, cloth_predictor,
+        head_frame, torso_frame, full_frame, head_mask, torso_mask, head_predictor, cloth_predictor,
 ):
     full_frame = cv2.cvtColor(full_frame, cv2.COLOR_BGR2RGB)
     head_frame = cv2.cvtColor(head_frame, cv2.COLOR_BGR2RGB)
@@ -499,7 +501,7 @@ def load_torch_model(model, optimizer, path="model.pth", cpu_only=False):
 
 
 def binary_erosion_dilation(
-    tensor, thresholds, erosion_iterations=1, dilation_iterations=1
+        tensor, thresholds, erosion_iterations=1, dilation_iterations=1
 ):
     """
     Apply binary threshold, followed by erosion and dilation to a tensor.

common/vision/lasr_vision_feature_extraction/src/lasr_vision_feature_extraction/categories_and_attributes.py

@@ -190,7 +190,7 @@ class DeepFashion2GeneralizedCategoriesAndAttributes(CategoriesAndAttributes):
     for key in mask_categories:
         if key not in _categories_to_merge:
             merged_categories[key] = [key]
-    mask_labels = ['top', 'down', 'outwear', 'dress',]
+    mask_labels = ['top', 'down', 'outwear', 'dress', ]
     selective_attributes = {}
     plane_attributes = []
     avoided_attributes = []

common/vision/lasr_vision_feature_extraction/src/lasr_vision_feature_extraction/image_with_masks_and_attributes.py

@@ -17,16 +17,16 @@ def _softmax(x: list[float]) -> list[float]:
 
 def _exp(x):
     """Compute e^x for a given x. A simple implementation of the exponential function."""
-    return 2.718281828459045**x  # Using an approximation of Euler's number e
+    return 2.718281828459045 ** x  # Using an approximation of Euler's number e
 
 
 class ImageWithMasksAndAttributes:
     def __init__(
-        self,
-        image: np.ndarray,
-        masks: dict[str, np.ndarray],
-        attributes: dict[str, float],
-        categories_and_attributes: CategoriesAndAttributes,
+            self,
+            image: np.ndarray,
+            masks: dict[str, np.ndarray],
+            attributes: dict[str, float],
+            categories_and_attributes: CategoriesAndAttributes,
     ):
         self.image: np.ndarray = image
         self.masks: dict[str, np.ndarray] = masks
@@ -41,7 +41,7 @@ def __init__(
 
         self.selective_attribute_dict: dict[str, dict[str, float]] = {}
         for category in sorted(
-            list(self.categories_and_attributes.selective_attributes.keys())
+                list(self.categories_and_attributes.selective_attributes.keys())
         ):
             self.selective_attribute_dict[category] = {}
             temp_list: list[float] = []
@@ -51,7 +51,7 @@ def __init__(
                 temp_list.append(self.attributes[attribute])
             softmax_list = _softmax(temp_list)
             for i, attribute in enumerate(
-                self.categories_and_attributes.selective_attributes[category]
+                    self.categories_and_attributes.selective_attributes[category]
             ):
                 self.selective_attribute_dict[category][attribute] = softmax_list[i]
 
@@ -67,17 +67,17 @@ def _max_value_tuple(some_dict: dict[str, float]) -> tuple[str, float]:
 
 class ImageOfPerson(ImageWithMasksAndAttributes):
     def __init__(
-        self,
-        image: np.ndarray,
-        masks: dict[str, np.ndarray],
-        attributes: dict[str, float],
-        categories_and_attributes: CategoriesAndAttributes,
+            self,
+            image: np.ndarray,
+            masks: dict[str, np.ndarray],
+            attributes: dict[str, float],
+            categories_and_attributes: CategoriesAndAttributes,
     ):
         super().__init__(image, masks, attributes, categories_and_attributes)
 
     @classmethod
     def from_parent_instance(
-        cls, parent_instance: ImageWithMasksAndAttributes
+            cls, parent_instance: ImageWithMasksAndAttributes
     ) -> "ImageOfPerson":
         """
         Creates an instance of ImageOfPerson using the properties of an
@@ -156,7 +156,7 @@ def describe(self) -> str:
                 hair_colour_str = "gray"
 
         if (
-            male
+                male
         ):  # here 'male' is only used to determine whether it is confident to decide whether the person has beard
             if not facial_hair[0] == "No_Beard":
                 description += "and has beard. "
@@ -180,7 +180,7 @@ def describe(self) -> str:
             if necktie[0]:
                 wearables.append("a necktie")
             description += (
-                ", ".join(wearables[:-2] + [" and ".join(wearables[-2:])]) + ". "
+                    ", ".join(wearables[:-2] + [" and ".join(wearables[-2:])]) + ". "
             )
 
         if description == "This customer has ":
@@ -209,17 +209,17 @@ def describe(self) -> str:
 
 class ImageOfCloth(ImageWithMasksAndAttributes):
     def __init__(
-        self,
-        image: np.ndarray,
-        masks: dict[str, np.ndarray],
-        attributes: dict[str, float],
-        categories_and_attributes: CategoriesAndAttributes,
+            self,
+            image: np.ndarray,
+            masks: dict[str, np.ndarray],
+            attributes: dict[str, float],
+            categories_and_attributes: CategoriesAndAttributes,
     ):
         super().__init__(image, masks, attributes, categories_and_attributes)
 
     @classmethod
     def from_parent_instance(
-        cls, parent_instance: ImageWithMasksAndAttributes
+            cls, parent_instance: ImageWithMasksAndAttributes
     ) -> "ImageOfCloth":
         """
         Creates an instance of ImageOfCloth using the properties of an
@@ -240,24 +240,31 @@ def describe(self) -> str:
                 "down": self.attributes["down"] > self.categories_and_attributes.thresholds_pred["down"],
                 "outwear": self.attributes["outwear"] > self.categories_and_attributes.thresholds_pred["outwear"],
                 "dress": self.attributes["dress"] > self.categories_and_attributes.thresholds_pred["dress"],
-                
-                "short sleeve top": self.attributes["short sleeve top"] > self.categories_and_attributes.thresholds_pred["short sleeve top"],
-                "long sleeve top": self.attributes["long sleeve top"] > self.categories_and_attributes.thresholds_pred["long sleeve top"],
-                "short sleeve outwear": self.attributes["short sleeve outwear"] > self.categories_and_attributes.thresholds_pred["short sleeve outwear"],
-                "long sleeve outwear": self.attributes["long sleeve outwear"] > self.categories_and_attributes.thresholds_pred["long sleeve outwear"],
+
+                "short sleeve top": self.attributes["short sleeve top"] >
+                                    self.categories_and_attributes.thresholds_pred["short sleeve top"],
+                "long sleeve top": self.attributes["long sleeve top"] > self.categories_and_attributes.thresholds_pred[
+                    "long sleeve top"],
+                "short sleeve outwear": self.attributes["short sleeve outwear"] >
+                                        self.categories_and_attributes.thresholds_pred["short sleeve outwear"],
+                "long sleeve outwear": self.attributes["long sleeve outwear"] >
+                                       self.categories_and_attributes.thresholds_pred["long sleeve outwear"],
                 "vest": self.attributes["vest"] > self.categories_and_attributes.thresholds_pred["vest"],
                 "sling": self.attributes["sling"] > self.categories_and_attributes.thresholds_pred["sling"],
                 "outwear": self.attributes["outwear"] > self.categories_and_attributes.thresholds_pred["outwear"],
                 "shorts": self.attributes["shorts"] > self.categories_and_attributes.thresholds_pred["shorts"],
                 "trousers": self.attributes["trousers"] > self.categories_and_attributes.thresholds_pred["trousers"],
                 "skirt": self.attributes["skirt"] > self.categories_and_attributes.thresholds_pred["skirt"],
-                "short sleeve dress": self.attributes["short sleeve dress"] > self.categories_and_attributes.thresholds_pred["short sleeve dress"],
-                "long sleeve dress": self.attributes["long sleeve dress"] > self.categories_and_attributes.thresholds_pred["long sleeve dress"],
-                "vest dress": self.attributes["vest dress"] > self.categories_and_attributes.thresholds_pred["vest dress"],
-                "sling dress": self.attributes["sling dress"] > self.categories_and_attributes.thresholds_pred["sling dress"],
+                "short sleeve dress": self.attributes["short sleeve dress"] >
+                                      self.categories_and_attributes.thresholds_pred["short sleeve dress"],
+                "long sleeve dress": self.attributes["long sleeve dress"] >
+                                     self.categories_and_attributes.thresholds_pred["long sleeve dress"],
+                "vest dress": self.attributes["vest dress"] > self.categories_and_attributes.thresholds_pred[
+                    "vest dress"],
+                "sling dress": self.attributes["sling dress"] > self.categories_and_attributes.thresholds_pred[
+                    "sling dress"],
             },
             "description": "this descrcription will be completed if we find out it is better to do it here.",
         }
 
         return result
-