update

UTAustin-SwarmLab · Jul 6, 2024 · 45593cf · 45593cf
1 parent 16771a2
commit 45593cf
Show file tree

Hide file tree

Showing 16 changed files with 150 additions and 51 deletions.
diff --git a/README.md b/README.md
@@ -1,12 +1,10 @@
 # Temporal Logic Video (TLV) Dataset
 
-<div align="center">
-[![Contributors][contributors-shield]][contributors-url]
-[![Forks][forks-shield]][forks-url]
-[![Stargazers][stars-shield]][stars-url]
-[![MIT License][license-shield]][license-url]
-</div>
 
+| [![Contributors][contributors-shield]][contributors-url] | [![Forks][forks-shield]][forks-url] | [![Stargazers][stars-shield]][stars-url] | [![MIT License][license-shield]][license-url] |
+|:--:|:--:|:--:|:--:|
+
+## Overview
 <!-- PROJECT LOGO -->
 <br />
 <div align="center">
@@ -86,12 +84,42 @@ Each serialized object contains the following attributes:
 
 You can download a dataset from here. The structure of dataset is as follows: serializer
    ```
-   ILSVRC/
-   ├── Annotations/
-   ├── Data/
-   ├── ImageSets/
-   └── LOC_synset_mapping.txt
+   tlv-dataset-v1/
+   ├── tlv_real_dataset/
+   ├──── prop1Uprop2/
+   ├──── (prop1&prop2)Uprop3/
+   ├── tlv_synthetic_dataset/
+   ├──── Fprop1/
+   ├──── Gprop1/
+   ├──── prop1&prop2/
+   ├──── prop1Uprop2/
+   └──── (prop1&prop2)Uprop3/
    ```
+#### Dataset Statistics
+1. Total Number of Frames
+
+| Ground Truth TL Specifications | Synthetic TLV Dataset | | Real TLV Dataset | |
+| --- | ---: | ---: | ---: | ---: |
+| | COCO | ImageNet | Waymo | Nuscenes |
+|---|---|---|---|---|
+| Eventually Event A | - | 15,750 | - | - |
+| Always Event A | - | 15,750 | - | - |
+| Event A And Event B | 31,500 | - | - | - |
+| Event A Until Event B | 15,750 | 15,750 | 8,736 | 19,808 |
+| (Event A And Event B) Until Event C | 5,789 | - | 7,459 | 7,459 |
+
+2. Total Number of datasets
+
+| Ground Truth TL Specifications | Synthetic TLV Dataset | | Real TLV Dataset | |
+| --- | ---: | ---: | ---: | ---: |
+| | COCO | ImageNet | Waymo | Nuscenes |
+|---|---|---|---|---|
+| Eventually Event A | - | 60 | - | - |
+| Always Event A | - | 60 | - | - |
+| Event A And Event B | 120 | - | - | - |
+| Event A Until Event B | 60| 60 | 45| 494 |
+| (Event A And Event B) Until Event C | 97 | - | 30 | 186|
+
 
 ## Installation
 

diff --git a/run_scripts/run_synthetic_tlv_coco.py b/run_scripts/run_synthetic_tlv_coco.py
@@ -78,7 +78,9 @@
         coco_image_source=args.coco_image_source,
     )
 
-    TLV_generator = SyntheticTLVGenerator(dataloader=dataloader, save_dir=args.save_dir)
+    TLV_generator = SyntheticTLVGenerator(
+        dataloader=dataloader, save_dir=args.save_dir
+    )
 
     if args.ltl_logic == "all":
         available_tl = [

diff --git a/run_scripts/run_synthetic_tlv_coco_until_long_horizon.py b/run_scripts/run_synthetic_tlv_coco_until_long_horizon.py
@@ -73,7 +73,9 @@
         coco_image_source=args.coco_image_source,
     )
 
-    TLV_generator = SyntheticTLVGenerator(dataloader=dataloader, save_dir=args.save_dir)
+    TLV_generator = SyntheticTLVGenerator(
+        dataloader=dataloader, save_dir=args.save_dir
+    )
 
     TLV_generator.generate_until_time_delta(
         initial_number_of_frame=args.initial_number_of_frame,

diff --git a/run_scripts/run_synthetic_tlv_imagenet.py b/run_scripts/run_synthetic_tlv_imagenet.py
@@ -77,7 +77,9 @@
         batch_id=args.batch_id,
     )
 
-    TLV_generator = SyntheticTLVGenerator(dataloader=dataloader, save_dir=args.save_dir)
+    TLV_generator = SyntheticTLVGenerator(
+        dataloader=dataloader, save_dir=args.save_dir
+    )
 
     if args.ltl_logic == "all":
         available_tl = [

diff --git a/run_scripts/run_synthetic_tlv_imagenet_until_long_horizon.py b/run_scripts/run_synthetic_tlv_imagenet_until_long_horizon.py
@@ -74,7 +74,9 @@
         batch_id=args.batch_id,
     )
 
-    TLV_generator = SyntheticTLVGenerator(dataloader=dataloader, save_dir=args.save_dir)
+    TLV_generator = SyntheticTLVGenerator(
+        dataloader=dataloader, save_dir=args.save_dir
+    )
 
     TLV_generator.generate_until_time_delta(
         initial_number_of_frame=args.initial_number_of_frame,

diff --git a/tlv_dataset/__init__.py b/tlv_dataset/__init__.py
@@ -1,2 +1,3 @@
 """Package containing your_project name."""
+
 __version__ = "1.0.0"
diff --git a/tlv_dataset/common/ltl_utility.py b/tlv_dataset/common/ltl_utility.py
@@ -20,7 +20,9 @@ def get_not_operator_mapping(ltl_formula):
     return not_operator_proposition_list
 
 
-def verification_result_eval(verification_result: ExplicitQualitativeCheckResult):
+def verification_result_eval(
+    verification_result: ExplicitQualitativeCheckResult,
+):
     # string result is "true" when is absolutely true
     # but it returns "true, false" when we have some true and false
     verification_result_str = str(verification_result)

diff --git a/tlv_dataset/common/omegaconf.py b/tlv_dataset/common/omegaconf.py
@@ -2,21 +2,24 @@
 from pathlib import Path
 from omegaconf import DictConfig, ListConfig, OmegaConf
 
+
 def load_config_from_yaml(config_path: str, read_only=False) -> DictConfig:
     """Load a yaml config file and return a DictConfig object."""
     config = OmegaConf.load(config_path)
     if read_only:
         OmegaConf.set_readonly(config, True)
     return config
 
+
 def load_config_from_dict(config_dict: dict, read_only=False) -> DictConfig:
     """Load a dictionary and return a DictConfig object."""
     config = OmegaConf.create(config_dict)
     if read_only:
         OmegaConf.set_readonly(config, True)
     return config
 
+
 def save_config_to_yaml(config: DictConfig, config_path: str) -> None:
     """Save a DictConfig object to a yaml file."""
     with Path(config_path) as fp:
-        OmegaConf.save(config=config, f=fp)
+        OmegaConf.save(config=config, f=fp)
diff --git a/tlv_dataset/common/utility.py b/tlv_dataset/common/utility.py
@@ -22,7 +22,9 @@ def get_file_or_dir_with_datetime(base_name, ext="."):
 
 
 def save_frames(
-    frames: list, path="/opt/Neuro-Symbolic-Video-Frame-Search/artifacts/result", file_label: str = ""
+    frames: list,
+    path="/opt/Neuro-Symbolic-Video-Frame-Search/artifacts/result",
+    file_label: str = "",
 ) -> None:
     """Save image to path.
 
@@ -37,7 +39,9 @@ def save_frames(
         Image.fromarray(img).save(f"{path}/{file_label}_{idx}.png")
 
 
-def save_dict_to_pickle(dict_obj: dict | object, path: str, file_name: str = "data.pkl"):
+def save_dict_to_pickle(
+    dict_obj: dict | object, path: str, file_name: str = "data.pkl"
+):
     # Decode the JSON data into a Python object
     # data_python = json.loads(dict_obj)
     full_path = Path(path) / file_name

diff --git a/tlv_dataset/data/tlv_raw_image.py b/tlv_dataset/data/tlv_raw_image.py
@@ -14,7 +14,9 @@ class TLVRawImage:
     labels: List[List[str]]
     images: List[np.ndarray]
 
-    def sample_image_from_label(self, labels: list, proposition: list) -> np.ndarray:
+    def sample_image_from_label(
+        self, labels: list, proposition: list
+    ) -> np.ndarray:
         """Sample image from label."""
         image_of_frame = []
         img_to_label = {}
@@ -60,7 +62,9 @@ def sample_image_from_label(self, labels: list, proposition: list) -> np.ndarray
                         for i, value in enumerate(self.labels)
                         if all(prop in value for prop in label)
                     ]
-                    random_idx = random.choice(img_to_label_list[tuple(sorted(label))])
+                    random_idx = random.choice(
+                        img_to_label_list[tuple(sorted(label))]
+                    )
                     image_of_frame.append(self.images[random_idx])
             label_idx += 1
         return labels, image_of_frame
@@ -74,7 +78,9 @@ class TLVRawImageDataset:
     labels: List[List[str]]
     images: torch.utils.data.Dataset
 
-    def sample_image_from_label(self, labels: list, proposition: list) -> np.ndarray:
+    def sample_image_from_label(
+        self, labels: list, proposition: list
+    ) -> np.ndarray:
         """Sample image from label."""
         image_of_frame = []
         img_to_label = {}

diff --git a/tlv_dataset/generator/real_tlv_generator.py b/tlv_dataset/generator/real_tlv_generator.py
@@ -51,7 +51,9 @@ def generate(self):
                 benchmark_frame: TLVDataset = load_pickle_to_dict(file)
                 self.generate_ltl_ground_truth(benchmark_frame)
         else:
-            self._dataloader.loading_data(generate_func=self.generate_ltl_ground_truth)
+            self._dataloader.loading_data(
+                generate_func=self.generate_ltl_ground_truth
+            )
 
     def get_label_count(self, lst):
         output = Counter()

diff --git a/tlv_dataset/generator/synthetic_tlv_generator.py b/tlv_dataset/generator/synthetic_tlv_generator.py
@@ -327,15 +327,15 @@ def ltl_function(
             else:
                 proposition_set = [proposition_1, proposition_2]
             if temporal_property == "U":
-                assert proposition_2 is not None, "proposition 2 must be not None"
+                assert (
+                    proposition_2 is not None
+                ), "proposition 2 must be not None"
                 u_index = logic_component.index("U")
                 pre_u_index = logic_component[u_index - 1]
                 post_u_index = logic_component[u_index + 1]
                 if post_u_index == "prop2":
                     # TODO: F & G...
-                    ltl_formula = (
-                        f'"{proposition_1}" {temporal_property} "{proposition_2}"'
-                    )
+                    ltl_formula = f'"{proposition_1}" {temporal_property} "{proposition_2}"'
                     post_u_label_idx = []
                     for idx in list(set(random_frame_idx_selection)):
                         temp_frames_of_interest.append(idx)
@@ -349,7 +349,9 @@ def ltl_function(
                                 post_u_label_idx.append(prop2_idx)
                                 labels_of_frame[prop2_idx] = proposition_2
                         else:
-                            prop2_idx = random.randrange(idx + 1, number_of_frame - 1)
+                            prop2_idx = random.randrange(
+                                idx + 1, number_of_frame - 1
+                            )
                             temp_frames_of_interest.append(prop2_idx)
                             post_u_label_idx.append(prop2_idx)
                             labels_of_frame[prop2_idx] = proposition_2
@@ -386,7 +388,9 @@ def ltl_function(
                                 post_u_label_idx.append(prop3_idx)
                                 labels_of_frame[prop3_idx] = proposition_3
                         else:
-                            prop3_idx = random.randrange(idx + 1, number_of_frame - 1)
+                            prop3_idx = random.randrange(
+                                idx + 1, number_of_frame - 1
+                            )
                             temp_frames_of_interest.append(prop3_idx)
                             post_u_label_idx.append(prop3_idx)
                             labels_of_frame[prop3_idx] = proposition_3
@@ -423,9 +427,7 @@ def ltl_function(
                 assert (
                     conditional_property == "!"
                 ), "conditional_property must be ! with one proposition"
-                ltl_formula = (
-                    f'{temporal_property} {conditional_property} "{proposition_1}"'
-                )
+                ltl_formula = f'{temporal_property} {conditional_property} "{proposition_1}"'
             # 1. F "prop1"
             frame_index = []
             if temporal_property == "F":

diff --git a/tlv_dataset/label_mapper/mapper_utils.py b/tlv_dataset/label_mapper/mapper_utils.py
@@ -2,7 +2,9 @@ def get_mapper_metadata(loader_name: str, mapping_to: str):
     loader_name = loader_name.split(".py")[0]
     if loader_name == "imagenet":
         valid_mapper = ["coco"]
-        assert mapping_to in valid_mapper, "please use valid mapper for ImageNet: coco"
+        assert (
+            mapping_to in valid_mapper
+        ), "please use valid mapper for ImageNet: coco"
         if mapping_to == "coco":
             from tlv_dataset.label_mapper.metadata.imagenet_to_coco import (
                 MAPPER_METADATA,

diff --git a/tlv_dataset/loader/imagenet.py b/tlv_dataset/loader/imagenet.py
@@ -102,7 +102,9 @@ def __getitem__(self, index):
             class_id = 0
             while (
                 index
-                >= self._num_images_per_class[self.mapping_number_to_class[class_id]]
+                >= self._num_images_per_class[
+                    self.mapping_number_to_class[class_id]
+                ]
             ):
                 index -= self._num_images_per_class[
                     self.mapping_number_to_class[class_id]
@@ -123,15 +125,21 @@ def __getitem__(self, index):
         else:
             # Obtain the metaclass where the index is located
             metaclass_id = 0
-            metaclassname = list(self.metaclass_imagenetclass.keys())[metaclass_id]
+            metaclassname = list(self.metaclass_imagenetclass.keys())[
+                metaclass_id
+            ]
             cum_count = 0
             while index >= self._num_images_per_metaclass[metaclassname]:
                 index -= self._num_images_per_metaclass[metaclassname]
                 cum_count += self._num_images_per_metaclass[metaclassname]
                 metaclass_id += 1
-                metaclassname = list(self.metaclass_imagenetclass.keys())[metaclass_id]
+                metaclassname = list(self.metaclass_imagenetclass.keys())[
+                    metaclass_id
+                ]
 
-            imagenet_class_for_metaclass = self.metaclass_imagenetclass[metaclassname]
+            imagenet_class_for_metaclass = self.metaclass_imagenetclass[
+                metaclassname
+            ]
             index = index_copy - cum_count
 
             class_id_val = 0
@@ -264,7 +272,9 @@ def __init__(
         self.imagenet = ImageNetDS(imagenet_dir_path, is_mapping=is_mapping)
         # Get text labels from metadata
         self.class_labels = list(self.imagenet.classnames)
-        self.data: TLVRawImageDataset = self.process_data(raw_data=self.load_data())
+        self.data: TLVRawImageDataset = self.process_data(
+            raw_data=self.load_data()
+        )
 
     def load_data(self) -> dict:
         """Load the labels of the data
@@ -274,7 +284,9 @@ def load_data(self) -> dict:
         labels = [0 for _ in range(len(self.imagenet))]
         mapped_labels = [0 for _ in range(len(self.imagenet))]
         cum_count = 0
-        for idx, (class_, count) in enumerate(self.imagenet.class_counts.items()):
+        for idx, (class_, count) in enumerate(
+            self.imagenet.class_counts.items()
+        ):
             cum_count += count
             for j in range(cum_count - count, cum_count):
                 labels[j] = idx

diff --git a/tlv_dataset/loader/nuscenes.py b/tlv_dataset/loader/nuscenes.py
@@ -28,7 +28,9 @@ def __init__(
                 from tlv_dataset.label_mapper.metadata.nuscenes_to_coco import (
                     MAPPER_METADATA,
                 )
-        self._nusc = NuScenes(version=version, dataroot=dataroot, verbose=verbose)
+        self._nusc = NuScenes(
+            version=version, dataroot=dataroot, verbose=verbose
+        )
         self._nuscene: list = self._nusc.scene
         # self._scene_data = self.loading_data(self._nuscene)
 
@@ -87,20 +89,26 @@ def loading_data(self, generate_func: callable = None):
             for data in self._nusc.sample:
                 if scene_token == data["scene_token"]:
                     front_cam_frame = cv2.imread(
-                        self._nusc.get_sample_data_path(data["data"]["CAM_FRONT"])
+                        self._nusc.get_sample_data_path(
+                            data["data"]["CAM_FRONT"]
+                        )
                     )
                     labels = self.parse_object_class(data["anns"])
                     # cv2.imwrite("test__.png", front_cam_frame)
                     if front_cam_frame is not None:
                         scene_data[scene_token]["images_of_frame"].append(
                             front_cam_frame
                         )
-                        scene_data[scene_token]["labels_of_frame"].append(labels)
+                        scene_data[scene_token]["labels_of_frame"].append(
+                            labels
+                        )
                     else:
                         data_validation = False
             if data_validation:
                 if generate_func is not None:
-                    generate_func(self.convert_to_tlv_dataset(scene_data[scene_token]))
+                    generate_func(
+                        self.convert_to_tlv_dataset(scene_data[scene_token])
+                    )
             else:
                 save_dict_to_pickle(
                     dict_obj=scene_data[scene_token],
Original file line number	Diff line number	Diff line change
		@@ -1,2 +1,3 @@
		"""Package containing your_project name."""

		__version__ = "1.0.0"