Implementation of Stanford Cars prototype dataset (#5442)

* basic stanford cars structure added.

* added class in the init.

* how to decode the images

* fix typo in init

* works partially

* formatting

* formatting

* formatting

* formatting

* formatting

* minor changes

* minor changes

* issue resolved

* both datapipes are in sync

* checksum dict keys changed

* formatting

* "ufmt formatting"

* "ufmt formatting"

* formatting

* minor change

* minor change

* test added

* lint (end of line issue)

* lint (end of line issue)

* minor changes

* mock dataset formatting

* minor changes

* hopefully final

* formatting

* prototype test

* prototype test

* prototype test

* prototype test

* prototype test

* prototype test

* prototype test

* prototype test

* Update builtin_dataset_mocks.py

* Update stanford_cars.py

* Update torchvision/prototype/datasets/_builtin/stanford_cars.py
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* Update torchvision/prototype/datasets/_builtin/stanford_cars.py
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* Update torchvision/prototype/datasets/_builtin/stanford_cars.py
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* Update torchvision/prototype/datasets/_builtin/stanford_cars.py
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* formatting and cleaning

* formatting and cleaning

* Update torchvision/prototype/datasets/_builtin/stanford_cars.py
Co-authored-by: Philip Meier <github.pmeier@posteo.de>

* generate catefories script

* generate categories script added

* sigh

* sigh

* sigh

* minor changes

* linting
Co-authored-by: Philip Meier <github.pmeier@posteo.de>
Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>

test/builtin_dataset_mocks.py

@@ -1390,3 +1390,44 @@ def pcam(info, root, config):
             compressed_file.write(compressed_data)
 
     return num_images
+
+
+@register_mock
+def stanford_cars(info, root, config):
+    import scipy.io as io
+    from numpy.core.records import fromarrays
+
+    num_samples = {"train": 5, "test": 7}[config["split"]]
+    num_categories = 3
+
+    devkit = root / "devkit"
+    devkit.mkdir(parents=True)
+
+    if config["split"] == "train":
+        images_folder_name = "cars_train"
+        annotations_mat_path = devkit / "cars_train_annos.mat"
+    else:
+        images_folder_name = "cars_test"
+        annotations_mat_path = root / "cars_test_annos_withlabels.mat"
+
+    create_image_folder(
+        root=root,
+        name=images_folder_name,
+        file_name_fn=lambda image_index: f"{image_index:5d}.jpg",
+        num_examples=num_samples,
+    )
+
+    make_tar(root, f"cars_{config.split}.tgz", images_folder_name)
+    bbox = np.random.randint(1, 200, num_samples, dtype=np.uint8)
+    classes = np.random.randint(1, num_categories + 1, num_samples, dtype=np.uint8)
+    fnames = [f"{i:5d}.jpg" for i in range(num_samples)]
+    rec_array = fromarrays(
+        [bbox, bbox, bbox, bbox, classes, fnames],
+        names=["bbox_x1", "bbox_y1", "bbox_x2", "bbox_y2", "class", "fname"],
+    )
+
+    io.savemat(annotations_mat_path, {"annotations": rec_array})
+    if config.split == "train":
+        make_tar(root, "car_devkit.tgz", devkit, compression="gz")
+
+    return num_samples

torchvision/prototype/datasets/_builtin/__init__.py

@@ -15,5 +15,6 @@ from .oxford_iiit_pet import OxfordIITPet
 from .pcam import PCAM
 from .sbd import SBD
 from .semeion import SEMEION
+from .stanford_cars import StanfordCars
 from .svhn import SVHN
 from .voc import VOC

torchvision/prototype/datasets/_builtin/stanford-cars.categories

+AM General Hummer SUV 2000
+Acura RL Sedan 2012
+Acura TL Sedan 2012
+Acura TL Type-S 2008
+Acura TSX Sedan 2012
+Acura Integra Type R 2001
+Acura ZDX Hatchback 2012
+Aston Martin V8 Vantage Convertible 2012
+Aston Martin V8 Vantage Coupe 2012
+Aston Martin Virage Convertible 2012
+Aston Martin Virage Coupe 2012
+Audi RS 4 Convertible 2008
+Audi A5 Coupe 2012
+Audi TTS Coupe 2012
+Audi R8 Coupe 2012
+Audi V8 Sedan 1994
+Audi 100 Sedan 1994
+Audi 100 Wagon 1994
+Audi TT Hatchback 2011
+Audi S6 Sedan 2011
+Audi S5 Convertible 2012
+Audi S5 Coupe 2012
+Audi S4 Sedan 2012
+Audi S4 Sedan 2007
+Audi TT RS Coupe 2012
+BMW ActiveHybrid 5 Sedan 2012
+BMW 1 Series Convertible 2012
+BMW 1 Series Coupe 2012
+BMW 3 Series Sedan 2012
+BMW 3 Series Wagon 2012
+BMW 6 Series Convertible 2007
+BMW X5 SUV 2007
+BMW X6 SUV 2012
+BMW M3 Coupe 2012
+BMW M5 Sedan 2010
+BMW M6 Convertible 2010
+BMW X3 SUV 2012
+BMW Z4 Convertible 2012
+Bentley Continental Supersports Conv. Convertible 2012
+Bentley Arnage Sedan 2009
+Bentley Mulsanne Sedan 2011
+Bentley Continental GT Coupe 2012
+Bentley Continental GT Coupe 2007
+Bentley Continental Flying Spur Sedan 2007
+Bugatti Veyron 16.4 Convertible 2009
+Bugatti Veyron 16.4 Coupe 2009
+Buick Regal GS 2012
+Buick Rainier SUV 2007
+Buick Verano Sedan 2012
+Buick Enclave SUV 2012
+Cadillac CTS-V Sedan 2012
+Cadillac SRX SUV 2012
+Cadillac Escalade EXT Crew Cab 2007
+Chevrolet Silverado 1500 Hybrid Crew Cab 2012
+Chevrolet Corvette Convertible 2012
+Chevrolet Corvette ZR1 2012
+Chevrolet Corvette Ron Fellows Edition Z06 2007
+Chevrolet Traverse SUV 2012
+Chevrolet Camaro Convertible 2012
+Chevrolet HHR SS 2010
+Chevrolet Impala Sedan 2007
+Chevrolet Tahoe Hybrid SUV 2012
+Chevrolet Sonic Sedan 2012
+Chevrolet Express Cargo Van 2007
+Chevrolet Avalanche Crew Cab 2012
+Chevrolet Cobalt SS 2010
+Chevrolet Malibu Hybrid Sedan 2010
+Chevrolet TrailBlazer SS 2009
+Chevrolet Silverado 2500HD Regular Cab 2012
+Chevrolet Silverado 1500 Classic Extended Cab 2007
+Chevrolet Express Van 2007
+Chevrolet Monte Carlo Coupe 2007
+Chevrolet Malibu Sedan 2007
+Chevrolet Silverado 1500 Extended Cab 2012
+Chevrolet Silverado 1500 Regular Cab 2012
+Chrysler Aspen SUV 2009
+Chrysler Sebring Convertible 2010
+Chrysler Town and Country Minivan 2012
+Chrysler 300 SRT-8 2010
+Chrysler Crossfire Convertible 2008
+Chrysler PT Cruiser Convertible 2008
+Daewoo Nubira Wagon 2002
+Dodge Caliber Wagon 2012
+Dodge Caliber Wagon 2007
+Dodge Caravan Minivan 1997
+Dodge Ram Pickup 3500 Crew Cab 2010
+Dodge Ram Pickup 3500 Quad Cab 2009
+Dodge Sprinter Cargo Van 2009
+Dodge Journey SUV 2012
+Dodge Dakota Crew Cab 2010
+Dodge Dakota Club Cab 2007
+Dodge Magnum Wagon 2008
+Dodge Challenger SRT8 2011
+Dodge Durango SUV 2012
+Dodge Durango SUV 2007
+Dodge Charger Sedan 2012
+Dodge Charger SRT-8 2009
+Eagle Talon Hatchback 1998
+FIAT 500 Abarth 2012
+FIAT 500 Convertible 2012
+Ferrari FF Coupe 2012
+Ferrari California Convertible 2012
+Ferrari 458 Italia Convertible 2012
+Ferrari 458 Italia Coupe 2012
+Fisker Karma Sedan 2012
+Ford F-450 Super Duty Crew Cab 2012
+Ford Mustang Convertible 2007
+Ford Freestar Minivan 2007
+Ford Expedition EL SUV 2009
+Ford Edge SUV 2012
+Ford Ranger SuperCab 2011
+Ford GT Coupe 2006
+Ford F-150 Regular Cab 2012
+Ford F-150 Regular Cab 2007
+Ford Focus Sedan 2007
+Ford E-Series Wagon Van 2012
+Ford Fiesta Sedan 2012
+GMC Terrain SUV 2012
+GMC Savana Van 2012
+GMC Yukon Hybrid SUV 2012
+GMC Acadia SUV 2012
+GMC Canyon Extended Cab 2012
+Geo Metro Convertible 1993
+HUMMER H3T Crew Cab 2010
+HUMMER H2 SUT Crew Cab 2009
+Honda Odyssey Minivan 2012
+Honda Odyssey Minivan 2007
+Honda Accord Coupe 2012
+Honda Accord Sedan 2012
+Hyundai Veloster Hatchback 2012
+Hyundai Santa Fe SUV 2012
+Hyundai Tucson SUV 2012
+Hyundai Veracruz SUV 2012
+Hyundai Sonata Hybrid Sedan 2012
+Hyundai Elantra Sedan 2007
+Hyundai Accent Sedan 2012
+Hyundai Genesis Sedan 2012
+Hyundai Sonata Sedan 2012
+Hyundai Elantra Touring Hatchback 2012
+Hyundai Azera Sedan 2012
+Infiniti G Coupe IPL 2012
+Infiniti QX56 SUV 2011
+Isuzu Ascender SUV 2008
+Jaguar XK XKR 2012
+Jeep Patriot SUV 2012
+Jeep Wrangler SUV 2012
+Jeep Liberty SUV 2012
+Jeep Grand Cherokee SUV 2012
+Jeep Compass SUV 2012
+Lamborghini Reventon Coupe 2008
+Lamborghini Aventador Coupe 2012
+Lamborghini Gallardo LP 570-4 Superleggera 2012
+Lamborghini Diablo Coupe 2001
+Land Rover Range Rover SUV 2012
+Land Rover LR2 SUV 2012
+Lincoln Town Car Sedan 2011
+MINI Cooper Roadster Convertible 2012
+Maybach Landaulet Convertible 2012
+Mazda Tribute SUV 2011
+McLaren MP4-12C Coupe 2012
+Mercedes-Benz 300-Class Convertible 1993
+Mercedes-Benz C-Class Sedan 2012
+Mercedes-Benz SL-Class Coupe 2009
+Mercedes-Benz E-Class Sedan 2012
+Mercedes-Benz S-Class Sedan 2012
+Mercedes-Benz Sprinter Van 2012
+Mitsubishi Lancer Sedan 2012
+Nissan Leaf Hatchback 2012
+Nissan NV Passenger Van 2012
+Nissan Juke Hatchback 2012
+Nissan 240SX Coupe 1998
+Plymouth Neon Coupe 1999
+Porsche Panamera Sedan 2012
+Ram C/V Cargo Van Minivan 2012
+Rolls-Royce Phantom Drophead Coupe Convertible 2012
+Rolls-Royce Ghost Sedan 2012
+Rolls-Royce Phantom Sedan 2012
+Scion xD Hatchback 2012
+Spyker C8 Convertible 2009
+Spyker C8 Coupe 2009
+Suzuki Aerio Sedan 2007
+Suzuki Kizashi Sedan 2012
+Suzuki SX4 Hatchback 2012
+Suzuki SX4 Sedan 2012
+Tesla Model S Sedan 2012
+Toyota Sequoia SUV 2012
+Toyota Camry Sedan 2012
+Toyota Corolla Sedan 2012
+Toyota 4Runner SUV 2012
+Volkswagen Golf Hatchback 2012
+Volkswagen Golf Hatchback 1991
+Volkswagen Beetle Hatchback 2012
+Volvo C30 Hatchback 2012
+Volvo 240 Sedan 1993
+Volvo XC90 SUV 2007
+smart fortwo Convertible 2012

torchvision/prototype/datasets/_builtin/stanford_cars.py

+import pathlib
+from typing import Any, Dict, List, Tuple, Iterator, BinaryIO
+
+from torchdata.datapipes.iter import Filter, IterDataPipe, Mapper, Zipper
+from torchvision.prototype.datasets.utils import Dataset, DatasetConfig, DatasetInfo, HttpResource, OnlineResource
+from torchvision.prototype.datasets.utils._internal import hint_sharding, hint_shuffling, path_comparator, read_mat
+from torchvision.prototype.features import BoundingBox, EncodedImage, Label
+
+
+class StanfordCarsLabelReader(IterDataPipe[Tuple[int, int, int, int, int, str]]):
+    def __init__(self, datapipe: IterDataPipe[Dict[str, Any]]) -> None:
+        self.datapipe = datapipe
+
+    def __iter__(self) -> Iterator[Tuple[int, int, int, int, int, str]]:
+        for _, file in self.datapipe:
+            data = read_mat(file, squeeze_me=True)
+            for ann in data["annotations"]:
+                yield tuple(ann)  # type: ignore[misc]
+
+
+class StanfordCars(Dataset):
+    def _make_info(self) -> DatasetInfo:
+        return DatasetInfo(
+            name="stanford-cars",
+            homepage="https://ai.stanford.edu/~jkrause/cars/car_dataset.html",
+            dependencies=("scipy",),
+            valid_options=dict(
+                split=("test", "train"),
+            ),
+        )
+
+    _URL_ROOT = "https://ai.stanford.edu/~jkrause/"
+    _URLS = {
+        "train": f"{_URL_ROOT}car196/cars_train.tgz",
+        "test": f"{_URL_ROOT}car196/cars_test.tgz",
+        "cars_test_annos_withlabels": f"{_URL_ROOT}car196/cars_test_annos_withlabels.mat",
+        "car_devkit": f"{_URL_ROOT}cars/car_devkit.tgz",
+    }
+
+    _CHECKSUM = {
+        "train": "b97deb463af7d58b6bfaa18b2a4de9829f0f79e8ce663dfa9261bf7810e9accd",
+        "test": "bffea656d6f425cba3c91c6d83336e4c5f86c6cffd8975b0f375d3a10da8e243",
+        "cars_test_annos_withlabels": "790f75be8ea34eeded134cc559332baf23e30e91367e9ddca97d26ed9b895f05",
+        "car_devkit": "512b227b30e2f0a8aab9e09485786ab4479582073a144998da74d64b801fd288",
+    }
+
+    def resources(self, config: DatasetConfig) -> List[OnlineResource]:
+        resources: List[OnlineResource] = [HttpResource(self._URLS[config.split], sha256=self._CHECKSUM[config.split])]
+        if config.split == "train":
+            resources.append(HttpResource(url=self._URLS["car_devkit"], sha256=self._CHECKSUM["car_devkit"]))
+
+        else:
+            resources.append(
+                HttpResource(
+                    self._URLS["cars_test_annos_withlabels"], sha256=self._CHECKSUM["cars_test_annos_withlabels"]
+                )
+            )
+        return resources
+
+    def _prepare_sample(self, data: Tuple[Tuple[str, BinaryIO], Tuple[int, int, int, int, int, str]]) -> Dict[str, Any]:
+        image, target = data
+        path, buffer = image
+        image = EncodedImage.from_file(buffer)
+
+        return dict(
+            path=path,
+            image=image,
+            label=Label(target[4] - 1, categories=self.categories),
+            bounding_box=BoundingBox(target[:4], format="xyxy", image_size=image.image_size),
+        )
+
+    def _make_datapipe(
+        self,
+        resource_dps: List[IterDataPipe],
+        *,
+        config: DatasetConfig,
+    ) -> IterDataPipe[Dict[str, Any]]:
+
+        images_dp, targets_dp = resource_dps
+        if config.split == "train":
+            targets_dp = Filter(targets_dp, path_comparator("name", "cars_train_annos.mat"))
+        targets_dp = StanfordCarsLabelReader(targets_dp)
+        dp = Zipper(images_dp, targets_dp)
+        dp = hint_sharding(dp)
+        dp = hint_shuffling(dp)
+        return Mapper(dp, self._prepare_sample)
+
+    def _generate_categories(self, root: pathlib.Path) -> List[str]:
+        config = self.info.make_config(split="train")
+        resources = self.resources(config)
+
+        devkit_dp = resources[1].load(root)
+        meta_dp = Filter(devkit_dp, path_comparator("name", "cars_meta.mat"))
+        _, meta_file = next(iter(meta_dp))
+
+        return list(read_mat(meta_file, squeeze_me=True)["class_names"])