| import os |
| import pickle |
|
|
| from .utils import * |
|
|
| from .oxford_pets import OxfordPets |
|
|
|
|
| class SUN397(DatasetBase): |
|
|
| dataset_dir = "sun397" |
|
|
| def __init__(self, root, num_shots=0, seed=1, subsample_classes='all'): |
| root = os.path.abspath(os.path.expanduser(root)) |
| self.dataset_dir = os.path.join(root, self.dataset_dir) |
| self.image_dir = os.path.join(self.dataset_dir, "SUN397") |
| self.split_path = os.path.join(self.dataset_dir, "split_zhou_SUN397.json") |
| self.split_fewshot_dir = os.path.join(self.dataset_dir, "split_fewshot") |
| mkdir_if_missing(self.split_fewshot_dir) |
|
|
| if os.path.exists(self.split_path): |
| train, val, test = OxfordPets.read_split(self.split_path, self.image_dir) |
| else: |
| classnames = [] |
| with open(os.path.join(self.dataset_dir, "ClassName.txt"), "r") as f: |
| lines = f.readlines() |
| for line in lines: |
| line = line.strip()[1:] |
| classnames.append(line) |
| cname2lab = {c: i for i, c in enumerate(classnames)} |
| trainval = self.read_data(cname2lab, "Training_01.txt") |
| test = self.read_data(cname2lab, "Testing_01.txt") |
| train, val = OxfordPets.split_trainval(trainval) |
| OxfordPets.save_split(train, val, test, self.split_path, self.image_dir) |
|
|
| if num_shots >= 1: |
| preprocessed = os.path.join(self.split_fewshot_dir, f"shot_{num_shots}-seed_{seed}.pkl") |
| |
| if os.path.exists(preprocessed): |
| print(f"Loading preprocessed few-shot data from {preprocessed}") |
| with open(preprocessed, "rb") as file: |
| data = pickle.load(file) |
| train, val = data["train"], data["val"] |
| else: |
| train = self.generate_fewshot_dataset(train, num_shots=num_shots) |
| val = self.generate_fewshot_dataset(val, num_shots=min(num_shots, 4)) |
| data = {"train": train, "val": val} |
| print(f"Saving preprocessed few-shot data to {preprocessed}") |
| with open(preprocessed, "wb") as file: |
| pickle.dump(data, file, protocol=pickle.HIGHEST_PROTOCOL) |
|
|
| subsample = subsample_classes |
| train, val, test = OxfordPets.subsample_classes(train, val, test, subsample=subsample) |
|
|
| self.templates = [ |
| lambda c: f"a photo of a {c}.", |
| lambda c: f"a photo of the {c}.", |
| ] |
|
|
| super().__init__(train_x=train, val=val, test=test) |
|
|
| def read_data(self, cname2lab, text_file): |
| text_file = os.path.join(self.dataset_dir, text_file) |
| items = [] |
|
|
| with open(text_file, "r") as f: |
| lines = f.readlines() |
| for line in lines: |
| imname = line.strip()[1:] |
| classname = os.path.dirname(imname) |
| label = cname2lab[classname] |
| impath = os.path.join(self.image_dir, imname) |
|
|
| names = classname.split("/")[1:] |
| names = names[::-1] |
| classname = " ".join(names) |
|
|
| item = Datum(impath=impath, label=label, classname=classname) |
| items.append(item) |
|
|
| return items |
|
|
