DFA-MoE / MTIL_datasets /caltech101.py
boringKey's picture
Upload 126 files
3ea5987 verified
Raw
History Blame Contribute Delete
3.84 kB
import os
import pickle
from .utils import *
from .oxford_pets import OxfordPets
from .dtd import DescribableTextures as DTD
IGNORED = ["BACKGROUND_Google", "Faces_easy"]
NEW_CNAMES = {
"airplanes": "airplane",
"Faces": "face",
"Leopards": "leopard",
"Motorbikes": "motorbike",
}
class Caltech101(DatasetBase):
dataset_dir = "caltech-101"
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, "101_ObjectCategories")
self.split_path = os.path.join(self.dataset_dir, "split_zhou_Caltech101.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:
train, val, test = DTD.read_and_split_data(self.image_dir, ignored=IGNORED, new_cnames=NEW_CNAMES)
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 painting of a {c}.",
lambda c: f"a plastic {c}.",
lambda c: f"a sculpture of a {c}.",
lambda c: f"a sketch of a {c}.",
lambda c: f"a tattoo of a {c}.",
lambda c: f"a toy {c}.",
lambda c: f"a rendition of a {c}.",
lambda c: f"a embroidered {c}.",
lambda c: f"a cartoon {c}.",
lambda c: f"a {c} in a video game.",
lambda c: f"a plushie {c}.",
lambda c: f"a origami {c}.",
lambda c: f"art of a {c}.",
lambda c: f"graffiti of a {c}.",
lambda c: f"a drawing of a {c}.",
lambda c: f"a doodle of a {c}.",
lambda c: f"a photo of the {c}.",
lambda c: f"a painting of the {c}.",
lambda c: f"the plastic {c}.",
lambda c: f"a sculpture of the {c}.",
lambda c: f"a sketch of the {c}.",
lambda c: f"a tattoo of the {c}.",
lambda c: f"the toy {c}.",
lambda c: f"a rendition of the {c}.",
lambda c: f"the embroidered {c}.",
lambda c: f"the cartoon {c}.",
lambda c: f"the {c} in a video game.",
lambda c: f"the plushie {c}.",
lambda c: f"the origami {c}.",
lambda c: f"art of the {c}.",
lambda c: f"graffiti of the {c}.",
lambda c: f"a drawing of the {c}.",
lambda c: f"a doodle of the {c}.",
]
super().__init__(train_x=train, val=val, test=test)