File size: 3,013 Bytes
8c6b5ee |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 |
import os
import pickle
from dassl.data.datasets import DATASET_REGISTRY, Datum, DatasetBase
from dassl.utils import mkdir_if_missing
from .oxford_pets import OxfordPets
@DATASET_REGISTRY.register()
class FGVCAircraft(DatasetBase):
dataset_dir = "fgvc_aircraft"
def __init__(self, cfg):
root = os.path.abspath(os.path.expanduser(cfg.DATASET.ROOT))
self.dataset_dir = os.path.join(root, self.dataset_dir)
self.image_dir = os.path.join(self.dataset_dir, "images")
self.split_fewshot_dir = os.path.join(self.dataset_dir, "split_fewshot")
mkdir_if_missing(self.split_fewshot_dir)
classnames = []
with open(os.path.join(self.dataset_dir, "variants.txt"), "r") as f:
lines = f.readlines()
for line in lines:
classnames.append(line.strip())
cname2lab = {c: i for i, c in enumerate(classnames)}
train = self.read_data(cname2lab, "images_variant_train.txt")
val = self.read_data(cname2lab, "images_variant_val.txt")
test = self.read_data(cname2lab, "images_variant_test.txt")
num_shots = cfg.DATASET.NUM_SHOTS
if num_shots >= 1:
seed = cfg.SEED
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 = cfg.DATASET.SUBSAMPLE_CLASSES
train, _, test = OxfordPets.subsample_classes(train, val, test, subsample=subsample)
super().__init__(train_x=train, val=test, test=test)
# if cfg.TRAINER.NAME == "SuPr":
self.all_classnames = OxfordPets.get_all_classnames(train, val, test)
def read_data(self, cname2lab, split_file):
filepath = os.path.join(self.dataset_dir, split_file)
items = []
with open(filepath, "r") as f:
lines = f.readlines()
for line in lines:
line = line.strip().split(" ")
imname = line[0] + ".jpg"
classname = " ".join(line[1:])
impath = os.path.join(self.image_dir, imname)
label = cname2lab[classname]
item = Datum(impath=impath, label=label, classname=classname)
items.append(item)
return items
|