def gen_bbox_transform(img_size):
transform = T.Compose([
T.NormalizeBbox(),
T.Resize(img_size),
T.DenormalizeBbox(),
])
def fun(img, bbox):
_, bbox = transform(img, bbox)
return torch.from_numpy(bbox)
return fun
def build_concept_quantization_clevr_dataset(args, configs, image_root, scenes_json):
import jactorch.transforms.bbox as T
image_transform = T.Compose([
T.NormalizeBbox(),
T.Resize(configs.data.image_size),
T.DenormalizeBbox(),
T.ToTensor(),
T.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])
from nscl.datasets.datasets import ConceptQuantizationDataset
dataset = ConceptQuantizationDataset(scenes_json, image_root=image_root, image_transform=image_transform)
return dataset
def build_clevr_dataset(args, configs, image_root, scenes_json, questions_json):
import jactorch.transforms.bbox as T
image_transform = T.Compose([
T.NormalizeBbox(),
T.Resize(configs.data.image_size),
T.DenormalizeBbox(),
T.ToTensor(),
T.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])
from nscl.datasets.datasets import NSCLDataset
dataset = NSCLDataset(
scenes_json, questions_json,
image_root=image_root, image_transform=image_transform,
vocab_json=args.data_vocab_json
)
return dataset
def build_concept_retrieval_clevrer_dataset(args, configs, program, image_root,
scenes_json):
import jactorch.transforms.bbox as T
image_transform = T.Compose([
T.NormalizeBbox(),
T.Resize(configs.data.image_size),
T.DenormalizeBbox(),
T.ToTensor(),
T.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
])
from nscl.datasets.datasets import ConceptRetrievalDataset
dataset = ConceptRetrievalDataset(program,
scenes_json,
image_root=image_root,
image_transform=image_transform)
return dataset