in data/audioVisual_dataset.py [0:0]
def initialize(self, opt):
self.opt = opt
self.audios = []
#load hdf5 file here
h5f_path = os.path.join(opt.hdf5FolderPath, opt.mode+".h5")
h5f = h5py.File(h5f_path, 'r')
self.audios = h5f['audio'][:]
normalize = transforms.Normalize(
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]
)
vision_transform_list = [transforms.ToTensor(), normalize]
self.vision_transform = transforms.Compose(vision_transform_list)