# Set up vg_<split> # for version in ['1600-400-20']: # for split in ['minitrain', 'train', 'minival', 'val', 'test']: # name = 'vg_{}_{}'.format(version,split) # __sets[name] = (lambda split=split, version=version: vg(version, split)) for version in [ '150-50-20', '150-50-50', '500-150-80', '750-250-150', '1750-700-450', '1600-400-20' ]: for split in [ 'minitrain', 'smalltrain', 'train', 'minival', 'smallval', 'val', 'test' ]: name = 'vg_{}_{}'.format(version, split) __sets[name] = ( lambda split=split, version=version: vg(version, split)) # set up image net. for split in ['train', 'val', 'val1', 'val2', 'test']: name = 'imagenet_{}'.format(split) devkit_path = 'data/imagenet/ILSVRC/devkit' data_path = 'data/imagenet/ILSVRC' __sets[name] = (lambda split=split, devkit_path=devkit_path, data_path= data_path: imagenet(split, devkit_path, data_path)) def get_imdb(name): """Get an imdb (image database) by name.""" if name not in __sets: raise KeyError('Unknown dataset: {}'.format(name)) return __sets[name]()
# Set up coco_2015_<split> for year in ['2015']: for split in ['test', 'test-dev']: name = 'coco_{}_{}'.format(year, split) __sets[name] = (lambda split=split, year=year: coco(split, year)) # Set up vg_<split> # for version in ['1600-400-20']: # for split in ['minitrain', 'train', 'minival', 'val', 'test']: # name = 'vg_{}_{}'.format(version,split) # __sets[name] = (lambda split=split, version=version: vg(version, split)) for version in ['150-50-20', '150-50-50', '500-150-80', '750-250-150', '1750-700-450', '1600-400-20']: for split in ['minitrain', 'smalltrain', 'train', 'minival', 'smallval', 'val', 'test']: name = 'vg_{}_{}'.format(version,split) __sets[name] = (lambda split=split, version=version: vg(version, split)) # set up image net. for split in ['train', 'val', 'val1', 'val2', 'test']: name = 'imagenet_{}'.format(split) devkit_path = 'data/imagenet/ILSVRC/devkit' data_path = 'data/imagenet/ILSVRC' __sets[name] = (lambda split=split, devkit_path=devkit_path, data_path=data_path: imagenet(split,devkit_path,data_path)) # Set up pdfpages for split in ['train', 'validation']: name = 'pdfpages_{}'.format(split) # path = '/home/ubuntu/persist/data_gen/data/pageseg/20190226' path = f'/opt/ml/input/data/training' __sets[name] = (lambda split=split: PDFPages(split, path=path))