def get_transforms()

in transforms_v2.py [0:0]

• 43 lines of code
• 8 McCabe index (conditional complexity)

def get_transforms(input_size=224,test_size=224, kind='full', crop=True, need=('train', 'val'), backbone=None):
    mean, std = [0.485, 0.456, 0.406], [0.229, 0.224, 0.225]
    if backbone is not None and backbone in ['pnasnet5large', 'nasnetamobile']:
        mean, std = [0.5, 0.5, 0.5], [0.5, 0.5, 0.5]
    transformations = {}
    if 'train' in need:
        if kind == 'torch':
            transformations['train'] = transforms.Compose([
                transforms.RandomResizedCrop(input_size),
                transforms.RandomHorizontalFlip(),
                transforms.ToTensor(),
                transforms.Normalize(mean, std),
            ])
        elif kind == 'full':
            transformations['train'] = transforms.Compose([
                transforms.RandomResizedCrop(input_size),
                transforms.RandomHorizontalFlip(),
                transforms.ColorJitter(0.3, 0.3, 0.3),
                transforms.ToTensor(),
                transforms.Normalize(mean, std),
            ])

        else:
            raise ValueError('Transforms kind {} unknown'.format(kind))
    if 'val' in need:
        if crop:
            transformations['val_test'] = transforms.Compose(
                [Resize(int((256 / 224) * test_size)),  # to maintain same ratio w.r.t. 224 images
                 transforms.CenterCrop(test_size),
                 transforms.ToTensor(),
                 transforms.Normalize(mean, std)])
            transformations['val_train'] = transforms.Compose(
                [Resize(int((256 / 224) * test_size)),  # to maintain same ratio w.r.t. 224 images
                 transforms.RandomHorizontalFlip(),
                 transforms.ColorJitter(0.05, 0.05, 0.05),
                 CenterCrop(test_size),
                 transforms.ToTensor(),
                 transforms.Normalize(mean, std)])
        else:
            transformations['val'] = transforms.Compose(
                [Resize(test_size, largest=True), 
                 transforms.ToTensor(),
                 transforms.Normalize(mean, std)])
    return transformations