Python transforms.Compose方法代码示例

# 需要导入模块: from torchvision.transforms import transforms [as 别名]
# 或者: from torchvision.transforms.transforms import Compose [as 别名]
def preprocess(image: PIL.Image.Image, image_min_side: float, image_max_side: float) -> Tuple[Tensor, float]:
        # resize according to the rules:
        #   1. scale shorter side to IMAGE_MIN_SIDE
        #   2. after scaling, if longer side > IMAGE_MAX_SIDE, scale longer side to IMAGE_MAX_SIDE
        scale_for_shorter_side = image_min_side / min(image.width, image.height)
        longer_side_after_scaling = max(image.width, image.height) * scale_for_shorter_side
        scale_for_longer_side = (image_max_side / longer_side_after_scaling) if longer_side_after_scaling > image_max_side else 1
        scale = scale_for_shorter_side * scale_for_longer_side

        transform = transforms.Compose([
            transforms.Resize((round(image.height * scale), round(image.width * scale))),  # interpolation `BILINEAR` is applied by default
            transforms.ToTensor(),
            transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
        ])
        image = transform(image)

        return image, scale 

# 需要导入模块: from torchvision.transforms import transforms [as 别名]
# 或者: from torchvision.transforms.transforms import Compose [as 别名]
def preprocess(self,image: PIL.Image.Image, image_min_side: float, image_max_side: float) -> Tuple[Tensor, float]:
        # resize according to the rules:
        #   1. scale shorter side to IMAGE_MIN_SIDE
        #   2. after scaling, if longer side > IMAGE_MAX_SIDE, scale longer side to IMAGE_MAX_SIDE
        scale_for_shorter_side = image_min_side / min(image.width, image.height)
        longer_side_after_scaling = max(image.width, image.height) * scale_for_shorter_side
        scale_for_longer_side = (image_max_side / longer_side_after_scaling) if longer_side_after_scaling > image_max_side else 1
        scale = scale_for_shorter_side * scale_for_longer_side

        transform = transforms.Compose([
            transforms.Resize((round(image.height * scale), round(image.width * scale))),  # interpolation `BILINEAR` is applied by default
            transforms.ToTensor(),
            transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
        ])
        image = transform(image)

        return image, scale 

# 需要导入模块: from torchvision.transforms import transforms [as 别名]
# 或者: from torchvision.transforms.transforms import Compose [as 别名]
def pil_to_tensor(img, shape=(64, 64, 3), transform=None):
    """
    Convert PIL image to float tensor

    :param img: PIL image
    :type img: Image.Image
    :param shape: image shape in (H, W, C)
    :type shape: tuple or list
    :param transform: image transform
    :return: tensor
    :rtype: torch.Tensor
    """
    if transform is None:
        transform = transforms.Compose((
            transforms.Resize(shape[0]),
            transforms.ToTensor()
        ))
    return transform(img) 

# 需要导入模块: from torchvision.transforms import transforms [as 别名]
# 或者: from torchvision.transforms.transforms import Compose [as 别名]
def get_datasets(initial_pool):
    transform = transforms.Compose(
        [transforms.Resize((224, 224)),
         transforms.RandomHorizontalFlip(),
         transforms.RandomRotation(30),
         transforms.ToTensor(),
         transforms.Normalize(3 * [0.5], 3 * [0.5]), ])
    test_transform = transforms.Compose(
        [
            transforms.Resize((224, 224)),
            transforms.ToTensor(),
            transforms.Normalize(3 * [0.5], 3 * [0.5]),
        ]
    )
    # Note: We use the test set here as an example. You should make your own validation set.
    train_ds = datasets.CIFAR10('.', train=True,
                                transform=transform, target_transform=None, download=True)
    test_set = datasets.CIFAR10('.', train=False,
                                transform=test_transform, target_transform=None, download=True)

    active_set = ActiveLearningDataset(train_ds, pool_specifics={'transform': test_transform})

    # We start labeling randomly.
    active_set.label_randomly(initial_pool)
    return active_set, test_set 

# 需要导入模块: from torchvision.transforms import transforms [as 别名]
# 或者: from torchvision.transforms.transforms import Compose [as 别名]
def get_training_set_gt(dataset_path: str, image_size: ImageSize):
    num_joints = 15
    left_indexes: List[int] = [3, 4, 5, 9, 10, 11]
    right_indexes: List[int] = [6, 7, 8, 12, 13, 14]

    datasets: List[EhpiLSTMDataset] = [
        EhpiLSTMDataset(os.path.join(dataset_path, "JOURNAL_2019_03_GT_30fps"),
                        transform=transforms.Compose([
                            RemoveJointsOutsideImgEhpi(image_size),
                            ScaleEhpi(image_size),
                            TranslateEhpi(image_size),
                            FlipEhpi(left_indexes=left_indexes, right_indexes=right_indexes),
                            NormalizeEhpi(image_size)
                        ]), num_joints=num_joints),
    ]
    for dataset in datasets:
        dataset.print_label_statistics()

    return ConcatDataset(datasets) 

# 需要导入模块: from torchvision.transforms import transforms [as 别名]
# 或者: from torchvision.transforms.transforms import Compose [as 别名]
def get_training_posealgo(dataset_path: str, image_size: ImageSize):
    num_joints = 15
    left_indexes: List[int] = [3, 4, 5, 9, 10, 11]
    right_indexes: List[int] = [6, 7, 8, 12, 13, 14]

    datasets: List[EhpiLSTMDataset] = [
        EhpiLSTMDataset(os.path.join(dataset_path, "JOURNAL_2019_03_POSEALGO_30fps"),
                        transform=transforms.Compose([
                            RemoveJointsOutsideImgEhpi(image_size),
                            ScaleEhpi(image_size),
                            TranslateEhpi(image_size),
                            FlipEhpi(left_indexes=left_indexes, right_indexes=right_indexes),
                            NormalizeEhpi(image_size)
                        ]), num_joints=num_joints),
    ]
    for dataset in datasets:
        dataset.print_label_statistics()

    return ConcatDataset(datasets) 

# 需要导入模块: from torchvision.transforms import transforms [as 别名]
# 或者: from torchvision.transforms.transforms import Compose [as 别名]
def get_test_set_lab(dataset_path: str, image_size: ImageSize):
    num_joints = 15
    datasets = [
    EhpiLSTMDataset(os.path.join(dataset_path, "JOURNAL_2019_03_TEST_VUE01_30FPS"),
                             transform=transforms.Compose([
                                 RemoveJointsOutsideImgEhpi(image_size),
                                 NormalizeEhpi(image_size)
                             ]), num_joints=num_joints, dataset_part=DatasetPart.TEST),
    EhpiLSTMDataset(os.path.join(dataset_path, "JOURNAL_2019_03_TEST_VUE02_30FPS"),
                             transform=transforms.Compose([
                                 RemoveJointsOutsideImgEhpi(image_size),
                                 NormalizeEhpi(image_size)
                             ]), num_joints=num_joints, dataset_part=DatasetPart.TEST),
    ]
    for dataset in datasets:
        dataset.print_label_statistics()
    return ConcatDataset(datasets) 

# 需要导入模块: from torchvision.transforms import transforms [as 别名]
# 或者: from torchvision.transforms.transforms import Compose [as 别名]
def prepare_data(images, color_mode='BGR', new_shape=416, color=(127.5, 127.5, 127.5), mode='square'):
    images_ok = np.zeros((images.shape[0], new_shape, new_shape, 3), dtype=images[0].dtype)
    images_tensor = torch.zeros((images.shape[0], 3, new_shape, new_shape), dtype=torch.float32)
    for i in range(len(images)):
        if color_mode == 'BGR':
            images[i] = cv2.cvtColor(images[i], cv2.COLOR_BGR2RGB)
        elif color_mode == 'RGB':
            pass
        else:
            raise NotImplementedError
        images_ok[i], _, _, _ = letterbox(images[i], new_shape, color, mode)

        images_tensor[i] = transforms.Compose([
            transforms.ToPILImage(),
            transforms.ToTensor(),
        ])(images_ok[i])

    return images_tensor 

# 需要导入模块: from torchvision.transforms import transforms [as 别名]
# 或者: from torchvision.transforms.transforms import Compose [as 别名]
def load_images(img_path):
    # imread from img_path
    img = cv2.imread(img_path)
    img = cv2.resize(img, (224, 224))

    # pytorch must normalize the pic by 
    # mean = [0.485, 0.456, 0.406]
    # std = [0.229, 0.224, 0.225]
    transform = transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize(mean=[0.485, 0.456, 0.406],std=[0.229, 0.224, 0.225])
        ])
    
    img = transform(img)
    img.unsqueeze_(0)
    #img_s = img.numpy()
    #img_s = np.transpose(img_s, (1, 2, 0))
    #cv2.imshow("test img", img_s)
    #cv2.waitKey()
    return img 

# 需要导入模块: from torchvision.transforms import transforms [as 别名]
# 或者: from torchvision.transforms.transforms import Compose [as 别名]
def get_transforms(eval=False, aug=None):
    trans = []

    if aug["randcrop"] and not eval:
        trans.append(transforms.RandomCrop(aug["randcrop"]))

    if aug["randcrop"] and eval:
        trans.append(transforms.CenterCrop(aug["randcrop"]))

    if aug["flip"] and not eval:
        trans.append(transforms.RandomHorizontalFlip())

    if aug["grayscale"]:
        trans.append(transforms.Grayscale())
        trans.append(transforms.ToTensor())
        trans.append(transforms.Normalize(mean=aug["bw_mean"], std=aug["bw_std"]))
    elif aug["mean"]:
        trans.append(transforms.ToTensor())
        trans.append(transforms.Normalize(mean=aug["mean"], std=aug["std"]))
    else:
        trans.append(transforms.ToTensor())

    trans = transforms.Compose(trans)
    return trans 

# 需要导入模块: from torchvision.transforms import transforms [as 别名]
# 或者: from torchvision.transforms.transforms import Compose [as 别名]
def get_test_set(dataset_path: str, image_size: ImageSize):
    num_joints = 15
    return EhpiDataset(os.path.join(dataset_path, "2019_03_13_Freilichtmuseum_30FPS"),
                       transform=transforms.Compose([
                           RemoveJointsOutsideImgEhpi(image_size),
                           NormalizeEhpi(image_size)
                       ]), dataset_part=DatasetPart.TEST, num_joints=num_joints) 

# 需要导入模块: from torchvision.transforms import transforms [as 别名]
# 或者: from torchvision.transforms.transforms import Compose [as 别名]
def get_training_set(dataset_path: str, image_size: ImageSize):
    num_joints = 15
    left_indexes: List[int] = [3, 4, 5, 9, 10, 11]
    right_indexes: List[int] = [6, 7, 8, 12, 13, 14]
    return EhpiDataset(os.path.join(dataset_path, "JHMDB_ITSC-1/"),
                       transform=transforms.Compose([
                           RemoveJointsOutsideImgEhpi(image_size),
                           RemoveJointsEhpi(indexes_to_remove=foot_indexes, indexes_to_remove_2=knee_indexes,
                                            probability=0.25),
                           ScaleEhpi(image_size),
                           TranslateEhpi(image_size),
                           FlipEhpi(left_indexes=left_indexes, right_indexes=right_indexes),
                           NormalizeEhpi(image_size)
                       ]), num_joints=num_joints) 

# 需要导入模块: from torchvision.transforms import transforms [as 别名]
# 或者: from torchvision.transforms.transforms import Compose [as 别名]
def get_sim_pose_algo_only(dataset_path: str, image_size: ImageSize):
    num_joints = 15
    left_indexes: List[int] = [3, 4, 5, 9, 10, 11]
    right_indexes: List[int] = [6, 7, 8, 12, 13, 14]

    datasets: List[EhpiDataset] = [
        EhpiDataset(os.path.join(dataset_path, "ofp_sim_pose_algo_equal_30fps"),
                    transform=transforms.Compose([
                        RemoveJointsOutsideImgEhpi(image_size),
                        RemoveJointsEhpi(indexes_to_remove=foot_indexes, indexes_to_remove_2=knee_indexes,
                                         probability=0.25),
                        ScaleEhpi(image_size),
                        TranslateEhpi(image_size),
                        FlipEhpi(left_indexes=left_indexes, right_indexes=right_indexes),
                        NormalizeEhpi(image_size)
                    ]), num_joints=num_joints),
        EhpiDataset(os.path.join(dataset_path, "ofp_from_mocap_pose_algo_30fps"),
                    transform=transforms.Compose([
                        RemoveJointsOutsideImgEhpi(image_size),
                        RemoveJointsEhpi(indexes_to_remove=foot_indexes, indexes_to_remove_2=knee_indexes,
                                         probability=0.25),
                        ScaleEhpi(image_size),
                        TranslateEhpi(image_size),
                        FlipEhpi(left_indexes=left_indexes, right_indexes=right_indexes),
                        NormalizeEhpi(image_size)
                    ]), num_joints=num_joints),
    ]
    for dataset in datasets:
        dataset.print_label_statistics()

    return ConcatDataset(datasets) 

# 需要导入模块: from torchvision.transforms import transforms [as 别名]
# 或者: from torchvision.transforms.transforms import Compose [as 别名]
def get_sim_gt_only(dataset_path: str, image_size: ImageSize):
    num_joints = 15
    left_indexes: List[int] = [3, 4, 5, 9, 10, 11]
    right_indexes: List[int] = [6, 7, 8, 12, 13, 14]

    datasets: List[EhpiDataset] = [
        EhpiDataset(os.path.join(dataset_path, "ofp_sim_gt_equal_30fps"),
                    transform=transforms.Compose([
                        RemoveJointsOutsideImgEhpi(image_size),
                        RemoveJointsEhpi(indexes_to_remove=foot_indexes, indexes_to_remove_2=knee_indexes,
                                         probability=0.25),
                        ScaleEhpi(image_size),
                        TranslateEhpi(image_size),
                        FlipEhpi(left_indexes=left_indexes, right_indexes=right_indexes),
                        NormalizeEhpi(image_size)
                    ]), num_joints=num_joints),
        EhpiDataset(os.path.join(dataset_path, "ofp_from_mocap_gt_30fps"),
                    transform=transforms.Compose([
                        RemoveJointsOutsideImgEhpi(image_size),
                        RemoveJointsEhpi(indexes_to_remove=foot_indexes, indexes_to_remove_2=knee_indexes,
                                         probability=0.25),
                        ScaleEhpi(image_size),
                        TranslateEhpi(image_size),
                        FlipEhpi(left_indexes=left_indexes, right_indexes=right_indexes),
                        NormalizeEhpi(image_size)
                    ]), num_joints=num_joints),
    ]
    for dataset in datasets:
        dataset.print_label_statistics()

    return ConcatDataset(datasets) 

# 需要导入模块: from torchvision.transforms import transforms [as 别名]
# 或者: from torchvision.transforms.transforms import Compose [as 别名]
def get_training_set(dataset_path: str, image_size: ImageSize):
    num_joints = 15
    left_indexes: List[int] = [3, 4, 5, 9, 10, 11]
    right_indexes: List[int] = [6, 7, 8, 12, 13, 14]
    return EhpiDataset(dataset_path,
                       transform=transforms.Compose([
                           RemoveJointsOutsideImgEhpi(image_size),
                           RemoveJointsEhpi(indexes_to_remove=foot_indexes, indexes_to_remove_2=knee_indexes,
                                            probability=0.25),
                           ScaleEhpi(image_size),
                           TranslateEhpi(image_size),
                           FlipEhpi(left_indexes=left_indexes, right_indexes=right_indexes),
                           NormalizeEhpi(image_size)
                       ]), num_joints=num_joints)