Python transforms.Compose方法代码示例

# 需要导入模块: from mxnet.gluon.data.vision import transforms [as 别名]
# 或者: from mxnet.gluon.data.vision.transforms import Compose [as 别名]
def test_transformer():
    from mxnet.gluon.data.vision import transforms

    transform = transforms.Compose([
        transforms.Resize(300),
        transforms.Resize(300, keep_ratio=True),
        transforms.CenterCrop(256),
        transforms.RandomResizedCrop(224),
        transforms.RandomFlipLeftRight(),
        transforms.RandomColorJitter(0.1, 0.1, 0.1, 0.1),
        transforms.RandomBrightness(0.1),
        transforms.RandomContrast(0.1),
        transforms.RandomSaturation(0.1),
        transforms.RandomHue(0.1),
        transforms.RandomLighting(0.1),
        transforms.ToTensor(),
        transforms.Normalize([0, 0, 0], [1, 1, 1])])

    transform(mx.nd.ones((245, 480, 3), dtype='uint8')).wait_to_read() 

# 需要导入模块: from mxnet.gluon.data.vision import transforms [as 别名]
# 或者: from mxnet.gluon.data.vision.transforms import Compose [as 别名]
def crop_resize_normalize(img, bbox_list, output_size,
                          mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)):
    output_list = []
    transform_test = transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize(mean, std)
    ])
    for bbox in bbox_list:
        x0 = max(int(bbox[0]), 0)
        y0 = max(int(bbox[1]), 0)
        x1 = min(int(bbox[2]), int(img.shape[1]))
        y1 = min(int(bbox[3]), int(img.shape[0]))
        w = x1 - x0
        h = y1 - y0
        res_img = image.fixed_crop(nd.array(img), x0, y0, w, h, (output_size[1], output_size[0]))
        res_img = transform_test(res_img)
        output_list.append(res_img)
    output_array = nd.stack(*output_list)
    return output_array 

# 需要导入模块: from mxnet.gluon.data.vision import transforms [as 别名]
# 或者: from mxnet.gluon.data.vision.transforms import Compose [as 别名]
def create_transformer(self):
        train_tforms, eval_tforms = [transforms.Resize(self.args.resize)], [transforms.Resize(self.args.resize)]

        if self.args.random_crop:
            train_tforms.append(transforms.RandomResizedCrop(self.args.size, scale=(0.8, 1.2)))
        else:
            train_tforms.append(transforms.CenterCrop(self.args.size))

        eval_tforms.append(transforms.CenterCrop(self.args.size))

        if self.args.flip:
            train_tforms.append(transforms.RandomFlipLeftRight())

        if self.args.random_color:
            train_tforms.append(transforms.RandomColorJitter(self.args.color_jitter, self.args.color_jitter,
                                                             self.args.color_jitter, 0.1))

        train_tforms.extend([transforms.ToTensor(), transforms.Normalize(self.args.mean, self.args.std)])
        eval_tforms.extend([transforms.ToTensor(), transforms.Normalize(self.args.mean, self.args.std)])

        train_tforms = transforms.Compose(train_tforms)
        eval_tforms = transforms.Compose(eval_tforms)

        return train_tforms, eval_tforms 

# 需要导入模块: from mxnet.gluon.data.vision import transforms [as 别名]
# 或者: from mxnet.gluon.data.vision.transforms import Compose [as 别名]
def cifar10_train_transform(ds_metainfo,
                            mean_rgb=(0.4914, 0.4822, 0.4465),
                            std_rgb=(0.2023, 0.1994, 0.2010),
                            jitter_param=0.4,
                            lighting_param=0.1):
    assert (ds_metainfo is not None)
    assert (ds_metainfo.input_image_size[0] == 32)
    return transforms.Compose([
        RandomCrop(
            size=32,
            pad=4),
        transforms.RandomFlipLeftRight(),
        transforms.RandomColorJitter(
            brightness=jitter_param,
            contrast=jitter_param,
            saturation=jitter_param),
        transforms.RandomLighting(lighting_param),
        transforms.ToTensor(),
        transforms.Normalize(
            mean=mean_rgb,
            std=std_rgb)
    ]) 

# 需要导入模块: from mxnet.gluon.data.vision import transforms [as 别名]
# 或者: from mxnet.gluon.data.vision.transforms import Compose [as 别名]
def crop_resize_normalize(img, bbox_list, output_size):
    output_list = []
    transform_test = transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ])
    for bbox in bbox_list:
        x0 = max(int(bbox[0]), 0)
        y0 = max(int(bbox[1]), 0)
        x1 = min(int(bbox[2]), int(img.shape[1]))
        y1 = min(int(bbox[3]), int(img.shape[0]))
        w = x1 - x0
        h = y1 - y0
        res_img = image.fixed_crop(nd.array(img), x0, y0, w, h, (output_size[1], output_size[0]))
        res_img = transform_test(res_img)
        output_list.append(res_img)
    output_array = nd.stack(*output_list)
    return output_array 

# 需要导入模块: from mxnet.gluon.data.vision import transforms [as 别名]
# 或者: from mxnet.gluon.data.vision.transforms import Compose [as 别名]
def get_data_loader(data_dir, batch_size, num_workers):
    normalize = transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    def batch_fn(batch, ctx):
        data = gluon.utils.split_and_load(batch[0], ctx_list=ctx, batch_axis=0)
        label = gluon.utils.split_and_load(batch[1], ctx_list=ctx, batch_axis=0)
        return data, label
    if opt.mode == 'symbolic':
        val_data = mx.io.NDArrayIter(
            mx.nd.random.normal(shape=(opt.dataset_size, 3, 224, 224)),
            label=mx.nd.array(range(opt.dataset_size)),
            batch_size=batch_size,
        )
        transform_test = transforms.Compose([
            transforms.Resize(256, keep_ratio=True),
            transforms.CenterCrop(224),
            transforms.ToTensor(),
            normalize
        ])
        val_data = gluon.data.DataLoader(
            imagenet.classification.ImageNet(data_dir, train=False).transform_first(transform_test),
            batch_size=batch_size, shuffle=False, num_workers=num_workers)

    return val_data, batch_fn 

# 需要导入模块: from mxnet.gluon.data.vision import transforms [as 别名]
# 或者: from mxnet.gluon.data.vision.transforms import Compose [as 别名]
def cifar_evaluate(net, args):
    batch_size = args.batch_size
    batch_size *= max(1, args.num_gpus)

    ctx = [mx.gpu(i) for i in range(args.num_gpus)] if args.num_gpus > 0 else [mx.cpu()]
    net.collect_params().reset_ctx(ctx)
    metric = mx.metric.Accuracy()
    transform_test = transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize([0.4914, 0.4822, 0.4465], [0.2023, 0.1994, 0.2010])
    ])
    val_data = gluon.data.DataLoader(
        gluon.data.vision.CIFAR10(train=False).transform_first(transform_test),
        batch_size=batch_size, shuffle=False, num_workers=args.num_workers)

    for i, batch in enumerate(val_data):
        data = gluon.utils.split_and_load(batch[0], ctx_list=ctx, batch_axis=0)
        label = gluon.utils.split_and_load(batch[1], ctx_list=ctx, batch_axis=0)
        outputs = [net(X) for X in data]
        metric.update(label, outputs)
    return metric.get()[1] 

# 需要导入模块: from mxnet.gluon.data.vision import transforms [as 别名]
# 或者: from mxnet.gluon.data.vision.transforms import Compose [as 别名]
def test_transformer():
    from mxnet.gluon.data.vision import transforms

    transform = transforms.Compose([
		transforms.Resize(300),
		transforms.CenterCrop(256),
		transforms.RandomResizedCrop(224),
		transforms.RandomFlipLeftRight(),
		transforms.RandomColorJitter(0.1, 0.1, 0.1, 0.1),
		transforms.RandomBrightness(0.1),
		transforms.RandomContrast(0.1),
		transforms.RandomSaturation(0.1),
		transforms.RandomHue(0.1),
		transforms.RandomLighting(0.1),
		transforms.ToTensor(),
		transforms.Normalize([0, 0, 0], [1, 1, 1])])

    transform(mx.nd.ones((245, 480, 3), dtype='uint8')).wait_to_read() 

# 需要导入模块: from mxnet.gluon.data.vision import transforms [as 别名]
# 或者: from mxnet.gluon.data.vision.transforms import Compose [as 别名]
def get_data(batch_size, test_set, query_set):
    normalizer = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])

    transform_test = transforms.Compose([
        transforms.Resize(size=(128, 384), interpolation=1),
        transforms.ToTensor(),
        normalizer])

    test_imgs = ImageTxtDataset(test_set, transform=transform_test)
    query_imgs = ImageTxtDataset(query_set, transform=transform_test)

    test_data = gluon.data.DataLoader(test_imgs, batch_size, shuffle=False, last_batch='keep', num_workers=8)
    query_data = gluon.data.DataLoader(query_imgs, batch_size, shuffle=False, last_batch='keep', num_workers=8)
    return test_data, query_data 

# 需要导入模块: from mxnet.gluon.data.vision import transforms [as 别名]
# 或者: from mxnet.gluon.data.vision.transforms import Compose [as 别名]
def get_data_iters(batch_size):
    train_set, val_set = LabelList(ratio=opt.ratio, root=opt.dataset_root, name=opt.dataset)

    normalizer = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])

    transform_train = transforms.Compose([
        transforms.Resize(size=(opt.img_width, opt.img_height), interpolation=1),
        transforms.RandomFlipLeftRight(),
        RandomCrop(size=(opt.img_width, opt.img_height), pad=opt.pad),
        transforms.ToTensor(),
        normalizer])

    train_imgs = ImageTxtDataset(train_set, transform=transform_train)
    train_data = gluon.data.DataLoader(train_imgs, batch_size, shuffle=True, last_batch='discard', num_workers=opt.num_workers)

    if opt.ratio < 1:
        transform_test = transforms.Compose([
            transforms.Resize(size=(opt.img_width, opt.img_height), interpolation=1),
            transforms.ToTensor(),
            normalizer])

        val_imgs = ImageTxtDataset(val_set, transform=transform_test)
        val_data = gluon.data.DataLoader(val_imgs, batch_size, shuffle=True, last_batch='discard', num_workers=opt.num_workers)
    else:
        val_data = None

    return train_data, val_data 

# 需要导入模块: from mxnet.gluon.data.vision import transforms [as 别名]
# 或者: from mxnet.gluon.data.vision.transforms import Compose [as 别名]
def get_val_data(rec_val, batch_size, data_nthreads, input_size, crop_ratio):
    def val_batch_fn(batch, ctx):
        data = batch[0].as_in_context(ctx)
        label = batch[1].as_in_context(ctx)
        return data, label

    normalize = transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    crop_ratio = crop_ratio if crop_ratio > 0 else 0.875
    resize = int(math.ceil(input_size/crop_ratio))

    from gluoncv.utils.transforms import EfficientNetCenterCrop
    from autogluon.utils import pil_transforms

    if input_size >= 320:
        transform_test = transforms.Compose([
            pil_transforms.ToPIL(),
            EfficientNetCenterCrop(input_size),
            pil_transforms.Resize((input_size, input_size), interpolation=Image.BICUBIC),
            pil_transforms.ToNDArray(),
            transforms.ToTensor(),
            normalize
        ])
    else:
        transform_test = transforms.Compose([
            transforms.Resize(resize, keep_ratio=True),
            transforms.CenterCrop(input_size),
            transforms.ToTensor(),
            normalize
        ])

    val_set = mx.gluon.data.vision.ImageRecordDataset(rec_val).transform_first(transform_test)

    val_sampler = SplitSampler(len(val_set), num_parts=num_workers, part_index=rank)
    val_data = gluon.data.DataLoader(val_set, batch_size=batch_size,
                                     num_workers=data_nthreads,
                                     sampler=val_sampler)

    return val_data, val_batch_fn

# Horovod: pin GPU to local rank 

# 需要导入模块: from mxnet.gluon.data.vision import transforms [as 别名]
# 或者: from mxnet.gluon.data.vision.transforms import Compose [as 别名]
def transform_eval(imgs, resize_short=256, crop_size=224,
                   mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)):
    """A util function to transform all images to tensors as network input by applying
    normalizations. This function support 1 NDArray or iterable of NDArrays.

    Parameters
    ----------
    imgs : NDArray or iterable of NDArray
        Image(s) to be transformed.
    resize_short : int, default=256
        Resize image short side to this value and keep aspect ratio.
    crop_size : int, default=224
        After resize, crop the center square of size `crop_size`
    mean : iterable of float
        Mean pixel values.
    std : iterable of float
        Standard deviations of pixel values.

    Returns
    -------
    mxnet.NDArray or list of such tuple
        A (1, 3, H, W) mxnet NDArray as input to network
        If multiple image names are supplied, return a list.
    """
    if isinstance(imgs, mx.nd.NDArray):
        imgs = [imgs]
    for im in imgs:
        assert isinstance(im, mx.nd.NDArray), "Expect NDArray, got {}".format(type(im))

    transform_fn = transforms.Compose([
        transforms.Resize(resize_short, keep_ratio=True),
        transforms.CenterCrop(crop_size),
        transforms.ToTensor(),
        transforms.Normalize(mean, std)
    ])

    res = [transform_fn(img).expand_dims(0) for img in imgs]

    if len(res) == 1:
        return res[0]
    return res 

# 需要导入模块: from mxnet.gluon.data.vision import transforms [as 别名]
# 或者: from mxnet.gluon.data.vision.transforms import Compose [as 别名]
def create_loader(self):
        """
        Overwrite the data loader function
        :return: pairwised data loader, None, eval source loader, test target loader
        """
        cpus = cpu_count()

        train_tforms, eval_tforms = [transforms.Resize(self.args.resize)], [transforms.Resize(self.args.resize)]

        if self.args.random_crop:
            train_tforms.append(transforms.RandomResizedCrop(self.args.size, scale=(0.8, 1.2)))
        else:
            train_tforms.append(transforms.CenterCrop(self.args.size))

        eval_tforms.append(transforms.CenterCrop(self.args.size))

        if self.args.flip:
            train_tforms.append(transforms.RandomFlipLeftRight())

        if self.args.random_color:
            train_tforms.append(transforms.RandomColorJitter(self.args.color_jitter, self.args.color_jitter,
                                                             self.args.color_jitter, 0.1))

        train_tforms.extend([transforms.ToTensor(), transforms.Normalize(self.args.mean, self.args.std)])
        eval_tforms.extend([transforms.ToTensor(), transforms.Normalize(self.args.mean, self.args.std)])

        train_tforms = transforms.Compose(train_tforms)
        eval_tforms = transforms.Compose(eval_tforms)

        if 'digits' in self.args.cfg:
            trs_set, tes_set, tet_set = self.create_digits_datasets(train_tforms, eval_tforms)
        elif 'office' in self.args.cfg:
            trs_set, tes_set, tet_set = self.create_office_datasets(train_tforms, eval_tforms)
        elif 'visda' in self.args.cfg:
            trs_set, tes_set, tet_set = self.create_visda_datasets(train_tforms, eval_tforms)
        else:
            raise NotImplementedError

        self.train_src_loader = DataLoader(trs_set, self.args.bs, shuffle=True, num_workers=cpus)
        self.test_src_loader = DataLoader(tes_set, self.args.bs, shuffle=False, num_workers=cpus)
        self.test_tgt_loader = DataLoader(tet_set, self.args.bs, shuffle=False, num_workers=cpus) 

# 需要导入模块: from mxnet.gluon.data.vision import transforms [as 别名]
# 或者: from mxnet.gluon.data.vision.transforms import Compose [as 别名]
def get_test_data_source(dataset_name,
                         dataset_dir,
                         batch_size,
                         num_workers):
    mean_rgb = (0.485, 0.456, 0.406)
    std_rgb = (0.229, 0.224, 0.225)

    transform_val = transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize(
            mean=mean_rgb,
            std=std_rgb)
    ])

    if dataset_name == "VOC":
        dataset_class = VOCSegDataset
    elif dataset_name == "ADE20K":
        dataset_class = ADE20KSegDataset
    elif dataset_name == "Cityscapes":
        dataset_class = CityscapesSegDataset
    elif dataset_name == "COCO":
        dataset_class = CocoSegDataset
    else:
        raise Exception('Unrecognized dataset: {}'.format(dataset_name))

    dataset = dataset_class(
        root=dataset_dir,
        mode="test",
        transform=transform_val)

    return gluon.data.DataLoader(
        dataset=dataset,
        batch_size=batch_size,
        shuffle=False,
        num_workers=num_workers) 

# 需要导入模块: from mxnet.gluon.data.vision import transforms [as 别名]
# 或者: from mxnet.gluon.data.vision.transforms import Compose [as 别名]
def voc_transform(ds_metainfo,
                  mean_rgb=(0.485, 0.456, 0.406),
                  std_rgb=(0.229, 0.224, 0.225)):
    assert (ds_metainfo is not None)
    return transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize(
            mean=mean_rgb,
            std=std_rgb)
    ])