Python ops.ImageDecoder方法代码示例

# 需要导入模块: from nvidia.dali import ops [as 别名]
# 或者: from nvidia.dali.ops import ImageDecoder [as 别名]
def __init__(self, batch_size, num_threads, device_id, data_dir, crop, seed=12, local_rank=0, world_size=1,
                 spos_pre=False):
        super(HybridTrainPipe, self).__init__(batch_size, num_threads, device_id, seed=seed + device_id)
        color_space_type = types.BGR if spos_pre else types.RGB
        self.input = ops.FileReader(file_root=data_dir, shard_id=local_rank, num_shards=world_size, random_shuffle=True)
        self.decode = ops.ImageDecoder(device="mixed", output_type=color_space_type)
        self.res = ops.RandomResizedCrop(device="gpu", size=crop,
                                         interp_type=types.INTERP_LINEAR if spos_pre else types.INTERP_TRIANGULAR)
        self.twist = ops.ColorTwist(device="gpu")
        self.jitter_rng = ops.Uniform(range=[0.6, 1.4])
        self.cmnp = ops.CropMirrorNormalize(device="gpu",
                                            output_dtype=types.FLOAT,
                                            output_layout=types.NCHW,
                                            image_type=color_space_type,
                                            mean=0. if spos_pre else [0.485 * 255, 0.456 * 255, 0.406 * 255],
                                            std=1. if spos_pre else [0.229 * 255, 0.224 * 255, 0.225 * 255])
        self.coin = ops.CoinFlip(probability=0.5) 

# 需要导入模块: from nvidia.dali import ops [as 别名]
# 或者: from nvidia.dali.ops import ImageDecoder [as 别名]
def __init__(self, batch_size, num_threads, shard_id, image_dir, file_list, nvjpeg_padding,
                 prefetch_queue=3, seed=1, num_shards=1, channel_last=True,
                 spatial_size=(224, 224), dtype="half",
                 mean=_pixel_mean, std=_pixel_std, pad_output=True):
        super(TrainPipeline, self).__init__(
            batch_size, num_threads, shard_id, seed=seed, prefetch_queue_depth=prefetch_queue)
        self.input = ops.FileReader(file_root=image_dir, file_list=file_list,
                                    random_shuffle=True, num_shards=num_shards, shard_id=shard_id)
        self.decode = ops.ImageDecoder(device="mixed", output_type=types.RGB,
                                       device_memory_padding=nvjpeg_padding,
                                       host_memory_padding=nvjpeg_padding)

        self.rrc = ops.RandomResizedCrop(device="gpu", size=spatial_size)
        self.cmnp = ops.CropMirrorNormalize(device="gpu",
                                            output_dtype=types.FLOAT16 if dtype == "half" else types.FLOAT,
                                            output_layout=types.NHWC if channel_last else types.NCHW,
                                            crop=spatial_size,
                                            image_type=types.RGB,
                                            mean=mean,
                                            std=std,
                                            pad_output=pad_output)
        self.coin = ops.CoinFlip(probability=0.5) 

# 需要导入模块: from nvidia.dali import ops [as 别名]
# 或者: from nvidia.dali.ops import ImageDecoder [as 别名]
def __init__(self, batch_size, num_threads, device_id, data_dir, crop, dali_cpu=False, local_rank=0, world_size=1):
        super(HybridTrainPipe, self).__init__(batch_size, num_threads, device_id, seed=12 + device_id)
        dali_device = "gpu"
        self.input = ops.FileReader(file_root=data_dir, shard_id=local_rank, num_shards=world_size, random_shuffle=True)
        self.decode = ops.ImageDecoder(device="mixed", output_type=types.RGB)
        self.res = ops.RandomResizedCrop(device="gpu", size=crop, random_area=[0.08, 1.25])
        self.cmnp = ops.CropMirrorNormalize(device="gpu",
                                            output_dtype=types.FLOAT,
                                            output_layout=types.NCHW,
                                            image_type=types.RGB,
                                            mean=[0.485 * 255, 0.456 * 255, 0.406 * 255],
                                            std=[0.229 * 255, 0.224 * 255, 0.225 * 255])
        self.coin = ops.CoinFlip(probability=0.5)
        print('DALI "{0}" variant'.format(dali_device)) 

# 需要导入模块: from nvidia.dali import ops [as 别名]
# 或者: from nvidia.dali.ops import ImageDecoder [as 别名]
def __init__(self, name, batch_size, num_threads, device_id, num_shards, shard_id,
                 root=os.path.expanduser('~/.mxnet/datasets/face'), ):
        super().__init__(batch_size, num_threads, device_id, seed=12)

        idx_files = [os.path.join(root, name, "train.idx")]
        rec_files = [os.path.join(root, name, "train.rec")]
        prop = open(os.path.join(root, name, "property"), "r").read().strip().split(',')
        assert len(prop) == 3
        self.num_classes = int(prop[0])
        self.image_size = [int(prop[1]), int(prop[2])]
        self.size = 0
        for idx_file in idx_files:
            with open(idx_file, "r") as f:
                self.size += len(list(f.readlines()))

        self._input = ops.MXNetReader(path=rec_files, index_path=idx_files, random_shuffle=True,
                                      num_shards=num_shards, shard_id=shard_id, seed=12,
                                      tensor_init_bytes=self.image_size[0] * self.image_size[1] * 8)
        self._decode = ops.ImageDecoder(device="mixed", output_type=types.RGB)

        self._cmnp = ops.CropMirrorNormalize(device="gpu",
                                             output_dtype=types.FLOAT,
                                             output_layout=types.NCHW,
                                             crop=self.image_size,
                                             image_type=types.RGB,
                                             mean=[0., 0., 0.],
                                             std=[255., 255., 255.])
        self._contrast = ops.Contrast(device="gpu")
        self._saturation = ops.Saturation(device="gpu")
        self._brightness = ops.Brightness(device="gpu")

        self._uniform = ops.Uniform(range=(0.7, 1.3))
        self._coin = ops.CoinFlip(probability=0.5) 

# 需要导入模块: from nvidia.dali import ops [as 别名]
# 或者: from nvidia.dali.ops import ImageDecoder [as 别名]
def __init__(self, batch_size, num_threads, device_id, data_dir, crop, size,
                 mean, std, local_rank=0, world_size=1, dali_cpu=False, shuffle=False, fp16=False):

        # As we're recreating the Pipeline at every epoch, the seed must be -1 (random seed)
        super(HybridValPipe, self).__init__(batch_size, num_threads, device_id, seed=-1)

        # Enabling read_ahead slowed down processing ~40%
        # Note: initial_fill is for the shuffle buffer.  As we only want to see every example once, this is set to 1
        self.input = ops.FileReader(file_root=data_dir, shard_id=local_rank, num_shards=world_size, random_shuffle=shuffle, initial_fill=1)
        if dali_cpu:
            decode_device = "cpu"
            self.dali_device = "cpu"
            self.crop = ops.Crop(device="cpu", crop=(crop, crop))

        else:
            decode_device = "mixed"
            self.dali_device = "gpu"

            output_dtype = types.FLOAT
            if fp16:
                output_dtype = types.FLOAT16

            self.cmnp = ops.CropMirrorNormalize(device="gpu",
                                                output_dtype=output_dtype,
                                                output_layout=types.NCHW,
                                                crop=(crop, crop),
                                                image_type=types.RGB,
                                                mean=mean,
                                                std=std)

        self.decode = ops.ImageDecoder(device=decode_device, output_type=types.RGB)

        # Resize to desired size.  To match torchvision dataloader, use triangular interpolation
        self.res = ops.Resize(device=self.dali_device, resize_shorter=size, interp_type=types.INTERP_TRIANGULAR) 

# 需要导入模块: from nvidia.dali import ops [as 别名]
# 或者: from nvidia.dali.ops import ImageDecoder [as 别名]
def __new__(
        cls,
        output_type='BGR',
        host_memory_padding=8388608,
        device_memory_padding=16777216,
    ):
        """Create a ``ImageDecoder`` operator.

        Parameters
        ----------
        output_type : {'BGR', 'RGB'}, optional
            The output color space.
        host_memory_padding : int, optional, default=8388608
            The number of bytes for host buffer.
        device_memory_padding : int, optional, default=16777216
            The number of bytes for device buffer.

        Returns
        -------
        nvidia.dali.ops.ImageDecoder
            The operator.

        """
        if isinstance(output_type, six.string_types):
            output_type = getattr(types, output_type)
        return ops.ImageDecoder(
            output_type=output_type,
            host_memory_padding=host_memory_padding,
            device_memory_padding=device_memory_padding,
            device=context.get_device_type(mixed=True),
        ) 

# 需要导入模块: from nvidia.dali import ops [as 别名]
# 或者: from nvidia.dali.ops import ImageDecoder [as 别名]
def __init__(self, batch_size, num_threads, path, training, annotations, world, device_id, mean, std, resize,
                 max_size, stride, rotate_augment=False,
                 augment_brightness=0.0,
                 augment_contrast=0.0, augment_hue=0.0,
                 augment_saturation=0.0):
        super().__init__(batch_size=batch_size, num_threads=num_threads, device_id=device_id,
                         prefetch_queue_depth=num_threads, seed=42)
        self.path = path
        self.training = training
        self.stride = stride
        self.iter = 0

        self.rotate_augment = rotate_augment
        self.augment_brightness = augment_brightness
        self.augment_contrast = augment_contrast
        self.augment_hue = augment_hue
        self.augment_saturation = augment_saturation

        self.reader = ops.COCOReader(annotations_file=annotations, file_root=path, num_shards=world,
                                     shard_id=torch.cuda.current_device(),
                                     ltrb=True, ratio=True, shuffle_after_epoch=True, save_img_ids=True)

        self.decode_train = ops.ImageDecoderSlice(device="mixed", output_type=types.RGB)
        self.decode_infer = ops.ImageDecoder(device="mixed", output_type=types.RGB)
        self.bbox_crop = ops.RandomBBoxCrop(device='cpu', bbox_layout="xyXY", scaling=[0.3, 1.0],
                                            thresholds=[0.1, 0.3, 0.5, 0.7, 0.9])

        self.bbox_flip = ops.BbFlip(device='cpu', ltrb=True)
        self.img_flip = ops.Flip(device='gpu')
        self.coin_flip = ops.CoinFlip(probability=0.5)
        self.bc = ops.BrightnessContrast(device='gpu')
        self.hsv = ops.Hsv(device='gpu')

        # Random number generation for augmentation
        self.brightness_dist = ops.NormalDistribution(mean=1.0, stddev=augment_brightness)
        self.contrast_dist = ops.NormalDistribution(mean=1.0, stddev=augment_contrast)
        self.hue_dist = ops.NormalDistribution(mean=0.0, stddev=augment_hue)
        self.saturation_dist = ops.NormalDistribution(mean=1.0, stddev=augment_saturation)

        if rotate_augment:
            raise RuntimeWarning("--augment-rotate current has no effect when using the DALI data loader.")

        if isinstance(resize, list): resize = max(resize)
        self.rand_resize = ops.Uniform(range=[resize, float(max_size)])

        self.resize_train = ops.Resize(device='gpu', interp_type=types.DALIInterpType.INTERP_CUBIC, save_attrs=True)
        self.resize_infer = ops.Resize(device='gpu', interp_type=types.DALIInterpType.INTERP_CUBIC,
                                       resize_longer=max_size, save_attrs=True)

        padded_size = max_size + ((self.stride - max_size % self.stride) % self.stride)

        self.pad = ops.Paste(device='gpu', fill_value=0, ratio=1.1, min_canvas_size=padded_size, paste_x=0, paste_y=0)
        self.normalize = ops.CropMirrorNormalize(device='gpu', mean=mean, std=std, crop=(padded_size, padded_size),
                                                 crop_pos_x=0, crop_pos_y=0)