# Copyright (c) OpenMMLab and Alibaba. All rights reserved.
from collections.abc import Sequence
import mmcv
import numpy as np
import torch
from mmcv.parallel import DataContainer as DC
from easycv.datasets.registry import PIPELINES
from easycv.framework.errors import TypeError
[docs]def to_tensor(data):
"""Convert objects of various python types to :obj:`torch.Tensor`.
Supported types are: :class:`numpy.ndarray`, :class:`torch.Tensor`,
:class:`Sequence`, :class:`int` and :class:`float`.
Args:
data (torch.Tensor | numpy.ndarray | Sequence | int | float): Data to
be converted.
"""
if isinstance(data, torch.Tensor):
return data
elif isinstance(data, np.ndarray):
return torch.from_numpy(data)
elif isinstance(data, Sequence) and not mmcv.is_str(data):
return torch.tensor(data)
elif isinstance(data, int):
return torch.LongTensor([data])
elif isinstance(data, float):
return torch.FloatTensor([data])
else:
raise TypeError(f'type {type(data)} cannot be converted to tensor.')
[docs]@PIPELINES.register_module()
class ImageToTensor(object):
"""Convert image to :obj:`torch.Tensor` by given keys.
The dimension order of input image is (H, W, C). The pipeline will convert
it to (C, H, W). If only 2 dimension (H, W) is given, the output would be
(1, H, W).
Args:
keys (Sequence[str]): Key of images to be converted to Tensor.
"""
[docs] def __init__(self, keys):
self.keys = keys
def __call__(self, results):
"""Call function to convert image in results to :obj:`torch.Tensor` and
transpose the channel order.
Args:
results (dict): Result dict contains the image data to convert.
Returns:
dict: The result dict contains the image converted
to :obj:`torch.Tensor` and transposed to (C, H, W) order.
"""
for key in self.keys:
img = results[key]
if len(img.shape) < 3:
img = np.expand_dims(img, -1)
results[key] = (to_tensor(img.transpose(2, 0, 1))).contiguous()
return results
def __repr__(self):
return self.__class__.__name__ + f'(keys={self.keys})'
[docs]@PIPELINES.register_module()
class Collect(object):
"""Collect data from the loader relevant to the specific task.
This is usually the last stage of the data loader pipeline. Typically keys
is set to some subset of "img", "proposals", "gt_bboxes",
"gt_bboxes_ignore", "gt_labels", and/or "gt_masks".
The "img_meta" item is always populated. The contents of the "img_meta"
dictionary depends on "meta_keys". By default this includes:
- "img_shape": shape of the image input to the network as a tuple \
(h, w). Note that images may be zero padded on the \
bottom/right if the batch tensor is larger than this shape.
- "scale_factor": a float indicating the preprocessing scale
- "flip": a boolean indicating if image flip transform was used
- "filename": path to the image file
- "ori_img_shape": original shape of the image as a tuple (h, w, c)
- "img_norm_cfg": a dict of normalization information:
- mean - per channel mean subtraction
- std - per channel std divisor
- to_rgb - bool indicating if bgr was converted to rgb
Args:
keys (Sequence[str]): Keys of results to be collected in ``data``.
meta_keys (Sequence[str], optional): Meta keys to be converted to
``mmcv.DataContainer`` and collected in ``data[img_metas]``.
Default: ``('filename', 'ori_filename', 'ori_img_shape', 'img_shape',
'scale_factor', 'flip', 'flip_direction', 'img_norm_cfg')``
"""
[docs] def __init__(self,
keys,
meta_keys=('filename', 'ori_filename', 'ori_img_shape',
'img_shape', 'scale_factor', 'pad', 'flip',
'flip_direction', 'img_norm_cfg')):
self.keys = keys
self.meta_keys = meta_keys
def __call__(self, results):
"""Call function to collect keys in results. The keys in ``meta_keys``
will be converted to :obj:mmcv.DataContainer.
Args:
results (dict): Result dict contains the data to collect.
Returns:
dict: The result dict contains the following keys
- keys in``self.keys``
- ``img_metas``
"""
data = {}
img_meta = {}
for key in self.meta_keys:
if key in results:
img_meta[key] = results[key]
data['img_metas'] = DC(img_meta, cpu_only=True)
for key in self.keys:
data[key] = results[key]
return data
def __repr__(self):
return self.__class__.__name__ + \
f'(keys={self.keys}, meta_keys={self.meta_keys})'