Datasets¶
TransformDataset¶
TransformDataset¶
-
class
chainercv.datasets.
TransformDataset
(dataset, transform)¶ Dataset that indexes data of a base dataset and transforms it.
This dataset wraps a base dataset by modifying the behavior of the base dataset’s
__getitem__()
. Arrays returned by__getitem__()
of the base dataset with an integer index are transformed by the given functiontransform
.The function
transform
takes, as an argument,in_data
, which is output of the base dataset’s__getitem__()
, and returns transformed arrays as output. Please see the following example.>>> from chainer.datasets import get_mnist >>> from chainercv.datasets import TransformDataset >>> dataset, _ = get_mnist() >>> def transform(in_data): >>> img, label = in_data >>> img -= 0.5 # scale to [-0.5, -0.5] >>> return img, label >>> dataset = TransformDataset(dataset, transform)
Note
The index used to access data is either an integer or a slice. If it is a slice, the base dataset is assumed to return a list of outputs each corresponding to the output of the integer indexing.
Note
This class is deprecated. Please use
chainer.datasets.TransformDataset
instead.Parameters: - dataset – Underlying dataset. The index of this dataset corresponds to the index of the base dataset.
- transform (callable) – A function that is called to transform values
returned by the underlying dataset’s
__getitem__()
.
CamVid¶
CamVidDataset¶
-
class
chainercv.datasets.
CamVidDataset
(data_dir='auto', split='train')¶ Dataset class for a semantic segmantion task on CamVid u.
Parameters: - data_dir (string) – Path to the root of the training data. If this is
auto
, this class will automatically download data for you under$CHAINER_DATASET_ROOT/pfnet/chainercv/camvid
. - split ({'train', 'val', 'test'}) – Select from dataset splits used in CamVid Dataset.
- data_dir (string) – Path to the root of the training data. If this is
CUB¶
CUBLabelDataset¶
-
class
chainercv.datasets.
CUBLabelDataset
(data_dir='auto', crop_bbox=True)¶ Caltech-UCSD Birds-200-2011 dataset with annotated class labels.
When queried by an index, this dataset returns a corresponding
img, label
, a tuple of an image and class id. The image is in RGB and CHW format. The class id are between 0 and 199.There are 200 labels of birds in total.
Parameters:
CUBKeypointDataset¶
-
class
chainercv.datasets.
CUBKeypointDataset
(data_dir='auto', crop_bbox=True, mask_dir='auto', return_mask=False)¶ Caltech-UCSD Birds-200-2011 dataset with annotated keypoints.
An index corresponds to each image.
When queried by an index, this dataset returns the corresponding
img, keypoint, kp_mask
, a tuple of an image, keypoints and a keypoint mask that indicates visible keypoints in the image. The data type of the three elements arefloat32, float32, bool
. Ifreturn_mask = True
,mask
will be returned as well, making the returned tuple to be of length four.mask
is auint8
image which indicates the region of the image where a bird locates.keypoints are packed into a two dimensional array of shape \((K, 2)\), where \(K\) is the number of keypoints. Note that \(K=15\) in CUB dataset. Also note that not all fifteen keypoints are visible in an image. When a keypoint is not visible, the values stored for that keypoint are undefined. The second axis corresponds to the \(y\) and \(x\) coordinates of the keypoints in the image.
A keypoint mask array indicates whether a keypoint is visible in the image or not. This is a boolean array of shape \((K,)\).
A mask image of the bird shows how likely the bird is located at a given pixel. If the value is close to 255, more likely that a bird locates at that pixel. The shape of this array is \((1, H, W)\), where \(H\) and \(W\) are height and width of the image respectively.
Parameters: - data_dir (string) – Path to the root of the training data. If this is
auto
, this class will automatically download data for you under$CHAINER_DATASET_ROOT/pfnet/chainercv/cub
. - crop_bbox (bool) – If true, this class returns an image cropped by the bounding box of the bird inside it.
- mask_dir (string) – Path to the root of the mask data. If this is
auto
, this class will automatically download data for you under$CHAINER_DATASET_ROOT/pfnet/chainercv/cub
. - return_mask (bool) – Decide whether to include mask image of the bird in a tuple served for a query.
- data_dir (string) – Path to the root of the training data. If this is
OnlineProducts¶
OnlineProductsDataset¶
-
class
chainercv.datasets.
OnlineProductsDataset
(data_dir='auto', split='train')¶ Dataset class for Stanford Online Products Dataset.
When queried by an index, this dataset returns a corresponding
img, class_id, super_class_id
, a tuple of an image, a class id and a coarse level class id. Images are in RGB and CHW format. Class ids start from 0.The
split
selects train and test split of the dataset as done in [1]. The train split contains the first 11318 classes and the test split contains the remaining 11316 classes.[1] Hyun Oh Song, Yu Xiang, Stefanie Jegelka, Silvio Savarese. Deep Metric Learning via Lifted Structured Feature Embedding. arXiv 2015. Parameters: - data_dir (string) – Path to the root of the training data. If this is
auto
, this class will automatically download data for you under$CHAINER_DATASET_ROOT/pfnet/chainercv/online_products
. - split ({'train', 'test'}) – Select a split of the dataset.
- data_dir (string) – Path to the root of the training data. If this is
PASCAL VOC¶
VOCDetectionDataset¶
-
class
chainercv.datasets.
VOCDetectionDataset
(data_dir='auto', split='train', year='2012', use_difficult=False, return_difficult=False)¶ Dataset class for the detection task of PASCAL VOC.
The index corresponds to each image.
When queried by an index, if
return_difficult == False
, this dataset returns a correspondingimg, bbox, label
, a tuple of an image, bounding boxes and labels. This is the default behaviour. Ifreturn_difficult == True
, this dataset returns correspondingimg, bbox, label, difficult
.difficult
is a boolean array that indicates whether bounding boxes are labeled as difficult or not.The bounding boxes are packed into a two dimensional tensor of shape \((R, 4)\), where \(R\) is the number of bounding boxes in the image. The second axis represents attributes of the bounding box. They are
(y_min, x_min, y_max, x_max)
, where the four attributes are coordinates of the top left and the bottom right vertices.The labels are packed into a one dimensional tensor of shape \((R,)\). \(R\) is the number of bounding boxes in the image. The class name of the label \(l\) is \(l\) th element of
chainercv.datasets.voc_detection_label_names
.The array
difficult
is a one dimensional boolean array of shape \((R,)\). \(R\) is the number of bounding boxes in the image. Ifuse_difficult
isFalse
, this array is a boolean array with allFalse
.The type of the image, the bounding boxes and the labels are as follows.
img.dtype == numpy.float32
bbox.dtype == numpy.float32
label.dtype == numpy.int32
difficult.dtype == numpy.bool
Parameters: - data_dir (string) – Path to the root of the training data. If this is
auto
, this class will automatically download data for you under$CHAINER_DATASET_ROOT/pfnet/chainercv/voc
. - split ({'train', 'val', 'trainval', 'test'}) – Select a split of the
dataset.
test
split is only available for 2007 dataset. - year ({'2007', '2012'}) – Use a dataset prepared for a challenge
held in
year
. - use_difficult (bool) – If true, use images that are labeled as difficult in the original annotation.
- return_difficult (bool) – If true, this dataset returns a boolean array
that indicates whether bounding boxes are labeled as difficult
or not. The default value is
False
.
VOCSemanticSegmentationDataset¶
-
class
chainercv.datasets.
VOCSemanticSegmentationDataset
(data_dir='auto', split='train')¶ Dataset class for the semantic segmantion task of PASCAL VOC2012.
The class name of the label \(l\) is \(l\) th element of
chainercv.datasets.voc_semantic_segmentation_label_names
.Parameters: - data_dir (string) – Path to the root of the training data. If this is
auto
, this class will automatically download data for you under$CHAINER_DATASET_ROOT/pfnet/chainercv/voc
. - split ({'train', 'val', 'trainval'}) – Select a split of the dataset.
- data_dir (string) – Path to the root of the training data. If this is