![]() |
OpenCV
3.4.20
Open Source Computer Vision
|
Classes | |
class | cv::datasets::OR_imagenet |
struct | cv::datasets::OR_imagenetObj |
class | cv::datasets::OR_mnist |
struct | cv::datasets::OR_mnistObj |
class | cv::datasets::OR_pascal |
struct | cv::datasets::OR_pascalObj |
class | cv::datasets::OR_sun |
struct | cv::datasets::OR_sunObj |
struct | cv::datasets::PascalObj |
struct | cv::datasets::PascalPart |
Implements loading dataset: "ImageNet": http://www.image-net.org/
Usage:
ILSVRC2010_images_train.tar\ILSVRC2010_images_test.tar\ILSVRC2010_images_val.tar
& devkit: ILSVRC2010_devkit-1.0.tar.gz
(Implemented loading of 2010 dataset as only this dataset has ground truth for test data, but structure for ILSVRC2014 is similar)some_folder/train/
, some_folder/test/
, some_folder/val
& some_folder/ILSVRC2010_validation_ground_truth.txt
, some_folder/ILSVRC2010_test_ground_truth.txt
.some_folder/labels.txt
, for example, using python script below (each file's row format: synset,labelID,description
. For example: "n07751451,18,plum").Python script to parse meta.mat
:
Implements loading dataset:
"MNIST": http://yann.lecun.com/exdb/mnist/
Usage:
t10k-images-idx3-ubyte.gz
, t10k-labels-idx1-ubyte.gz
, train-images-idx3-ubyte.gz
, train-labels-idx1-ubyte.gz
.Implements loading dataset:
"SUN Database, Scene Recognition Benchmark. SUN397": http://vision.cs.princeton.edu/projects/2010/SUN/
Usage:
SUN397.tar
& file with splits: Partitions.zip
SUN397.tar
into folder: SUN397/
& Partitions.zip
into folder: SUN397/Partitions/