Object Recognition#
Detailed Description#
ImageNet#
Implements loading dataset: “ImageNet”: http://www.image-net.org/
Usage:
From link above download dataset files:
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)Unpack them to:
some_folder/train/,some_folder/test/,some_folder/val&some_folder/ILSVRC2010_validation_ground_truth.txt,some_folder/ILSVRC2010_test_ground_truth.txt.Create file with labels:
some_folder/labels.txt, for example, using python script below (each file’s row format:synset,labelID,description. For example: “n07751451,18,plum”).Unpack all tar files in train.
To load data run:
Python script to parse meta.mat:
import scipy.io
meta_mat = scipy.io.loadmat("devkit-1.0/data/meta.mat")
labels_dic = dict((m[0][1][0], m[0][0][0][0]-1) for m in meta_mat['synsets']
label_names_dic = dict((m[0][1][0], m[0][2][0]) for m in meta_mat['synsets']
for label in labels_dic.keys():
print "{0},{1},{2}".format(label, labels_dic[label], label_names_dic[label])
MNIST#
Implements loading dataset:
“MNIST”: http://yann.lecun.com/exdb/mnist/
Usage:
From link above download dataset files:
t10k-images-idx3-ubyte.gz,t10k-labels-idx1-ubyte.gz,train-images-idx3-ubyte.gz,train-labels-idx1-ubyte.gz.Unpack them.
To load data run:
SUN Database#
Implements loading dataset:
“SUN Database, Scene Recognition Benchmark. SUN397”: http://vision.cs.princeton.edu/projects/2010/SUN/
Usage:
From link above download dataset file:
SUN397.tar& file with splits:Partitions.zipUnpack
SUN397.tarinto folder:SUN397/&Partitions.zipinto folder:SUN397/Partitions/To load data run:
Classes#
Name |
Description |
|---|---|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|