Module vipy.data.coil100

Expand source code Browse git 
import os
from vipy.util import remkdir, tocache, filebase
import vipy.downloader
from vipy.dataset import Dataset
from vipy.image import ImageCategory


URL = 'http://www.cs.columbia.edu/CAVE/databases/SLAM_coil-20_coil-100/coil-100/coil-100.zip'
SHA1 = '402d86b63cf3ace831f2af03bc9889e5e5c3dd1a'


class COIL100(Dataset):
    def __init__(self, datadir=None, redownload=False):

        datadir = tocache('coil100') if datadir is None else datadir
        
        # Download
        self._datadir = remkdir(datadir)        
        if redownload or not os.path.exists(os.path.join(self._datadir, '.complete')):
            vipy.downloader.download_and_unpack(URL, self._datadir, sha1=SHA1)            
            
        # Create dataset
        imlist = []
        imgdir = os.path.join(self._datadir, 'coil-100')
        for f in os.listdir(imgdir):
            if '__' in f:
                imlist.append(f)

        loader = lambda f, imgdir=imgdir: ImageCategory(filename=os.path.join(imgdir, f), category=f.split('__')[0], attributes={'orientation':filebase(f).split('__')[1]})
        super().__init__(imlist, id='coil100', loader=loader)
            

        open(os.path.join(self._datadir, '.complete'), 'a').close()

Classes

class COIL100 (datadir=None, redownload=False)

vipy.dataset.Dataset() class

Common class to manipulate large sets of objects in parallel

Args

  • dataset [list, tuple, set, obj]: a python built-in type that supports indexing or a generic object that supports indexing and has a length
  • id [str]: an optional id of this dataset, which provides a descriptive name of the dataset
  • loader [callable]: a callable loader that will construct the object from a raw data element in dataset. This is useful for custom deerialization or on demand transformations Datasets can be indexed, shuffled, iterated, minibatched, sorted, sampled, partitioned. Datasets constructed of vipy objects are lazy loaded, delaying loading pixels until they are needed
(trainset, valset, testset) = vipy.dataset.registry('mnist')

(trainset, valset) = trainset.partition(0.9, 0.1)
categories = trainset.set(lambda im: im.category())
smaller = testset.take(1024)
preprocessed = smaller.map(lambda im: im.resize(32, 32).gain(1/256))

for b in preprocessed.minibatch(128):
    print(b)

# visualize the dataset 
(trainset, valset, testset) = vipy.dataset.registry('pascal_voc_2007')
for im in trainset:
    im.mindim(1024).show().print(sleep=1).close()

Datasets can be constructed from directories of json files or image files (Dataset.from_directory()) Datasets can be constructed from a single json file containing a list of objects (Dataset.from_json())

Note: that if a lambda function is provided as loader then this dataset is not serializable. Use self.load() then serialize

Expand source code Browse git 
class COIL100(Dataset):
    def __init__(self, datadir=None, redownload=False):

        datadir = tocache('coil100') if datadir is None else datadir
        
        # Download
        self._datadir = remkdir(datadir)        
        if redownload or not os.path.exists(os.path.join(self._datadir, '.complete')):
            vipy.downloader.download_and_unpack(URL, self._datadir, sha1=SHA1)            
            
        # Create dataset
        imlist = []
        imgdir = os.path.join(self._datadir, 'coil-100')
        for f in os.listdir(imgdir):
            if '__' in f:
                imlist.append(f)

        loader = lambda f, imgdir=imgdir: ImageCategory(filename=os.path.join(imgdir, f), category=f.split('__')[0], attributes={'orientation':filebase(f).split('__')[1]})
        super().__init__(imlist, id='coil100', loader=loader)
            

        open(os.path.join(self._datadir, '.complete'), 'a').close()

Ancestors

Inherited members