def convert(self, sequence):
"""convert ICVL sequence"""
config = sequence.config
name = '{}/{}_{}.h5'.format(self.cacheDir, self.datasetName,
sequence.name)
if os.path.isfile(name):
print '{} exist, please check if h5 is right!'.format(name)
return
Dataset = ICVLDataset([sequence])
dpt, gt3D = Dataset.imgStackDepthOnly(sequence.name)
depth = []
gtorig = []
gtcrop = []
T = []
gt3Dorig = []
gt3Dcrop = []
com = []
fileName = []
for i in xrange(len(sequence.data)):
data = sequence.data[i]
depth.append(data.dpt)
gtorig.append(data.gtorig)
gtcrop.append(data.gtcrop)
T.append(data.T)
gt3Dorig.append(data.gt3Dorig)
gt3Dcrop.append(data.gt3Dcrop)
com.append(data.com)
fileName.append(
int(data.fileName[(data.fileName.find('image_') +
6):(data.fileName.find('.png'))]))
dataset = h5py.File(name, 'w')
dataset['com'] = np.asarray(com)
dataset['inds'] = np.asarray(fileName)
dataset['config'] = config['cube']
dataset['depth'] = np.asarray(dpt)
dataset['joint'] = np.asarray(gt3D)
dataset['gt3Dorig'] = np.asarray(gt3Dorig)
dataset.close()
def convert(self, sequence, size_before=None):
"""convert sequence data"""
config = sequence.config
if self.name == 'NYU':
Dataset = NYUDataset([sequence])
elif self.name == 'ICVL':
Dataset = ICVLDataset([sequence])
dpt, gt3D = Dataset.imgStackDepthOnly(sequence.name)
dataset = {}
com = []
fileName = []
dpt3D = []
size = len(sequence.data)
print('size of {} {} dataset is {}'.format(self.name, sequence.name,
size))
for i in xrange(len(sequence.data)):
data = sequence.data[i]
com.append(data.com)
dpt3D.append(data.dpt3D)
if self.name == 'NYU':
fileName.append(int(data.fileName[-11:-4]))
elif self.name == 'ICVL' and size_before is not None:
fileName.append(int(data.fileName[(data.fileName.find('image_') + 6): \
(data.fileName.find('.png'))]) + size_before)
else:
fileName.append(int(data.fileName[(data.fileName.find('image_') + 6): \
(data.fileName.find('.png'))]))
dataset['depth'] = np.asarray(dpt)
dataset['dpt3D'] = np.asarray(dpt3D)
dataset['com'] = np.asarray(com)
dataset['inds'] = np.asarray(fileName)
dataset['config'] = np.asarray(config['cube']).reshape(
1, self.dim).repeat(size, axis=0)
dataset['joint'] = np.asarray(gt3D)
return dataset
print("create data")
aug_modes = ['com', 'rot', 'none'] # 'sc',
di = ICVLImporter('../data/ICVL/')
Seq1_1 = di.loadSequence('train', ['0'], shuffle=True, rng=rng, docom=False)
Seq1_1 = Seq1_1._replace(name='train_gt')
Seq1_2 = di.loadSequence('train', ['0'], shuffle=True, rng=rng, docom=True)
Seq1_2 = Seq1_2._replace(name='train_com')
trainSeqs = [Seq1_1, Seq1_2]
Seq2 = di.loadSequence('test_seq_1', docom=True)
testSeqs = [Seq2]
# create training data
trainDataSet = ICVLDataset(trainSeqs)
nSamp = numpy.sum([len(s.data) for s in trainSeqs])
d1, g1 = trainDataSet.imgStackDepthOnly(trainSeqs[0].name)
train_data = numpy.ones((nSamp, d1.shape[1], d1.shape[2], d1.shape[3]), dtype='float32')
train_gt3D = numpy.ones((nSamp, g1.shape[1], g1.shape[2]), dtype='float32')
train_data_com = numpy.ones((nSamp, 3), dtype='float32')
train_data_M = numpy.ones((nSamp, 3, 3), dtype='float32')
train_data_cube = numpy.ones((nSamp, 3), dtype='float32')
del d1, g1
gc.collect()
gc.collect()
gc.collect()
oldIdx = 0
for seq in trainSeqs:
d, g = trainDataSet.imgStackDepthOnly(seq.name)
train_data[oldIdx:oldIdx+d.shape[0]] = d
floatX = theano.config.floatX # @UndefinedVariable
rng = numpy.random.RandomState(23455)
print("create data")
di = ICVLImporter('../data/ICVL/')
Seq1 = di.loadSequence('train', ['0'], shuffle=True, rng=rng)
trainSeqs = [Seq1]
Seq2 = di.loadSequence('test_seq_1')
testSeqs = [Seq2]
# create training data
trainDataSet = ICVLDataset(trainSeqs)
train_data, train_gt3D = trainDataSet.imgStackDepthOnly('train')
mb = (train_data.nbytes) / (1024 * 1024)
print("data size: {}Mb".format(mb))
valDataSet = ICVLDataset(testSeqs)
val_data, val_gt3D = valDataSet.imgStackDepthOnly('test_seq_1')
testDataSet = ICVLDataset(testSeqs)
test_data, test_gt3D = testDataSet.imgStackDepthOnly('test_seq_1')
print train_gt3D.max(), test_gt3D.max(), train_gt3D.min(), test_gt3D.min()
print train_data.max(), test_data.max(), train_data.min(), test_data.min()
imgSizeW = train_data.shape[3]