# print inputMeans
# print inputStds
# print inputs
labels = list(charSet)
print len(labels), labels
# i = 0
# for s in targetStrings:
# i += 1
# print i
# print s
# for point in inputs:
# print point
# for s in wordTargetStrings:
# print s
ncFile = netcdf_helpers.NetCDFFile(ncFileName, 'w')
netcdf_helpers.createNcDim(ncFile, 'numSeqs', len(seqLengths))
netcdf_helpers.createNcDim(ncFile, 'numTimesteps', len(inputs))
netcdf_helpers.createNcDim(ncFile, 'inputPattSize', len(inputs[0]))
netcdf_helpers.createNcDim(ncFile, 'numDims', 1)
netcdf_helpers.createNcDim(ncFile, 'numLabels', len(labels))
netcdf_helpers.createNcStrings(ncFile, 'seqTags', seqTags,
('numSeqs', 'maxSeqTagLength'), 'sequence tags')
netcdf_helpers.createNcStrings(ncFile, 'labels', labels,
('numLabels', 'maxLabelLength'), 'labels')
netcdf_helpers.createNcStrings(ncFile, 'targetStrings', targetStrings,
('numSeqs', 'maxTargetStringLength'),
'target strings')
netcdf_helpers.createNcStrings(ncFile, 'wordTargetStrings', wordTargetStrings,
#print 'targetString:',targetString
if targetString == '':
print 'removing the image'
continue
targetStrings.append(targetString)
seqTags.append(base)
readFeatures(fname)
counter += 1
#create a new .nc file
print '# Creating NetCDFFile:', args.ncFileName
ncfile = netcdf_helpers.NetCDFFile(args.ncFileName, 'w')
#create the dimensions
netcdf_helpers.createNcDim(ncfile, 'numSeqs', len(seqLengths))
netcdf_helpers.createNcDim(ncfile, 'numTimesteps', len(inputs))
netcdf_helpers.createNcDim(ncfile, 'inputPattSize', len(inputs[0]))
netcdf_helpers.createNcDim(ncfile, 'numDims', 1)
netcdf_helpers.createNcDim(ncfile, 'numLabels', len(labels))
#create the variables
netcdf_helpers.createNcStrings(ncfile, 'labels', labels,
('numLabels', 'maxLabelLength'), 'labels')
netcdf_helpers.createNcStrings(ncfile, 'targetStrings', targetStrings,
('numSeqs', 'maxTargStringLength'),
'target strings')
netcdf_helpers.createNcStrings(ncfile, 'seqTags', seqTags,
parser.add_option("-c", "--booleanColomn", action="store", type="int", dest="booleanColomn", default=-1, help="dont normalize nth colomn of input array")
def Std(array,axis):
if shape(array)[axis]>1:
return (std(array,axis))
return array
#parse command line options
(options, args) = parser.parse_args()
print options
if (len(args) != 2):
parser.error("incorrect number of arguments")
inputFilename = args[0]
outputFilename = args[1]
print 'inputFilename', inputFilename
infile = netcdf_helpers.NetCDFFile(inputFilename, 'r')
print "loading in input array"
inputVar = infile.variables[options.inputArrayName]
outputArray = zeros(inputVar.shape, 'f')
if options.bigFile:
offset = 0
step = options.maxArraySize
while offset < inputVar.shape[0]:
max = min (offset+step, inputVar.shape[0])
outputArray[offset:max] = inputVar[offset:max]
offset += step
else:
outputArray = inputVar.getValue()
if options.stdMeanFilename <> "":
print len(labels),'labels'
print labels
totalLen = sum(seqLengths)
print 'totalLen', totalLen
inputs = zeros((totalLen,1), 'f')
offset = 0
for filename in seqTags:
print "reading image file", filename
image = Image.open(filename).transpose(Image.FLIP_TOP_BOTTOM).transpose(Image.ROTATE_270)
for i in image.getdata():
inputs[offset][0] = (float(i) - inputMean)/inputStd
offset += 1
#create a new .nc file
file = netcdf_helpers.NetCDFFile(outputFilename, 'w')
#create the dimensions
netcdf_helpers.createNcDim(file,'numSeqs',len(seqLengths))
netcdf_helpers.createNcDim(file,'numTimesteps',len(inputs))
netcdf_helpers.createNcDim(file,'inputPattSize',len(inputs[0]))
netcdf_helpers.createNcDim(file,'numDims',2)
netcdf_helpers.createNcDim(file,'numLabels',len(labels))
#create the variables
netcdf_helpers.createNcStrings(file,'seqTags',seqTags,('numSeqs','maxSeqTagLength'),'sequence tags')
netcdf_helpers.createNcStrings(file,'labels',labels,('numLabels','maxLabelLength'),'labels')
netcdf_helpers.createNcStrings(file,'wordTargetStrings',wordTargetStrings,('numSeqs','maxWordTargStringLength'),'target strings')
netcdf_helpers.createNcStrings(file,'targetStrings',targetStrings,('numSeqs','maxTargStringLength'),'target strings')
netcdf_helpers.createNcVar(file,'seqLengths',seqLengths,'i',('numSeqs',),'sequence lengths')
netcdf_helpers.createNcVar(file,'seqDims',seqDims,'i',('numSeqs','numDims'),'sequence dimensions')
