Darkflow: Training our own data

[normansiboro]

I got this error when I was training my data set. I already followed every step

Enter training ...

cfg/tiny-yolo-voc-1c.cfg parsing train/Annotations
Parsing for ['macncheese']
Traceback (most recent call last):
File "flow", line 6, in
cliHandler(sys.argv)
File "D:MDPSystemSupportOJT IIPython ProjectTensorflowdarkflowdarkflowcli.py", line 29, in cliHandler
print('Enter training ...'); tfnet.train()
File "D:MDPSystemSupportOJT IIPython ProjectTensorflowdarkflowdarkflownetflow.py", line 39, in train
for i, (x_batch, datum) in enumerate(batches):
File "D:MDPSystemSupportOJT IIPython ProjectTensorflowdarkflowdarkflownetyolodata.py", line 97, in shuffle
data = self.parse()
File "D:MDPSystemSupportOJT IIPython ProjectTensorflowdarkflowdarkflownetyolodata.py", line 18, in parse
dumps = pascal_voc_clean_xml(ann, meta['labels'], exclusive)
File "D:MDPSystemSupportOJT IIPython ProjectTensorflowdarkflowdarkflowutilspascal_voc_clean_xml.py", line 22, in pascal_voc_clean_xml
annotations = glob.glob(str(annotations)+'*.xml')
File "C:Python35libglob.py", line 20, in glob
return list(iglob(pathname, recursive=recursive))
File "C:Python35libglob.py", line 54, in _iglob
yield from glob1(dirname, basename)
File "C:Python35libglob.py", line 90, in glob1
return fnmatch.filter(names, pattern)
File "C:Python35libfnmatch.py", line 52, in filter
match = _compile_pattern(pat)
File "C:Python35libfnmatch.py", line 46, in _compile_pattern
return re.compile(res).match
File "C:Python35libre.py", line 224, in compile
return _compile(pattern, flags)
File "C:Python35libre.py", line 293, in _compile
p = sre_compile.compile(pattern, flags)
File "C:Python35libsre_compile.py", line 536, in compile
p = sre_parse.parse(p, flags)
File "C:Python35libsre_parse.py", line 829, in parse
p = _parse_sub(source, pattern, 0)
File "C:Python35libsre_parse.py", line 437, in _parse_sub
itemsappend(_parse(source, state))
File "C:Python35libsre_parse.py", line 575, in _parse
raise source.error(msg, len(this) + 1 + len(that))
sre_constants.error: bad character range i-a at position 179

I use https://github.com/tzutalin/labelImg to label my images
I want to train my data only for one class

[t-fernandez]

Did you get this issue resolved? Im having the same problem?

[normansiboro]

I just changed the line annotations = glob.glob(str(annotations)+'*.xml') to annotations = glob.glob('*.xml') in the darkflowutilspascal_voc_clean_xml.py file as mention here