my dataset

If I want to train my data,the thing that I need do is run the main.py --dataset mydate ?But when I run the code ,it has something errors.
Traceback (most recent call last):
File "D:\Anaconda\envs\tensorflow\lib\site-packages\absl\flags\_flag.py", line
181, in _parse
return self.parser.parse(argument)
File "D:\Anaconda\envs\tensorflow\lib\site-packages\absl\flags\_argument_parse
r.py", line 152, in parse
val = self.convert(argument)
File "D:\Anaconda\envs\tensorflow\lib\site-packages\absl\flags\_argument_parse
r.py", line 268, in convert
type(argument)))
TypeError: Expect argument to be a string or int, found

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "main.py", line 20, in
flags.DEFINE_integer("train_size", np.inf, "The size of train images [np.inf
]")
File "D:\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\platform
\flags.py", line 58, in wrapper
return original_function(*args, **kwargs)
File "D:\Anaconda\envs\tensorflow\lib\site-packages\absl\flags\_defines.py", l
ine 315, in DEFINE_integer
DEFINE(parser, name, default, help, flag_values, serializer, **args)
File "D:\Anaconda\envs\tensorflow\lib\site-packages\absl\flags\_defines.py", l
ine 81, in DEFINE
DEFINE_flag(_flag.Flag(parser, serializer, name, default, help, **args),
File "D:\Anaconda\envs\tensorflow\lib\site-packages\absl\flags\_flag.py", line
110, in __init__
self._set_default(default)
File "D:\Anaconda\envs\tensorflow\lib\site-packages\absl\flags\_flag.py", line
211, in _set_default
self.default = self._parse(value)
File "D:\Anaconda\envs\tensorflow\lib\site-packages\absl\flags\_flag.py", line
184, in _parse
'flag --%s=%s: %s' % (self.name, argument, e))
absl.flags._exceptions.IllegalFlagValueError: flag --train_size=inf: Expect argu
ment to be a string or int, found

Start in main.py at the flags.DEFINE_integer("train_size", np.inf, ...) declaration shown in the traceback, then review how train_size is used when running with --dataset. Reproduce the command with the reported environment and confirm that dataset training starts without the flag-parsing error.

Written by the indexing model from the issue text.