Open ouisyasser opened 4 years ago
Hi ouisyasser! Can you show us the code where you load the file? I think this is happening because your directory structure isn't what is required for training on the CIFAR dataset.
Yes sure! Thank you for responding me.
https://colab.research.google.com/drive/1sFwKBam6LrYmNJoHIDw3HSFQ4fVR_QDW
This is the file and how I execute it. Im working on a project and I need your classifier.
Le mer. 20 mai 2020 à 4:22 AM, Vidur Satija notifications@github.com a écrit :
Hi ouisyasser! Can you show us the code where you load the file? I think this is happening because your directory structure isn't what is required for training on the CIFAR dataset.
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/tensorflow/models/issues/8518#issuecomment-631211802, or unsubscribe https://github.com/notifications/unsubscribe-auth/AOAXXX7L6WTYPLMYQW32DSTRSNEIPANCNFSM4NDAFEFQ .
Traceback (most recent call last): File "train_cifar.py", line 452, in
tf.app.run()
File "/tensorflow-1.15.2/python2.7/tensorflow_core/python/platform/app.py", line 40, in run
_run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
File "/usr/local/lib/python2.7/dist-packages/absl/app.py", line 300, in run
_run_main(main, args)
File "/usr/local/lib/python2.7/dist-packages/absl/app.py", line 251, in _run_main
sys.exit(main(argv))
File "train_cifar.py", line 447, in main
cifar_trainer = CifarModelTrainer(hparams)
File "train_cifar.py", line 225, in init
self.data_loader = data_utils.DataSet(hparams)
File "/content/models/research/autoaugment/data_utils.py", line 85, in init
d = unpickle(os.path.join(hparams.data_path, f))
File "/content/models/research/autoaugment/data_utils.py", line 182, in unpickle
d = cPickle.load(fo)
File "/tensorflow-1.15.2/python2.7/tensorflow_core/python/lib/io/file_io.py", line 122, in read
self._preread_check()
File "/tensorflow-1.15.2/python2.7/tensorflow_core/python/lib/io/file_io.py", line 84, in _preread_check
compat.as_bytes(self.__name), 1024 * 512)
tensorflow.python.framework.errors_impl.NotFoundError: /cifar-100-binary.tar.gz/train; No such file or directory