carlini/nn_robust_attacks

GZip error

ananyag16 opened this issue · 2 comments

ananyag16 commented

I am getting the following error on running the train.py file:

File "train_models.py", line 110, in <module>
    train(MNIST(), "models/mnist", [32, 32, 64, 64, 200, 200], num_epochs=50)
  File "/users/btech/ananyag/Desktop/ugp/nn_robust_attacks/setup_mnist.py", line 49, in __init__
    train_data = extract_data("data/train-images-idx3-ubyte.gz", 60000)
  File "/users/btech/ananyag/Desktop/ugp/nn_robust_attacks/setup_mnist.py", line 23, in extract_data
    bytestream.read(16)
  File "/usr/lib/python3.8/gzip.py", line 292, in read
    return self._buffer.read(size)
  File "/usr/lib/python3.8/_compression.py", line 68, in readinto
    data = self.read(len(byte_view))
  File "/usr/lib/python3.8/gzip.py", line 479, in read
    if not self._read_gzip_header():
  File "/usr/lib/python3.8/gzip.py", line 427, in _read_gzip_header
    raise BadGzipFile('Not a gzipped file (%r)' % magic)
gzip.BadGzipFile: Not a gzipped file (b'<!')

Can anyone please suggest the solution?

carlini commented

Probably data/train-images-idx3-ubyte.gz is an HTML file if I had to guess. If you just cat data/train-images-idx3-ubyte.gz you'll probably see somethingl ike <!DOCTYPE html> given what those first two bytes are. Assuming this is the case, you'll want to get a correct version of this file. (Or, if the link used in this repo has now gone stale, please let me know and I'll update it.)

ananyag16 commented

Yes, the file is an HTML file. I am using the file from your repo only, so if you could check the link once, it would be extremely helpful.