Is there Something to be done after running download.sh for smallNORB data to be available?

[moriyas1984]

I run ./download.sh under ./data and then the directory smallNORB and 4 files smallnorb-xxxx-{testing|training}-{cat|dat}.mat got available. But when I tried to train the network with the smallNORB dataset by sending the command python train.py "smallNORB", errors as follows returned.

$ python3 train.py "smallNORB"
Using TensorFlow backend.
2018-08-07 19:49:45,984 [5964] INFO     __main__: Using dataset: smallNORB
2018-08-07 19:49:45,990 [5964] CRITICAL root: Traceback (most recent call last):
  File "train.py", line 156, in <module>
    tf.app.run()
  File "/home/user/python3.6/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 126, in run
    _sys.exit(main(argv))
  File "train.py", line 52, in main
    batch_x, batch_labels = create_inputs()
  File "/path/to/Matrix-Capsules-EM-Tensorflow/config.py", line 84, in <lambda>
    'smallNORB': lambda: create_inputs_norb(is_train, epochs),
  File "/path/to/Matrix-Capsules-EM-Tensorflow/utils.py", line 31, in create_inputs_norb
    image, label = norb.read_norb_tfrecord(chunk_files, epochs)
  File "/path/to/Matrix-Capsules-EM-Tensorflow/data/smallNORB.py", line 128, in read_norb_tfrecord
    filename_queue = tf.train.string_input_producer(filenames, num_epochs=epochs)
  File "/home/user/python3.6/lib/python3.6/site-packages/tensorflow/python/training/input.py", line 241, in string_input_producer
    raise ValueError(not_null_err)
ValueError: string_input_producer requires a non-null input tensor

Did I miss anything to do before training with smallNORB? I think the 4 files downloaded should be converted tfrecord files.

I'm a begginer of tensorflow so what I said maybe beside the point...

Thanks.

[lithostark]

Hi, I'm having exactly the same problem. Any solutions please?

[zhaolei0413]

嗨，我也遇到了 相同的问题，请问有解决吗

[yhyu13]

I believe python smallNORB.py tfrecord to generate tfrecord files (tensorflow multi-thread I/O files) from raw data.

[zhaolei0413]

I believe python smallNORB.py tfrecord to generate tfrecord files (tensorflow multi-thread I/O files) from raw data.

Thank you very much for your reply. But after I ran your code “python3 smallNORB.py tfrecord” , there were new errors. CRITICAL root: Traceback (most recent call last): File "smallNORB.py", line 210, in argh.dispatch(parser) File "/home/ailab/.local/lib/python3.5/site-packages/argh/dispatching.py", line 174, in dispatch for line in lines: File "/home/ailab/.local/lib/python3.5/site-packages/argh/dispatching.py", line 277, in _execute_command for line in result: File "/home/ailab/.local/lib/python3.5/site-packages/argh/dispatching.py", line 260, in _call result = function(*positional, **keywords) File "smallNORB.py", line 115, in tfrecord write_data_to_tfrecord(kind='train', chunkify=False) File "smallNORB.py", line 86, in write_data_to_tfrecord images = images[perm] MemoryError After I tried to allocate 6G memory to the virtual machine, it was still a mistake. Do you know the solution?

[yhyu13]

@zhaolei0413 Try to allocate as much memory to the VM as possible, 6G might not be enough since it still shows "MemoryError".

[zhaolei0413]

我相信python smallNORB.py tfrecord从原始数据生成tfrecord文件（tensorflow多线程I / O文件）。

当我尝试这个时，我收到以下错误： FileNotFoundError: [Errno 2] No such file or directory: './smallNORB/smallnorb-5 x46789x9x18x6x2x96x96-training-dat.mat' You downloaded less smallNORB files. You can download them from my link and extract them into the data directory. 链接: https://pan.baidu.com/s/1_AmFIG8hagZMgevvK8wPmQ 提取码: rcd1