mingzhu0527 / har Goto Github PK

Could you please provide the HealthQA dataset to run the code? Thank you!

Hello !

I am getting the following error:

[09-12-2019 15:10:09]   [Train:train] Traceback (most recent call last):
  File "/home/dpappas/HAR/matchzoo/main.py", line 359, in <module>
    main(sys.argv)
  File "/home/dpappas/HAR/matchzoo/main.py", line 351, in main
    train(config)
  File "/home/dpappas/HAR/matchzoo/main.py", line 159, in train
    verbose = 0
  File "/usr/lib64/python2.7/site-packages/keras/legacy/interfaces.py", line 91, in wrapper
    return func(*args, **kwargs)
  File "/usr/lib64/python2.7/site-packages/keras/engine/training.py", line 1426, in fit_generator
    initial_epoch=initial_epoch)
  File "/usr/lib64/python2.7/site-packages/keras/engine/training_generator.py", line 191, in fit_generator
    class_weight=class_weight)
  File "/usr/lib64/python2.7/site-packages/keras/engine/training.py", line 1214, in train_on_batch
    class_weight=class_weight)
  File "/usr/lib64/python2.7/site-packages/keras/engine/training.py", line 792, in _standardize_user_data
    exception_prefix='target')
  File "/usr/lib64/python2.7/site-packages/keras/engine/training_utils.py", line 100, in standardize_input_data
    str(len(data)) + ' arrays: ' + str(data)[:200] + '...')
ValueError: Error when checking model target: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 1 array(s), but instead got the following list of 2 arrays: [array([[1],
       [0],
       [1],
       [0],
       [1],
       [0],
       [1],
       [0],
       [1],
       [0],
       [1],
       [0],
       [1],
       [0],
       [1],
       [0],
       ...

Could you please help me to fix it ?
Thank you

To run the model ANMM and DRMM , we need to generate hist and binsum txt file.
But I found in the process.py, the function cal_hist and cal_binsum have some errors. The question and answer matching matrix should be calculated as the cosine similarity value instead of the dot product directly.

Is there a pytorch version of the implementation?

Hello

I get the following error:
python: can't open file 'norm_embed.py': [Errno 2] No such file or directory

Shortly after starting the training the process crashes with the following error:

Traceback (most recent call last): File "matchzoo/main.py", line 359, in <module> main(sys.argv) File "matchzoo/main.py", line 351, in main train(config) File "matchzoo/main.py", line 159, in train verbose = 1 File "/usr/lib/python3.7/site-packages/keras/legacy/interfaces.py", line 91, in wrapper return func(*args, **kwargs) File "/usr/lib/python3.7/site-packages/keras/engine/training.py", line 1658, in fit_generator initial_epoch=initial_epoch) File "/usr/lib/python3.7/site-packages/keras/engine/training_generator.py", line 215, in fit_generator class_weight=class_weight) File "/usr/lib/python3.7/site-packages/keras/engine/training.py", line 1443, in train_on_batch class_weight=class_weight) File "/usr/lib/python3.7/site-packages/keras/engine/training.py", line 795, in _standardize_user_data exception_prefix='target') File "/usr/lib/python3.7/site-packages/keras/engine/training_utils.py", line 105, in standardize_input_data str(len(data)) + ' arrays: ' + str(data)[:200] + '...') ValueError: Error when checking model target: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 1 array(s), but instead got the following list of 2 arrays: [array([[1], [0], [1], [0], [1], [0], [1], [0], [1], [0], [1], [0], [1], [0], [1], [0], ...
I tried to train the model with the HealthQA-dataset and adjusted my config so the paths point to the prepared HealthQA-dataset-directory.