TypeError: iteration over a 0-d array when trying to label from df

(Dean) #1

I’ve been trying to create a databunch from my personal Gait dataset. The output classification I am looking to predict is the last column named ‘label’, seen below:

Each subject in the dataset is either healthy, old, or has Parkinson’s disease.

This is the code I’ve been using to try provide these labels

MixedGaitList.from_df(joined_df, cat_cols, cont_cols, txt_cols, vocab=None, procs=procs, path=PATH)
                            .label_from_df() #cols=dep_var, label_cls=MultiCategoryList)  #.get_label_cls(labels=labels)   #.label_from_df(dep_var)
                            #Data augmentation? -> Standard transforms; also transform the label images
                            .databunch(bs=8,collate_fn=collate_fn, no_check=False)   

This worked for test datasets I’ve thrown through it, the only difference is that the dependant variable is text instead of numerical, any ideas what I am doing wrong?


=== Software === 
python        : 3.6.7
fastai        : 1.0.52
fastprogress  : 0.1.21
torch         : 1.1.0
nvidia driver : 410.79
torch cuda    : 10.0.130 / is available
torch cudnn   : 7501 / is enabled

=== Hardware === 
nvidia gpus   : 1
torch devices : 1
  - gpu0      : 15079MB | Tesla T4

=== Environment === 
platform      : Linux-4.14.79+-x86_64-with-Ubuntu-18.04-bionic
distro        : #1 SMP Wed Dec 19 21:19:13 PST 2018
conda env     : Unknown
python        : /usr/bin/python3
sys.path      :