train only with VOC

[Ann-Rachel]

Hey mvoelk,

your work is great!
I try to train DSOD512 with VOC2012.

from data_voc import GTUtility
gt_util_voc = GTUtility('data/VOC2012/')
gt_util_train, gt_util_val = GTUtility.split(gt_util_voc)
.
.
.
with open(checkdir+'/source.py','wb') as f:
source = ''.join(['# In[%i]\n%s\n\n' % (i, In[i]) for i in range(len(In))])
f.write(source.encode())

and get the Error, because 'In' is unknown.
I don't think that the problem is splitting. Before I change the code I got the same issue. Is In the train List?

Could you help me please?

[mvoelk]

with open(checkdir+'/source.py','wb') as f:
    source = ''.join(['# In[%i]\n%s\n\n' % (i, In[i]) for i in range(len(In))])
    f.write(source.encode())

saves the already executed cells of the Jupyter Notebook in source.py. This makes it easier to find out under which conditions (hyperparams, etc.) the training was done.

If you run the code as Python file, you can simply remove those lines.

[Ann-Rachel]

yes, i use python, i uncommented this lines yesterday.
and it works.

thanks