Error：seq2seq_im_mask.py, line125, keep[d['low_idx']] = im[i]

[shogi880]

Hi~ I get an Error:

"MyPC/alfred/models/model/seq2seq_im_mask.py", line 125, in featurize keep[d['low_idx']] = im[i] IndexError: index 70 is out of bounds for dimension 0 with size 60

Hi, when I run this script on local macbook. python models/train/train_seq2seq.py --data data/json_feat_2.1.0 --model seq2seq_im_mask --dout exp/model:{model},name:pm_and_subgoals_01 --splits data/splits/oct21.json --batch 8 --pm_aux_loss_wt 0.1 --subgoal_aux_loss_wt 0.1

and I fix it to change the code this way. But I don't know is it Okay ~ keep[d['low_idx']] = im[i] -> keep[d['low_idx']] = im[d['low_idx']]

Could anyone check it for me ! Thank you very much. ^_^

[MohitShridhar]

@shogi880 have you pulled the latest from master? Because L125 looks different.

Also, we recently updated the json_feat_2.1.0 dataset (about a month ago). So make sure to re-download that too.

[shogi880]

@shogi880 have you pulled the latest from master? Because L125 looks different.

Also, we recently updated the json_feat_2.1.0 dataset (about a month ago). So make sure to re-download that too.

Ohhh! Thanks for your response! It seems I need to re-download the big data~

By the way, very interesting dataset!! Thanks😊