Hello all ～
I have successfully run the ./src/make.sh and ./src/data.py with some personal modifications， Now I am trying to execute the train.py. However, in train.py line 103 "with BatchLoading(data_splitter.training_bags, data_splitter.training_tags, require_shuffle=True) as training" ,as we can see,when i use kitti dataset,the variable"data_splitter" won't be defined,so the line will report an error "NameError: name 'data_splitter' is not defined",because "data_splitter " is only initialized in line 82 for didi2 dataset.
all in all，how should I initialize the class "data_splitter "when using kitti dataset.
adioshun
commented
7 years ago
Hello all ～ I have successfully run the ./src/make.sh and ./src/data.py with some personal modifications， Now I am trying to execute the train.py. However, in train.py line 103 "with BatchLoading(data_splitter.training_bags, data_splitter.training_tags, require_shuffle=True) as training" ,as we can see,when i use kitti dataset,the variable"data_splitter" won't be defined,so the line will report an error "NameError: name 'data_splitter' is not defined",because "data_splitter " is only initialized in line 82 for didi2 dataset.
all in all，how should I initialize the class "data_splitter "when using kitti dataset.
Thank you