Closed zhangbin0917 closed 6 years ago
Did you resolve it? How?
how you solve it?
@acardoco @ydzhang12345 you need update tensorflow to 1.7.0 or set total_loss = none, and change train_set path in pipline.config with train_input_reader: { tf_record_input_reader { input_path:
@acardoco @ydzhang12345 did you all figure out this total_loss error? i can't follow the suggestion.
System information
Describe the problem
When I run train.py has a UnboundLocalError , I don't know why:
Source code / logs
train.sh
ssd_mobilenet_v1_pets.config