tensorflow.python.framework.errors_impl.DataLossError: corrupted_record at 0 [Op:IteratorGetNext]

MCZhi / DIPP

[TNNLS] Differentiable Integrated Prediction and Planning Framework for Urban Autonomous Driving

https://mczhi.github.io/DIPP/

197 stars 40 forks source link

tensorflow.python.framework.errors_impl.DataLossError: corrupted_record at 0 [Op:IteratorGetNext] #25

Closed WeiXiCZ closed 8 months ago

WeiXiCZ commented 8 months ago

Hi, @MCZhi! Thank you very much for your nice work! When I launch open loop test, it comes to the error as shown in the following figure

Could you kindly help me to find the reason? Thank you very much for your help!~

MCZhi commented 8 months ago

Hi, @WeiXiCZ, thank you for your interest. I guess that you didn't pass the correct argument --test_set to the program of open-loop testing. Please ensure that it is a directory containing some tfrecord files.

WeiXiCZ commented 8 months ago

Oh! excuse me, sorry to bother you! I set --test_set as the directory containing the processed data, which is used for training actually. What a stupid mistake😅 Thank you again for your nice work and your help!