Python Forum
Unresolvable traceback | Tensorflow
Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Unresolvable traceback | Tensorflow
#1
Hello,
first of all, I am a total beginner in terms of TensorFlow, therefore I ask for forbearance. So, let s get to my problem. I am building a RNN for sound classification, therefor I have chosen this example code: github.com/aqibsaeed/Urban-Sound-Classification/blob/master/Urban%20Sound%20Classification%20using%20RNN.ipynb

I had to change a lot because of version changes. Here is my code: github.com/MrGrimod/accent-recognition_rnn

Python: '3.5.4' TensorFlow: '1.3.0'

When I run my code this err occurs: github.com/MrGrimod/accent-recognition_rnn/blob/master/err.txt

I do only know that the second tensor[50,2] is batch_y because batch_y=tr features[offset + batch_size,:] and offset is 0 and batch_size 50. 0+50 = 50 = [50,2]. But when I remove offset from batch_y everything stays same. But when I remove offset from batch_x the second tensor in tracback is [414,2].

But x_batch tensor should have 3 dimensoins -.- .

I am overwhelmed and hope for constructive answers.
Reply


Forum Jump:

User Panel Messages

Announcements
Announcement #1 8/1/2020
Announcement #2 8/2/2020
Announcement #3 8/6/2020