TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10: error First step cannot be zero when running train.py

i tried to use the same images (card) provided, i just delete all the processed file (csv,dll) and follow all the step. And when i tried to issue python train.py I got this error

Traceback (most recent call last):
  File "train.py", line 184, in <module>
    tf.app.run()
  File "C:\Users\MRCPP-Fablab\AppData\Local\conda\conda\envs\tensorflow\lib\site-packages\tensorflow\python\platform\app.py", line 126, in run
    _sys.exit(main(argv))
  File "train.py", line 180, in main
    graph_hook_fn=graph_rewriter_fn)
  File "E:\tensor\models\research\object_detection\trainer.py", line 288, in train
    train_config.optimizer)
  File "E:\tensor\models\research\object_detection\builders\optimizer_builder.py", line 50, in build
    learning_rate = _create_learning_rate(config.learning_rate)
  File "E:\tensor\models\research\object_detection\builders\optimizer_builder.py", line 109, in _create_learning_rate
    learning_rate_sequence, config.warmup)
  File "E:\tensor\models\research\object_detection\utils\learning_schedules.py", line 156, in manual_stepping
    raise ValueError('First step cannot be zero.')
ValueError: First step cannot be zero.

Any clues why this happen?

About this issue

Original URL
State: open
Created 6 years ago
Comments: 20

Most upvoted comments

yes, edit this in your config file in …\models\research\object_detection\training

train_config: {
  batch_size: 1
  optimizer {
    momentum_optimizer: {
      learning_rate: {
        manual_step_learning_rate {
          initial_learning_rate: 0.0002
          schedule {
            step: 900000
            learning_rate: .00002
          }
          schedule {
            step: 1200000
            learning_rate: .000002
          }
        }
      }
      momentum_optimizer_value: 0.9
    }
    use_moving_average: false
  }

+29

blockhunts on Jun 4, 2018

I see that epratheeban has the solution to my problem mentioned here https://github.com/EdjeElectronics/TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10/issues/11:

It’s easy. Go to the utils folder. Find the learning_schedules.py file. Go to the line 167. And replace the line 167 with below

rate_index = tf.reduce_max(tf.where(tf.greater_equal(global_step, boundaries), list(range(num_boundaries)), [0] * num_boundaries))

jim-meyer on Jun 30, 2018

@tamizharasank what file ? this kind of error copy it in google you will find the fix easily

leccyril on Jul 20, 2018

TypeError: Cannot convert a list containing a tensor of dtype <dtype: ‘int32’> to <dtype: ‘float32’> (Tensor is: <tf.Tensor ‘Preprocessor/stack_1:0’ shape=(1, 3) dtype=int32>)

tamizharasank on Jul 20, 2018