0

I am getting this error when performing a custom training over a model, but the training seems to continue anyway... Is is something I should be worried about?

I tried with several batch size and learning rates, and more hyperparameter combination in general. The data is previously converted to tensorflow datasets before feeding them to the model

SrTangente
  • 11
  • 2
  • These are just warning messages which will not affect code execution until there is any code error. To solve this issue, Please make sure the `batch_size` should not be larger and can also try running this code above all the code - gpus = `tf.config.experimental.list_physical_devices('GPU')`, `tf.config.experimental.set_memory_growth(gpu, True)`. Let us know if the issue still persists. Thank you. –  Jan 18 '23 at 15:09

0 Answers0