0

I am doing a classification using CNN on fake images. My data contains 100K+ images of two classes. I'm using Google Colab for doing the work. I already increased the RAM to 25 GB, but while appending the images to the array it keeps crashing. The most I can append is 16K images. Is it better to do it in smaller groups and then combine and take the average to get the accuracy, etc?

Is there any advice/solution that I can try for this?

Cris Luengo
  • 55,762
  • 10
  • 62
  • 120
nasyaaa
  • 9
  • 2
  • Use some other data type like numpy array or pandas data frame . Numpy array will be more good. Try to decrese image resolution and better if possible do not store image. Store image path – Parag Jain Jan 07 '20 at 19:19
  • What is your batch_size? Try something like this - https://github.com/santanu13/CIFAR_10_Classification_TPU/blob/master/CIFAR_10_CLASSIFICATION_TPU.ipynb – Sharan Jan 08 '20 at 06:52

0 Answers0