0

I am facing difficulties in training a custom image classification model (EfficientNetB0) on a dataset of 36,000 images of size (100, 100, 3). The images consist of alphanumeric characters (0-9 and A-Z) and my goal is to classify them. My attempts at training the model have been unsuccessful due to either high memory usage on Google Colab or overheating on my MacBook Air M1. I am seeking suggestions for free alternative training methods and models that would be suitable for this classification task.

Below I have also attached images of Google Colab issue and a sample image from my dataset. colab_crash_image sample_dataset_image

Here, is what I have tried till now:

  • Using Google Colab for training, didn't work due to high memory usage.
  • Using inbuilt processor of MacBook Air M1, didn't work due to overheating issue.
  • Tried implementing transfer learning on EfficientNetB0 with imagenet weights, got training accuracy of 87% but only 46% test accuracy.
Utsav Desai
  • 1
  • 2
  • EfficientNetB0 is a small model and your dataset is also on the small side. A regular off-the-shelf laptop should have no trouble with this, let alone Google Colab or a Macbook Air M1. There's probably a problem with your code somewhere. I would suggest following a tutorial on the PyTorch website using one of their datasets. Then slowly work up to your case until either you get it working or you figure out the cause of the problem. – Tyson Feb 10 '23 at 03:08
  • There are no programming details here, no code, just vague descriptions, with this we cannot really help you. – Dr. Snoopy Feb 10 '23 at 07:48

0 Answers0