I am working on classifying images in "Left", "Right", "Center", "Back". Training and Validation images look like this:

enter image description here enter image description here enter image description here

The images are "Left", "Right", and "Center". I am following Pytorch transfer learning tutorial with Resnet50 architecture and have not changed anything.

The transformations I am using is as follows.

data_transforms = {"train"  : A.Compose([
                          #  A.ShiftScaleRotate(shift_limit=0.05, scale_limit=0.05, rotate_limit=15, p=0.5),
                          #  A.RandomCrop(height=128, width=128),
                           A.RGBShift(r_shift_limit=15, g_shift_limit=15, b_shift_limit=15, p=0.5),
                           A.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)),
                  "val": A.Compose([
                                    # A.CenterCrop(height=128, width=128),
                                    A.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)),

Initially I had back images too, but they were getting miss-classified with center a lot with val accuracy 65%.

Without back images I got 74% accuracy with labels left, right and center. Modified it to classify only center and not center, with only three type of images "left", "right" and "center" I have achieved 91% of val accuracy.

I am looking for ways to increase accuracy for classifying images in left, right, center.

  • $\begingroup$ Hi sandepp! does your dataset contain only one object? $\endgroup$
    – malioboro
    Sep 13 at 23:43
  • $\begingroup$ No, there are various products which I gathered from different sources mostly include electrical products like these. One of the sites I scrapped was Eaton $\endgroup$
    – sandepp
    Sep 14 at 11:18

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.