Skip to main content
Cross Validated

Return to Answer

added 60 characters in body
Source Link
Dave
Dave
  • 67.2k
  • 7
  • 105
  • 305

THIS MAKES ME THINK THERE HAS BEEN A CODING ERROR

I remember this once happening to me. I had managed to scramble the true labels so that the expected accuracy really was just one out of ten for a $90\%$ error rate (because there are ten categories with even representation). Once I fixed that coding mistake I had made, my accuracy jumped up to be more along the lines of what would be anticipated for MNIST digit classification.

MNIST is pretty easy to solve with quite high accuracy, and while overfitting could happen, your model is so simple that I would suspect a coding error that has scrambled your test set categories before I would suspect a major issue with the model.

THIS MAKES ME THINK THERE HAS BEEN A CODING ERROR

I remember this once happening to me. I had managed to scramble the true labels so that the expected accuracy really was just one out of ten for a $90\%$ error rate. Once I fixed that coding mistake I had made, my accuracy jumped up to be more along the lines of what would be anticipated for MNIST digit classification.

MNIST is pretty easy to solve with quite high accuracy, and while overfitting could happen, your model is so simple that I would suspect a coding error that has scrambled your test set categories before I would suspect a major issue with the model.

THIS MAKES ME THINK THERE HAS BEEN A CODING ERROR

I remember this once happening to me. I had managed to scramble the true labels so that the expected accuracy really was just one out of ten for a $90\%$ error rate (because there are ten categories with even representation). Once I fixed that coding mistake I had made, my accuracy jumped up to be more along the lines of what would be anticipated for MNIST digit classification.

MNIST is pretty easy to solve with quite high accuracy, and while overfitting could happen, your model is so simple that I would suspect a coding error that has scrambled your test set categories before I would suspect a major issue with the model.

added 161 characters in body
Source Link
Dave
Dave
  • 67.2k
  • 7
  • 105
  • 305

THIS MAKES ME THINK THERE HAS BEEN A CODING ERROR

I remember this once happening to me. I had managed to scramble the true labels so that the expected accuracy really was just one out of ten for a $90\%$ error rate. Once I fixed that coding mistake I had made, my accuracy jumped up to be more along the lines of what would be anticipated for MNIST digit classification.

MNIST is pretty easy to solve with quite high accuracy, and while overfitting could happen, your model is so simple that I would suspect a coding error that has scrambled your test set categories, not before I would suspect a major issue with the model performance.

I remember this once happening to me. I had managed to scramble the true labels so that the expected accuracy really was just one out of ten for a $90\%$ error rate.

MNIST is pretty easy to solve with quite high accuracy, and while overfitting could happen, your model is so simple that I would suspect a coding error that has scrambled your test set categories, not a major issue with the model performance.

THIS MAKES ME THINK THERE HAS BEEN A CODING ERROR

I remember this once happening to me. I had managed to scramble the true labels so that the expected accuracy really was just one out of ten for a $90\%$ error rate. Once I fixed that coding mistake I had made, my accuracy jumped up to be more along the lines of what would be anticipated for MNIST digit classification.

MNIST is pretty easy to solve with quite high accuracy, and while overfitting could happen, your model is so simple that I would suspect a coding error that has scrambled your test set categories before I would suspect a major issue with the model.

Source Link
Dave
Dave
  • 67.2k
  • 7
  • 105
  • 305

I remember this once happening to me. I had managed to scramble the true labels so that the expected accuracy really was just one out of ten for a $90\%$ error rate.

MNIST is pretty easy to solve with quite high accuracy, and while overfitting could happen, your model is so simple that I would suspect a coding error that has scrambled your test set categories, not a major issue with the model performance.