Questions tagged [mnist]
MNIST is a database of handwritten digits collected by Yann Lecun, a famous computer scientist, when he was working at AT&T-Bell Labs on the problem of automation of check readings for banks. The data set is a benchmark widely used in machine learning research. Due to its small size it is also widely used for educational purposes.s based on C++ but provides APIs for Python and Matlab.
91 questions
5 votes
0 answers
72 views
Model misclassifies digits from MNIST dataset after trained it on Digits dataset
I am training a machine learning model to classify digits in order to detect and solve a Sudoku puzzle. Here’s the approach I followed: This is the pipeline I am following: Classifier training: I ...
- 177
0 votes
1 answer
62 views
My keras CNN model gives good predictions in 10/11 classes but missleads to the 11th class. What can I do to improve?
My project involves classifying printed numerical characters from real-life essays. My dataset includes 11 classes ('0' - '10'), with the label '10' representing the '/' symbol. The issue is that ...
0 votes
0 answers
46 views
Convolutional Network not Fully Learning MNIST (60% accuracy)
I have been working on a self-made Conv Net for some time. In addition to my network taking multiple epochs to increase the test-set accuracy, the accuracy flatlines at about 60% around 30 Epochs. ...
- 1
1 vote
0 answers
110 views
Negative MNIST - Trying to understand what's going on here
I'm new to machine learning and pytorch and any insight would be greatly appreciated. I've been playing around with the MNIST number recognition dataset and thought it would be interesting to train ...
- 111
1 vote
0 answers
70 views
GAN/DC-GAN isn't converging
I've been trying to train a vanilla GAN(for MNIST) for a few days, and nothing works. I've tried a lot of different layers, hyperparameters, and more, but every time the discriminator's loss decreases(...
- 11
2 votes
2 answers
801 views
Is there a list of all the incorrectly labelled MNIST images along with their correct labels?
It seems that its well known that the MNIST handwritten digit dataset contains quite a few examples where the labels are clearly wrong and correspond to the wrong digit, some examples of people ...
- 21
0 votes
1 answer
65 views
What is the highest possible prediction accuracy when I flip some labels at random?
I want to predict MNIST labels in a binary setting using a simple MLP model (0 for digits 0-4 and 1 for 5-9). For the train and test data, I randomly flip 25% of the labels. Is the maximum achievable ...
1 vote
2 answers
4k views
Training and validation loss are almost the same (perfect fit?)
I am developing an ANN from scratch which classifies MNIST digits. These are the curves I get using only one hidden layer composed of 100 neurons activated by ...
- 177