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.

Filter by
Sorted by
Tagged with
0
votes
0answers
7 views

Novice machine learner wondering how to interpret big variance in batch error across batches in MNIST perceptron

I'm trying to get a better understanding of basic neural networks by implementing a little framework in C++. I've started with the classical MNIST exercise. I get to 91% accuracy on the test sample ...
0
votes
0answers
5 views

save reconstructed data points from variational autoencoder as original MNIST

I have a VAE implementation that generates images from the latent distribution. I want to save those "images" as we have in the original dataset. For example, my VAE generates a data point, ...
0
votes
0answers
13 views

How to modify this training function in order to print the aggregation of models

I have 3 VGG: VGGA, VGGB and VGG*, trained with the following training function: ...
0
votes
1answer
29 views

MNIST dataset for digit recognition

I noticed that the MNIST dataset for digit recognition is just a CSV file They don't provide the images. https://www.kaggle.com/c/digit-recognizer/data Is it possible to get the corresponding ...
0
votes
3answers
62 views

Which neural network is better?

MNIST dataset with 60 000 training samples and 10 000 test samples. Neural network #1. Accuracy on the training set: 99.53%. Accuracy on the test set: 99.31%. Neural network #2. Accuracy on the ...
2
votes
1answer
46 views

Difference between grayscaled and binary mnist dataset

When making a cnn you could use the classic mnist dataset containing grayscale images. I am considering transforming them to simple binary images instead, the questions is should i? It will be much ...
0
votes
0answers
12 views

What is a "knowledge-free" neural network model?

In the paper Representation Learning: A Review and New Perspectives by Bengio et al., Bengio writes The beginnings of deep learning in 2006 have focused on the MNIST digit image classification ...
1
vote
0answers
13 views

Multi Input Network MNIST-CIFAR10

I have the following task of meta learning: We want that our neural network learns to sum weights. 1)Do the training on MNIST, and on CIFAR10 (as support dataset). We want that performance (accuracy) ...
1
vote
0answers
16 views

Developing Custom MLP for Mnist

I am trying to develop a custom MLP for MNIST Dataset with 2 hidden fully connected layers Mnist: 28281 FC1: input 28*28, output 512 FC2: input 512, output 128 Classifier: FC: input 128, output 10 I ...
0
votes
1answer
58 views

How to pass a sequence of 4 images into LSTM and CNN-LSTM

I got an assignment and stuck with it while going down the rabbit hole of learning PyTorch, LSTM, and CNN. Provided the well-known MNIST library I take combinations of 4 numbers and per combination, ...
0
votes
0answers
16 views

Can't get a regression problem to converge

I am working on implementing a really simple version of YOLO to learn about pytorch and building deep learning models. My dataset consists of images which have two MNIST digits placed somewhere on the ...
0
votes
0answers
22 views

Why is my accuracy 0 on the first epoch in continuous training on MNIST

I'm trying an experiment where I first train my model on MNIST labels [0-4], and then I freeze the first conv layers and continue training my model on labels [5-9]. When I dont re-initialize my Fully ...
0
votes
1answer
26 views

keras mnist dataset

I am learning Neural Network. I was running following source code ...
0
votes
0answers
26 views

Generalized Hebbian Algoithm (GHA) stability issues

The GHA proposed by Sanger in 1989 is supposed to be very numerically stable. There are some implementations of it floating around, for example this one https://github.com/matwey/python-gha. In that ...
0
votes
1answer
50 views

What are some general tips to improve my MNIST classifier?

I have built a CNN from scratch in python using Numpy, to tackle the MNIST hand-written digit recognition problem. It's composed out of a convolutional layer (3 3x3 filters), a maxpooling layer (2x2 ...
0
votes
0answers
50 views

Defining input shape in TensorFlow layers

I am trying to code my first TF program using Fashion-mnist data. In doing so i have some doubts regarding the usage of parameters while creating the layers. Irrespective of me defining the first ...
0
votes
1answer
61 views

MNIST 2-layer NN failing to recognize certain digits

Recently I've been taking a look into some basic multilayer neural networks, and I decided to try tackling the MNIST database of handwritten digits using a 2 layer neural network with 100 neurons in ...
2
votes
1answer
34 views

What are the Most Dissimilar MNIST Digits?

Using whatever definition of dissimilarity over sets that you'd like, what are the most dissimilar two digits in MNIST? I was thinking that a reasonable approach to answering the question would be to ...
1
vote
0answers
110 views

pytorch code for VAE for MINST forces mu and logvar to zero

I am new to pytorch and trying to implement a VAE for MNIST data. When I try to train my model, it appears that the model forces mu and logvar to zero (or something very close to zero) independent of ...
0
votes
1answer
34 views

Neural Network written in Kotlin working for simple math problems but not for MNIST classification

I'm building a neural network in Kotlin while reading the book "Neural Networks and Deep Learning" from Michael Nielsen. At the moment the network uses: sigmoid neurons, backpropagation, ...
4
votes
1answer
206 views

How to make an MNIST classifier work with blank images?

I am trying to make a Sudoku solver and for the image recognition I trained a CNN but the problem that I am facing is that I don't know how to make it see a clear distinction between numbers and blank ...
1
vote
1answer
518 views

How do reshape an image to fit my Mnist Convolutional model?

I have done research but cannot seem to find what's wrong here I have created this model for Mnist digit clasification : ...
2
votes
1answer
15 views

Separating styles of numbers for simple digit classification

I am just getting started with my first simple digit classifier, so my doubts are at a pretty low level. In every dataset of digit images I've seen so far, different variants of each digit are grouped ...
1
vote
2answers
169 views

MNIST data shape

In going through the different tutorials on CNN, autoencoders, and so on I trained myself on the MNIST problem. The different images are stored in a 3D array which shape is (60000,28,28). In some ...
1
vote
0answers
148 views

MNIST GAN generator loss increasing

I'm trying to train a simple vanilla GAN on MNIST with Tensorflow. I used this github page as a reference and in my process to try and get my GAN to work I've made my code more and more similar to ...
0
votes
1answer
40 views

Should I put time on my Vanilla ANN for classifying MNIST Dataset

I am building a Vanilla Neural Network in Python for my Final Year project, just using Numpy and Matplotlib, to classify the MNIST dataset. Here's the specifications of the model: One Input Layer + ...
1
vote
0answers
12 views

HoG features taking longer time in Google CO-LAB

I have been doing this for 2 days now. I want to make a model using sklearn that uses the HoG (Histogram oriented Gradients) features to classify the image (MNIST dataset having 70,000 images both ...
3
votes
3answers
1k views

Artificially expanding the datasets through rotation of images in MNIST

I came across this question from the 3rd chapter of the book Neural Networks and Deep Learning by Michael Nielsen, this is a question given in his exercise. One way of expanding the MNIST training ...
-1
votes
2answers
440 views

ValueError: Error when checking input: expected dense_9_input to have 2 dimensions, but got array with shape (60000, 28, 28)

I'm doing a regular detection of numbers from photos with MNIST, but when i try to fit my model, it doesn't work, and it dispayed this message... ...
1
vote
0answers
35 views

tf.keras: val accuracy on mnist dataset drops to random guess

For transfer learning purposes I changed mnist into 224x224 px dataset and applied skeletonizing algorithms. I want to train MNIST dataset on "squeezenet" like CNN, which can be found on github. The ...
1
vote
0answers
34 views

What neural network can I use to unmerge numbers?

I am working on a hobby project where I superimpose two different samples of two different numbers from the MNIST dataset. However, I'm stuck at what model I could use. I tried messing around with ...
2
votes
0answers
96 views

Understanding the significance of LeNet-5 w/ MNIST data set

I'm beginning to learn about conv nets and started with what I understand to be one of the seminal works: LeNet-5. However, my limited experimentation doesn't seem to show any advantage over a single ...
5
votes
1answer
377 views

How to use MNIST dataset to make predictions on similar images (colorblindness charts)?

I am trying to use the MNIST dataset to train a convolutional neural network to classify digits written in colorblindness charts. As some people have suggested, I have tried playing with the ...
0
votes
1answer
153 views

KNN scoring low compared to Logistic regression in MNIST challenge

KNN gives me a score of 0.76100 while it shows 94% accuracy for my training data (splitted with test_size =0.3) in my jupyter notebook while logistic regression gives me a score of 0.91485 with an ...
1
vote
1answer
40 views

Is it faster and better to train a GAN on just one digit as opposed to the whole mnist dataset?

When going through an introductory GAN tutorial to generate mnist like handwritten digits I wondered whether the systematic variance in the training data due to the different digits makes the model ...
0
votes
1answer
1k views

Split tuples with labeled samples in training, validation and test sets

I was reading through all the internet and i can't find nothing similar what i am looking for, i only saw this topic for pd.DataFrame, np.ndarray and list datasets but i didn't find nothing explaining ...
1
vote
0answers
151 views

Do we need to divide our gradients by batch size our we will use the sum (Mini batch GSD plus L2 Regularization)?

I am implementing L2 regularization in C++ and I used mini batch GSD. Without L2, I was using sum of gradients during back propagation and I was not dividing my cost function by batch size. I was ...
3
votes
2answers
208 views

Finding correlation between MNIST digits

What way would be correct to calculate the correlation between say digit '1' and digit '7' images from MNIST? Taking average values of all digit '1' pixels and digit '7' pixels to compute correlation ...
1
vote
0answers
26 views

Binary training result in chainer

I am training simple Chainer based CNN to recognise MNIST samples. To each sample I add poissonian noise. For the test purpose I have always the same random seed. I restart training resetting the ...
3
votes
2answers
2k views

DC GAN with Batch Normalization not working

I'm trying to implement DC GAN as they have described in the paper. Specifically, they mention the below points Use strided convolutions instead of pooling or upsampling layers. Use only one fully ...
0
votes
0answers
314 views

How to visualize the weights of the output(classification) layer?

I'm doing a Convolutional Neural Network of MNIST data set, and how can I visualize the weights of the output(classification) layer? I only found several websites visualizing the filters in CNN model ...
0
votes
2answers
432 views

Low accuracy on MNIST Dataset [closed]

Hi downloaded the MNIST dataset images and labels and I am trying to train but I am getting low accuracy which is very low . not Even 50 %. below is my code. ...
0
votes
0answers
6k views

Error: Negative dimension size caused by subtracting 3 from 1

The dataset here is the famous MNIST. Here's the error: Negative dimension size caused by subtracting 3 from 1 for 'conv2d_8/convolution' (op: 'Conv2D') with input shapes: [?,1,1,64], [3,3,64,128] ...
0
votes
1answer
47 views

Error on CGAN / InfoGan [closed]

So i'm trying to execute the code provided here: https://github.com/eriklindernoren/Keras-GAN/blob/master/infogan/infogan.py Both for InfoGAN and CGAN i get the same error: ...
0
votes
1answer
143 views

Data set of vectors of SVG paths for digits

I have used the MNIST data set many times to train models for digit recognition based on object character recognition (OCR). I am now trying to do the same but with a data set of svg paths.. I am ...
2
votes
2answers
169 views

Need a little help Understanding how to build model's in Keras

I am trying to make a CNN in Keras, and to test the validity of my model i am trying to get it to train on MNIST dataset, so i am sure that everything is working fine, but unfortunately model is ...
0
votes
0answers
205 views

Better way to deal with downsampled MNIST images

...
1
vote
1answer
121 views

Does MNIST generalise to european handwriting?

I want to use the MNIST dataset to teach my neural network to recognise numbers. My problem is: The data I am working with is "european". What i mean by that is: the seven always has a dash (it often ...
1
vote
0answers
289 views

How to avoid MemoryError when using fetch_openml()?

I am using the following code to get mnist from sklearn.datasets import fetch_openml mnist = fetch_openml('mnist_784', version=1, cache=True) It has worked ...
5
votes
3answers
4k views

How mean and deviation come out with MNIST dataset?

I am a novice at the data science, and I notice some repository state the mean value and deviation in MNIST dataset are ...