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
14 views

Reproducing risk curve

I want to reproduce the curve above with a code implementation using MNIST data. How can I plot the curve above with an increasing model complexity? What should I do to run experiments with increasing ...
0
votes
1answer
28 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
9 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
38 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 ...
0
votes
0answers
10 views

High accuracy in one v. all, lower accuracy in all vs. all

I am training a classifier (similar to logistic regression) on MNIST. I have 10 one -vs.-all classifiers for each number, each of which independently achieves >90% test set accuracy. However, when I ...
1
vote
0answers
22 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 ...
1
vote
0answers
17 views

How does a simple logistic regression model achieve a 92% classification accuracy on MNIST?

Even though all the images in the MNIST dataset are centered, with a similar scale, and face up with no rotations, they have a significant handwriting variation that puzzles me how a linear model ...
1
vote
2answers
31 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
20 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 ...
0
votes
0answers
28 views

How exactly should i use softmax activation in last layer of a Neural Network

I am developing a digit classifer with MNIST Dataset. I have read that for classification problems softmax activation function is used, as it maps last layer neuron's outputs into probabilities. ...
0
votes
1answer
157 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
38 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
97 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
546 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
35 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
50 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
119 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
52 views
1
vote
0answers
36 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 ...
0
votes
0answers
231 views

IndexError: too many indices for array when switching dataset to MNIST

I am trying to run a Transfer Learning Code from Github Section 9. Transfer learning for large image classification. I have gotten the original code to work with the flower dataset and inception v3. I ...
1
vote
0answers
129 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 ...
3
votes
2answers
628 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 ...
2
votes
1answer
346 views

How long does it typically take to train a MNIST data on a Mac Pro?

My code is below: ...
0
votes
1answer
73 views

Why my model can't recognise my own hand written digit?

Currently i am working on digit recognizer[0-9]. My model train accuracy 100% and test accuracy ...
0
votes
1answer
38 views

What do I initialise each model in cross validation with in a multi-layer Perceptron?

So, as far as my understanding goes, cross-validation is used to determine the best model. I understand that once we determine the best model, we then train it on the entire dataset. I'm supposed to ...
2
votes
4answers
3k views

Too low accuracy on MNIST dataset using a neural network

I am beginning with deep learning. This is an implementation of a simple neural network with just 1 hidden layer on MNIST dataset. Why is it that the loss doesn't change at all after any epoch? It ...
4
votes
1answer
1k views

0.1 accuracy on MNIST fashion dataset following official Tensorflow/Keras tutorial

My goal is to classify products pictures into categories such as dress, sandals, etc. I am using the MNIST fashion dataset, following this official tutorial word-per-word: https://www.tensorflow.org/...
1
vote
1answer
397 views

padding on mnist for LeNet Architecture

LeNet accepts 32X32 image. So, to use LeNet for MNIST dataset,we have to change the size from 28X28 to 32X32. I came across This implementation. i am confused about how the following line of code work....
2
votes
0answers
68 views

What is wrong in this Deep Neural network.?

I have recently written some simple Neural Network code just for my toy dataset and it works fine, so I have decided to take a big step forward and try to write code from scratch for MNIST data. But ...
4
votes
2answers
334 views

Pre-trained CNN for one-shot learning

I'm currently trying to learn one-shot learning using convolutional neural networks. According to this video, the CNN that I use should have been pre-trained on the MNIST. Why must the CNN be pre-...
1
vote
1answer
71 views

CNN to learn and visualize 2d features

In the paper Large-Margin Softmax Loss for Convolutional Neural Networks the author has a figure as below: He is claiming that he is using only 2d features to classify MNIST with a CNN. How is he ...
11
votes
1answer
660 views

Effect of NOT changing filter weights of CNN during backprop

What is the effect of NOT changing filter weights of a CNN during backpropagation? I changed only the fully connected layer weights while training on the MNIST dataset and still achieved almost 99 ...
3
votes
1answer
2k views

How are data in tensorflow.examples.tutorials.mnist formatted?

I am analyzing a sample code that implements a Restricted Boltzmann Machine (RBM) using Tensorflow. The input data seems to be the good old MNIST, except that apparently, it is now available in ...
2
votes
2answers
47 views

how can I infer no target in a target classification problem based on deep learning?

Let's take the MNIST dataset (My application is different) with a lot of noise, I am going to train a deep NN to classify the letters. What's the right way to infer, there's no letter possibility? or ...
3
votes
0answers
158 views

Identifying computer scanned digits

I have digit images as below which I would like to identify: Some are of slightly worse quality : The images are not of a fixed resolution but are mostly in the range (80*20 to 130 *40). Due to ...
2
votes
1answer
258 views

MNIST - Vanilla Neural Network - Why Cost Function is Increasing?

I've been combing through this code for a week now trying to figure out why my cost function is increasing as in the following image. Reducing the learning rate does help but very little. Can anyone ...
5
votes
3answers
2k views

Are CNNs insensitive to rotations and shifts in images?

Can CNNs predict well if they are trained on canonical-like images but tested on a version of images that are little bit shifted? I tried it using ...
2
votes
1answer
686 views

GAN discriminator converging to one output

I am running a GAN on the MNIST dataset. As the GAN continues to train, the quality of the generator seems to get worse, and it even seems as if it is starting to converge to just one value. Epoch 7:...
0
votes
1answer
60 views

very low variance explained after applying pca

I applied PCA on MNIST data and found that the first 64 components are able to retain 86% of variance. Is there any problem while applying pca to a big dataset like MNIST. Because in most of the ...
0
votes
1answer
797 views

Softmax vs Sigmoid in RBM/Auto Encoder final layer

I'm creating a deep network with 3 hidden layers for classification of the MNIST dataset. The network architecture is something like: ...
1
vote
2answers
1k views

how to prepare data for cross validation in mnist dataset?

How to use k-fold cross validation for MNIST dataset? I read article documentation on sci-kit learn ,in that example they used the whole iris dataset for cross validation. ...
0
votes
1answer
374 views

What is the reason that CNN classify some images horribly wrong

I'm trying to train a CNN for MNIST, everything goes well except for the loss stays very high in my model, while it's very low in example(which has different structure). this model still yields high ...
3
votes
2answers
713 views

What is the state-of-the art ANN architecture for MNIST?

What is actually the best neural network architecture for the classic MNIST digit classifying task? I couldn't find any that would claim to be the winner...
0
votes
1answer
51 views

does accuracy and performance depends on whole dataset or fraction of that data mimics the whole?

MNIST dataset is handwritten images which contains 60000 training and 10000 testing samples , can I use only a fraction of dataset for instance 10000 for training and 4000 for testing. I want to know ...
2
votes
1answer
58 views

Unknown return value in CNTK 103A

I came across this statement from CNTK 103A: gzfname, h = urlretrieve(src, './delete.me') I understand all the rest but that ...
1
vote
1answer
162 views

Classifying hand written digits dataset using Probabilistic neural network (PNN)?

I am trying to apply Probabilistic Neural Network (PNN) on MNIST dataset using MATLAB on 28000 samples. I tried to build the model but it gave an error saying matrix dimension exceeds memory showing ...
1
vote
1answer
331 views

How to divide MNIST training dataset into subparts? [closed]

Background: I am trying to train different sub-samples of MNIST dataset(1 model for 10,000 , another model for 20,000 samples, and so on until a model for all 60,000 training samples) using Caffe. ...
2
votes
0answers
135 views

SGD learning gets stuck when using a max pooling layer (but it works fine with just conv + fc)

I'm working on a CNN library for a university project and I'm having some trouble implementing the backpropagation through the max pooling layer. Please note that the whole thing was built from ...
0
votes
1answer
562 views

Why use the .idx data format?

The MNIST handwritten digit dataset uses a file format .idx. What are the advantages of this file format over alternatives such as CSV, TSX and ODS?
3
votes
1answer
2k views

Why not use more than 3 hidden layers for MNIST classification?

Many works use 2-hidden-layer neural networks for classifying MNIST handwritten digits sets. To improve accuracy, other techniques (dropout, ReLU.. etc) have been used without increasing the number ...