Stack Overflow
Stack Overflow

Questions tagged [mnist]

MNIST is a database of handwritten digits collected by Yann Lecun and widely used in machine learning research.

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.

Here is the full documentation for MNIST database of handwritten digits:

It is a good database for people who want to try learning techniques and pattern recognition methods on real-world data while spending minimal efforts on preprocessing and formatting.

1329 questions
0
votes
0 answers

How to stack Autoencoder/ Create Deep Autoencoder with Theano class

I understand the concept behind Stacked/ Deep Autoencoders and therefore want to implement it with the following code of a single-layer de-noising Autoencoder. Theano also provides a tutorial for a Stacked Autoencoder but this is trained in a…
Jamona
  • 97
  • 1
  • 11
0
votes
0 answers

get mnist data as input for my program (RBMs)

i need to go from binary data when testing my RBM to simple images as MNIST. but just wonder how i could pass them as input to my program. from matlab side. Replacing X with mnist data. X= [ 1, 1, 1, 0, 0, 0; ... 1, 0, 1, 0, 0, 0; ... 1, 1, 1,…
JNW
  • 79
  • 1
  • 2
  • 8
0
votes
1 answer

How do I use a trained Theano artificial neural network on single examples?

I have been following the http://deeplearning.net/tutorial/ tutorial on how to train an ANN to classify the MNIST numbers. I am now at the "Convolutional Neural Networks" chapter. I want to use the trained network on single examples (MNIST images)…
Cajoek
  • 3
  • 2
0
votes
2 answers

Why I got unsatisfactory result when I use svm model in scikit-learner to recognize handwriting figures in MNIST?

I use the svm model in scikit-learner to predict handwriting in MNIST. However, the result I got is confused. When I use trained model to predict training set that already used in learning procedure the accuracy is 100% When dealing with the test…
sun zhaoxing
  • 1
  • 3
0
votes
1 answer

Error in system(cmd, input = filelist, intern = TRUE) : 'zip' not found

I tried to read the MNIST database using the package darch and the function readMNIST() It seems to work fine until I get the message: Error in system(cmd, input = filelist, intern = TRUE) : 'zip' not found' I looked on the internet and found out…
jeandut
  • 2,471
  • 4
  • 29
  • 56
0
votes
1 answer

R:open mnist label file

recently I am doing a project related to image recognition. And I am trying to use the MNIST dataset. I have already got some help with how to open the image file of the dataset(using readBin) but was stuck in how to open the label file. I used…
user3833612
  • 409
  • 1
  • 5
  • 14
0
votes
1 answer

Little Endian Reading MNIST File. Numbers out of range

I'm trying to read the ubyte format. I verified I'm on a little endian machine and have reversed the bits to little endian. The problem is however that the numbers I see in my file after conversion are way above 255. Any ideas? I got the code…
myselfesteem
  • 733
  • 1
  • 6
  • 23
0
votes
1 answer

Matio performance

I am trying to read MNIST data-set (size is 784*60000) my implementation of reading MNIST binary format takes around 20 secs, but I tried to use Matio library to read same data-set in .mat format and it takes much longer about 4~5 min. this is how I…
HadiRj
  • 1,015
  • 3
  • 21
  • 41
-1
votes
1 answer

How to add heading or text before input/output in gradio?

I did a machine learning project on MNIST and deployed that on gradio. Any user won't understand what he should input to use the model. So I want to add a heading or description on gradio live website so that anyone can understand. I tried with…
Indranil Saha
  • 1
-1
votes
1 answer

MNIST number guesser stuck at 9.84% accuracy

I built a MNIST dataset through watching yt tutorials. Every tutorial was using numpy but since pytorch is a newer technology I decided to build mine using pytorch. The problem is that my model is stuck at 9.84% accuracy, which means it is guessing…
josill
  • 1
-1
votes
1 answer

CNN model accuracy is oscillating strangely

I have a CNN that is designed to be trained on the MNIST data set using federated averaging (the model is trained locally on a number of clients for a number of local epochs on local client's data and then averaged). The accuracy of the model is…
Hashitiba
  • 1
-1
votes
1 answer

I want to convert array of intensities to an image

I have the MNIST dataset. The CSV file contains 70,000 rows and 785 columns. The last column is the label. I want to convert the first columns of a row to the respective grayscale image with dimensions 28x28. Image of the data:
Yasin Karayanık
  • 1
  • 2
-1
votes
1 answer

CNN: Unstable of model score vs iteration

I got my model score vs iteration graph is unstable. How can I improve it? This is what I get Here is my code Code 1 Code 2 Code 3 Code 4 Code 5
Chee Wei Han
  • 1
  • 1
-1
votes
1 answer

Why doesn't loss function decrease under 1.5?

I'm trying to do machine learning using mnist dataset in pytorch, but the loss function doesn't decrease under 1.5. I want the loss function to decrease under 1. What to do for this problem? what code should I fix? This is my code: BATCH_SIZE =…
kindamu24005
  • 1
  • 2
-1
votes
1 answer

Pytorch MNIST ResNet50 ValueError: Target is multiclass but average='binary'

https://colab.research.google.com/github/kjamithash/Pytorch_DeepLearning_Experiments/blob/master/FashionMNIST_ResNet_TransferLearning.ipynb#scrollTo=QrIm8SnsUmaK When I ran this code, I encountered a problem that: ValueError: Target is multiclass…
Jason Wang
  • 1
1 2 3
…
88 89