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.
86
questions
0
votes
1
answer
19
views
I cannot run MNIST MWE (hello world for DL)
I have installed Anaconda and want tor run MWE for MNIST but I'me getting this error:
D:\STAZENE_last\Anaconda2\Lib\site-packages\torch\cuda\__init__.py:107:
...
- 101
0
votes
1
answer
25
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 ...
0
votes
0
answers
40
views
The cost function gets stuck at 120 epochs
I did a neural network in c++ to recognize handwritten digits using the MNIST dataset without any neural network pre-existing libraries. My network has 784 inputs neuron (the pixel of the image), 100 ...
- 1
0
votes
0
answers
37
views
Getting matrix multiplication error when running inference on a Pytorch model(LeNet) using MNIST data
I have successfully trained the Pytorch LeNet model on the MNIST data, but have a probelm when running inference on single images. Below is my model architecture:
...
0
votes
0
answers
26
views
(Python, MNIST) how to load/import my own img for AI to train
Questions like these are difficult to debug, but you'll hopefully find
more help on datascience.stackexchange.com than here
I see the suggestion, that post my questionin Data science is also a good ...
1
vote
1
answer
54
views
Using python AI mnist to recognize my picture, trained accuracy is 97.99%, but accuracy to my img is less than 20%
Questions like these are difficult to debug, but you'll hopefully find more help on datascience.stackexchange.com than here
I see the suggestion that post in Data science is also a good option
Using ...
- 111
0
votes
2
answers
750
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 ...
- 113
0
votes
0
answers
23
views
Is it possible to you MNIST model for thousands of classifications?
I am very new to ML and I am trying to create a CNN which basically does exactly the same thing as MNIST handwritten digit recognition model, but instead of 10 classifications I'd like to use over ...
- 1
0
votes
0
answers
94
views
Very low accuracy and it remains constant after few epochs on MNIST database
I am developing my ANN from scratch which is supposed to classify MNIST database of handwritten digits (0-9). My feed-forward fully connected ANN has to be composed of:
One input layer, with ...
- 113
1
vote
1
answer
33
views
How to stop my CNN getting confused between 3s and 8s, and 1s and 7s?
I am trying to train a CNN, using the MNIST dataset (which I perform data augmentation on), to classify numbers on a sudoku grid from 0-9.
While mostly successful, my network seems to get confused ...
- 147
1
vote
0
answers
260
views
Reduce MNIST dataset
I am working on the MNIST dataset. How I can reduce 50% of this data?
(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()
1
vote
1
answer
117
views
Accuracy over 100%
I am using OpenFL, the Intel framework for Federated Learning.
If I run their tutorial example, I have that loss decreases and accuracy is in range 0-100%, like this:
...
- 229
4
votes
3
answers
5k
views
MNIST Digit dataset requires login
I want to download the MNIST handwritten digit data from the offical site: https://yann.lecun.com/exdb/mnist/
But it wants me to enter a username and a password. How can I download the data? Does ...
- 141
1
vote
0
answers
70
views
What model to train to restore MNIST test dataset
I came across this problem, and not sure where to start. What model would work best for this problem and why?
Imagine the digits in the test set of the MNIST dataset
(http://yann.lecun.com/exdb/mnist/)...
0
votes
2
answers
2k
views
Tensorflow - I don't get the right shapes - `ValueError: Shapes (100, 10, 10) and (100, 10) are incompatible`
I am working on the mnist classification code.
Such errors continue to occur in the code 코드 below.
...
- 1
0
votes
1
answer
339
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 ...
- 15
0
votes
3
answers
165
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
1
answer
465
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 ...
- 61
1
vote
0
answers
50
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) ...
- 229
1
vote
0
answers
24
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 ...
- 11
0
votes
1
answer
253
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, ...
- 33
0
votes
0
answers
24
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 ...
- 113
0
votes
1
answer
107
views
keras mnist dataset
I am learning Neural Network.
I was running following source code
...
user112902
0
votes
3
answers
258
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
1
answer
126
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
1
answer
171
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 ...
- 121
1
vote
0
answers
183
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 ...
- 11
0
votes
1
answer
70
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
1
answer
451
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 ...
- 157
1
vote
1
answer
2k
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 :
...
- 157
2
votes
1
answer
24
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 ...
- 123
1
vote
2
answers
714
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 ...
- 21
1
vote
0
answers
246
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 ...
- 11
0
votes
1
answer
83
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
0
answers
42
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 ...
- 21
3
votes
3
answers
2k
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 ...
- 109
-1
votes
2
answers
1k
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
0
answers
77
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
0
answers
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 ...
- 11
2
votes
0
answers
136
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 ...
- 31
5
votes
1
answer
543
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 ...
- 151
0
votes
1
answer
277
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
1
vote
1
answer
95
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 ...
- 1,723
0
votes
1
answer
2k
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 ...
3
votes
2
answers
539
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 ...
- 133
1
vote
0
answers
27
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 ...
4
votes
2
answers
3k
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 ...
- 724
0
votes
0
answers
475
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
2
answers
898
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
0
answers
7k
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]
...
