![Questions Tagged [Mnist]](https://docuprint.cloud68.co/uploads/questions-tagged-mnist_1200.jpg)
MNIST is a database of handwritten digits collected by Yann Lecun and widely used in machine learning research.
1,232
questions
3
votes
1
answer
23
views
traceback when trying to set up the Michael Nielsen mnist network
I'm trying to set up a network for learning mnist digits as described by Michael Nielsen in his book (). However, when trying to ...
0
votes
0
answers
27
views
Number of digits in MNIST data in python
How can I find the number of samples per digit in training and test sets? Also if I want to >visualize at least 9 images for each digit in the training data.
#Loading MNIST data set in Python
...
0
votes
0
answers
24
views
Adding a voice output to the python project
i want to improve this project, i shared the link of it down below.
In the link that i shared i want to improve the project where i want to add a voice output when the digit gets recognised for ...
0
votes
0
answers
16
views
Convert tensorflow 1.x model architecture into tensorflow 2.x compatable code
I've been having trouble implementing a tensorflow 1.x model arch in tensorflow 2.x. Here is the v1 code
class ZicoMNIST(object):
def __init__(self, images):
self.x_image = images
...
0
votes
0
answers
31
views
Trying to download dataset, code doesn't work in Jupyter notebook but it does work in Pycharm
I'm trying to download the MNIST dataset from openml, using the openml library.
I tried using Jupyter notebooks because I don't want to download the same dataset every time.
Problem is, after running ...
0
votes
0
answers
21
views
How can we use a dataset like mnist to create a .traineddata file in pytesseract datasets
I am trying to improve accuracy of (py)tesseract OCR for handwritten digits(0-9)
How can I create a custom font file like mnist.traineddata by using mnist dataset to use with pytesseract ...
-1
votes
0
answers
11
views
caffe2 - create own MNIST lmdb dataset from numpy array
I am currently trying to create a MNIST lmdb dataset from my own data saved as numpy arrays data (shape (50000,1,28,28)) and label (shape (50000,)).
Does someone know how to convert numpy arrays to a ...
1
vote
0
answers
18
views
Fully connected network loss not decreasing over CIFAR-10 Dataset
Problem Description
I have constructed a fully connected model as shown by the code below:
auto* model = new Sequential({
new Linear(3072,120),
new ReLU(120),
new Linear(...
1
vote
1
answer
34
views
Failed to use transforms.ToTensor and transforms.Normalize to normalize the MNIST dataset
I used the following code to normalize the MNIST dataset, when I print the first sample, it fails to normalize as the max element is 255, not 1.
train_transform = transforms.Compose([
transforms....
-1
votes
0
answers
16
views
Why might my SVM (support vector machine) predict every input the same? MNIST Digit Recognition
Ive been working at this for awhile trying to verify the correct inputs and everything, but no matter what I try, my SVM is always predicting the same value for every single input, even when training ...
0
votes
0
answers
17
views
converting gray image of single digit to text using mnist trained cnn for better results than tesseract
My aim is to convert and image of single digit to text
Currently I am using tesseract with trained data (digits1) from
Accuracy is < 70% in my case ....
-1
votes
0
answers
57
views
ValueError: Data cardinality is ambiguous (x sizes: 60000 y sizes: 10000 Make sure all arrays contain the same number of samples.)
I'm using mnist dataset for my project on VsCode IDE. Following is the complete code. what is it that I'm doing wrong and how can I solve this error?
# Import Libraries
import numpy as np
import ...
0
votes
1
answer
61
views
How to solve - from tensorflow.examples.tutorials.mnist import input_data Error
I'm trying import all the libraries needed to run a two-layer model. However when I add following
from tensorflow.examples.tutorials.mnist import input_data
It shows yellow curly lines below the same ...
0
votes
1
answer
13
views
How to print dataset sample like shown in first and second pictures, rather than third picture?
This is the first sample from MNIST dataset, as you could see, data is more expressive in first and second pictures, where we could also see the class when observed/stared carefully, you could see 5 ...
0
votes
0
answers
20
views
Split Datasets per labels
I want to split some datasets such as CIFAR10 or MNIST in a non-iid way: basically I am doing Federated Learning experiments, in which I want that each client has 2 classes of the dataset. I achieve ...
