Neural Network Python Project - Handwritten Digit Recognition
Why Stack Overflow recommends it
Stack Overflow users cite it as the beginner tutorial they followed when they hit problems saving the model, reading their own digit images, or extending the approach to multiple digits.
Recommended by 0 people across 0 different months, 2023 to 2024.
What it is
A roughly 23-minute tutorial by NeuralNine that uses TensorFlow and Keras to build and train a neural network on the MNIST dataset, then tests it on handwritten digit images the presenter draws himself. It walks through the code step by step in Python.
What people said
Cites azazelspeaks · 2023-03 · Stack Overflow · on “Neural Network: Detect multiple digits from an image”
I have a neural network that detects single digits from an image of a 6 digit display (A digital clock with hours, minutes and seconds). I've trained it on a picture database of 10k images of the clock (tagged with eg- 14:45:02 corresponding to the clock) using most of the techniques mentioned in this youtube video on digit detection: [this video] It works well on one digit at a time. However, I have to do image segmentation and contour detection to find my digits every time because depending on how the picture of the image was taken, the digits can be randomly spaced. I then send the separated images to the NN to detect the numbers. The problem is, depending on how the picture of the clock was t
Cites Santaissick · 2023-10 · Stack Overflow · on “Can't use model.save with TensorFlow/Keras. Probably because TensorFlow doesn't support non-English letters”
I'm a beginner and I'm following tutorial by NeuralNine: [this video] Trying to make a very basic neural network to recognize handwritten digits in python. Training the model and everything else works just fine until I try to save the model using model.save and I get the following in the terminal: Traceback (most recent call last): File "c:\Users\Käyttäjä\Desktop\Sampo\Neural\handwritten.py", line 33, in model.save('handwritten.model.test1') File "C:\Users\Käyttäjä\AppData\Local\Programs\Python\Python311\Lib\site-packages\keras\src\utils\traceback_utils.py", line 70, in error_handler raise e.with_traceback(filtered_tb) from None File "C:\Users\Käyttäjä\AppData\Local\Programs\Python\Python311\Lib\
Cites NonoTheGrappler · 2024-02 · Stack Overflow · on “Neuronal Network doesnt recognize Handwritten Digits 28*28 Pixel MNIST Data set trained”
I have done a YT tutorial [this video] about creating a neuronal network which recognizes handwritten digits. It's trained with the mnist dataset and my network recognizes them all correctly. But when i show this network my own handwritten digits in paint, it does not recognize them. I did everything from asking chatgpt to rewriting re doing changing params etc. My image has the exact same shape and looks identical but it just will not recognize my digits ... Looking at my code what is missing why are my digits not recognized if the networks works well? import cv2 import numpy as np import tensorflow as tf # My own data model = tf.keras.models.load_model("handwritten.model") img = cv2.imread("Dig