https://github.com/veb-101/mnist-flask_app
Rendering a flask app for hand-written digits recognition.
https://github.com/veb-101/mnist-flask_app
flask keras-tensorflow mnist-handwriting-recognition python3
Last synced: about 1 month ago
JSON representation
Rendering a flask app for hand-written digits recognition.
- Host: GitHub
- URL: https://github.com/veb-101/mnist-flask_app
- Owner: veb-101
- License: unlicense
- Created: 2019-07-29T18:04:11.000Z (almost 7 years ago)
- Default Branch: master
- Last Pushed: 2023-05-01T20:35:22.000Z (about 3 years ago)
- Last Synced: 2025-09-13T01:30:05.779Z (10 months ago)
- Topics: flask, keras-tensorflow, mnist-handwriting-recognition, python3
- Language: HTML
- Homepage:
- Size: 13.6 MB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Classifying Hand-drawn Digits using Flask
---------
* Original Paper
* [Gradient Based learning applied to document Recognition](http://yann.lecun.com/exdb/publis/pdf/lecun-98.pdf)
* Learning Resources
1. [CS231N Convolutional Neural Networks](http://cs231n.github.io/convolutional-networks/)
2. [CS231N Visualizing what ConvNets learn](http://cs231n.github.io/understanding-cnn/)
3. [A Beginner's Guide To Understanding Convolutional Neural Networks](https://adeshpande3.github.io/adeshpande3.github.io/A-Beginner's-Guide-To-Understanding-Convolutional-Neural-Networks/)
4. [Machine Learning is Fun! Part 3: Deep Learning and Convolutional Neural Networks](https://medium.com/@ageitgey/machine-learning-is-fun-part-3-deep-learning-and-convolutional-neural-networks-f40359318721)
5. [Visualizing MNIST: An Exploration of Dimensionality Reduction - Chris Olag](https://colah.github.io/posts/2014-10-Visualizing-MNIST/)
* Code Resources
* [Convolutional Neural Network by Magnus Erik Hvass Pedersen](https://nbviewer.jupyter.org/github/Hvass-Labs/TensorFlow-Tutorials/blob/master/02_Convolutional_Neural_Network.ipynb)
* [keras repositoy](https://github.com/keras-team/keras/blob/master/examples/mnist_cnn.py)
* Deep Learning with Python - Francois Chollet
* Model Training Files (2 different models trained)
* (Basic) Initial -> [mnist-keras(colab)](https://colab.research.google.com/drive/1kJBrQ-jHNb9LLnbFKJAjp-MqZuGzbgor#forceEdit=true&offline=true&sandboxMode=true)
* (Augmented) Used for predictions -> [Mnist-data-augmented(colab)](https://colab.research.google.com/drive/1UJjljA9TBmA_YNhfxe4wn_CwfVFYgaUK#forceEdit=true&offline=true&sandboxMode=true)
* Run Online
* [repl.it](https://repl.it/@VaibhavSingh4/Classifying-hand-written-images)
* Inspired by
* [Sourav Johar's Doodle Classifier](https://github.com/SouravJohar/doodle-classifier)
#### Run Locally
1. Create a seperate python 3 environment.
2. Install the required packages
```python
pip install -r requirements.txt
```
3. Run from environment
```python
python server.py
```
##### Outputs
- Input
- Output
- Input
- Output
* ToDo
1. Remove scipy.misc.imresize deprecated warning.
(remove this line to view the warning)
```python
warnings.filterwarnings("ignore")
```
2. Do instant detection of number.
3. Create a better GUI.