All Projects → frogermcs → MNIST-TFLite

frogermcs / MNIST-TFLite

Licence: MIT license
MNIST classifier built for TensorFlow Lite - Android, iOS and other "lite" platforms

Programming Languages

Jupyter Notebook
11667 projects
java
68154 projects - #9 most used programming language

Projects that are alternatives of or similar to MNIST-TFLite

Hand-Digits-Recognition
Recognize your own handwritten digits with Tensorflow, embedded in a PyQT5 GUI. The Neural Network was trained on MNIST.
Stars: ✭ 11 (-67.65%)
Mutual labels:  mnist
cDCGAN
PyTorch implementation of Conditional Deep Convolutional Generative Adversarial Networks (cDCGAN)
Stars: ✭ 49 (+44.12%)
Mutual labels:  mnist
MNIST
Handwritten digit recognizer using a feed-forward neural network and the MNIST dataset of 70,000 human-labeled handwritten digits.
Stars: ✭ 28 (-17.65%)
Mutual labels:  mnist
digit recognizer
CNN digit recognizer implemented in Keras Notebook, Kaggle/MNIST (0.995).
Stars: ✭ 27 (-20.59%)
Mutual labels:  mnist
cluttered-mnist
Experiments on cluttered mnist dataset with Tensorflow.
Stars: ✭ 20 (-41.18%)
Mutual labels:  mnist
LeNet-from-Scratch
Implementation of LeNet5 without any auto-differentiate tools or deep learning frameworks. Accuracy of 98.6% is achieved on MNIST dataset.
Stars: ✭ 22 (-35.29%)
Mutual labels:  mnist
tensorflow-mnist-AAE
Tensorflow implementation of adversarial auto-encoder for MNIST
Stars: ✭ 86 (+152.94%)
Mutual labels:  mnist
image-defect-detection-based-on-CNN
TensorBasicModel
Stars: ✭ 17 (-50%)
Mutual labels:  mnist
DCGAN-Pytorch
A Pytorch implementation of "Deep Convolutional Generative Adversarial Networks"
Stars: ✭ 23 (-32.35%)
Mutual labels:  mnist
playing with vae
Comparing FC VAE / FCN VAE / PCA / UMAP on MNIST / FMNIST
Stars: ✭ 53 (+55.88%)
Mutual labels:  mnist
pytorch-siamese-triplet
One-Shot Learning with Triplet CNNs in Pytorch
Stars: ✭ 74 (+117.65%)
Mutual labels:  mnist
tensorflow-mnist-MLP-batch normalization-weight initializers
MNIST classification using Multi-Layer Perceptron (MLP) with 2 hidden layers. Some weight-initializers and batch-normalization are implemented.
Stars: ✭ 49 (+44.12%)
Mutual labels:  mnist
fast-tsetlin-machine-with-mnist-demo
A fast Tsetlin Machine implementation employing bit-wise operators, with MNIST demo.
Stars: ✭ 58 (+70.59%)
Mutual labels:  mnist
catacomb
The simplest machine learning library for launching UIs, running evaluations, and comparing model performance.
Stars: ✭ 13 (-61.76%)
Mutual labels:  mnist
gradient-boosted-decision-tree
GBDT (Gradient Boosted Decision Tree: 勾配ブースティング) のpythonによる実装
Stars: ✭ 49 (+44.12%)
Mutual labels:  mnist
tensorflow-example
Tensorflow-example:使用MNIST训练模型,并识别手写数字图片
Stars: ✭ 26 (-23.53%)
Mutual labels:  mnist
BP-Network
Multi-Classification on dataset of MNIST
Stars: ✭ 72 (+111.76%)
Mutual labels:  mnist
PaperSynth
Handwritten text to synths!
Stars: ✭ 18 (-47.06%)
Mutual labels:  mnist
MNIST-adversarial-images
Create adversarial images to fool a MNIST classifier in TensorFlow
Stars: ✭ 13 (-61.76%)
Mutual labels:  mnist
digdet
A realtime digit OCR on the browser using Machine Learning
Stars: ✭ 22 (-35.29%)
Mutual labels:  mnist

MNIST-TFLite

TensorFlow 2.0 (alpha)

This respository contains Jupyter Notebook with the code running on TensorFlow 2.0 alpha. As this is not yet stable version, entire code may break in any moment. Notebook was created just for the Colaboratory environment. It requires some changes to make it working on Docker environment described in the blog post.

Open In Colab

TensorFlow 1.x

Open In Colab

Example TensorFlow Lite implementation of MNIST classifier. This project was created to show how to build the simplest Machine Learning model and use it in mobile app. For more details see:

Blog post: Mobile intelligence - TensorFlow Lite classification model in Android

Jupyter Notebook containing: model training, export and converstion to TensorFlow Lite.

Example video

MNIST classifier in Android app

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].