微信公众号数字识别

Learning with Signatures

Experiments on cluttered mnist dataset with Tensorflow.

Derin Öğrenme kullanarak el yazısıyla yazılmış rakamları tanımak için yazılmış bir Flask uygulamasıdır.

Learning deep learning 😎 and neuroevolution 👾 ⭐

Kakiburi is a dataset of computer generated japanese characters (60x60 grayscale, 382,878 images).

MNIST demo with canvas hand-written digit

Draw random shape on HTML5 canvas and let Deep ConvNet predict it.

python | deep learning | neural networks

Canvas to JSON, using Tensorflow & MNIST to predict digit

Holds code written for MATH 384: Algorithms for Decision-Making at St. Olaf College

Django + DRF + JavaScript (Angular or React) + Machine Learning + Anaconda

Neural network classifier to classify fashion MNIST from scratch. All the calculation are done using NumPy library.

Generative Adverserial Network for face generation using Tensorflow and DCGAN architecture

Using generative adversarial networks to generate new images of faces (datasets: MNIST, CelebA).

Generazione di Immagini Avversariali in Tensorflow

🔮😎 Keras mnist model served through a serverless endpoint

Project 2: Udacity Deep Learning Image classification

Leveraging the mapreduce paradigm we propose a solution to parallelize the feedforward operation of neural networks in order to speed it up for sufficiently large NN architectures and for sufficiently large datasets. Tested Using the MNIST dataset results can be found in the results.html and results.ipynb files.

Use GANs with normalization techniques like dropouts, batch normalization along with having a low variance in kernel weight initialization, achieve realistic images of faces trained on the CelebA dataset. Images also have been generated of hand written digits after being trained on the MNIST dataset. This would be useful for generating training …