handsomebrothers Goto Github PK

an-empirical-study-for-gan-metric-master

an-empirical-study-for-gan-metrics

awesome-gans

Awesome Generative Adversarial Networks with tensorflow

awesome-pytorch-chinese

【干货】史上最全的PyTorch学习资源汇总

bert-chinese-classification-task

bert中文分类实践

bert-classification-tutorial

callback2vec

cifar10_gan

sample GAN using cifar10 dataset

clustering-on-the-mnist-data

Comparisons between KMeans, PCA, LDA, t-SNE on the MNIST dataset

compare_gan

Compare GAN code.

crnn-keras

CRNN (CNN+RNN) for OCR using Keras / License Plate Recognition

defector

defect prediction using DBN generated semantic features by https://ece.uwaterloo.ca/~lintan/publications/deeplearn-icse16.pdf

fashion-mnist

A MNIST-like fashion product database. Benchmark :point_right:

gan

Generate images via a Generative Adversarial Network (GAN)

gan-1

Resources and Implementations of Generative Adversarial Nets: GAN, DCGAN, WGAN, CGAN, InfoGAN

gan-2

Generating Fake Images using CIFAR10 dataset for training

generative-models

Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.

generative_adversarial_networks_101

Keras implementations of Generative Adversarial Networks. GAN, DCGAN, CGAN, CCGAN, WGAN and LSGAN models with MNIST and CIFAR-10 datasets.

inception-score-pytorch

Inception Score for GANs in Pytorch

keras-1

Deep Learning for humans

keras-bert

Implementation of BERT that could load official pre-trained models for feature extraction and prediction

keras-gan

Keras implementations of Generative Adversarial Networks.

keras_text_cnn

kerasgan

A couple of simple GANs in Keras

license-plate-recognition

Detection of license plate and recognising the registration number

lstm-classification-pytorch

Text classification based on LSTM on R8 dataset for pytorch implementation

machinelearning

Basic Machine Learning and Deep Learning

mlnd

Udacity Machine Learning Nano Degree Courses

mnist-digit-recognizer-cnn-keras-99.66

Used the Dataset "MNIST Digit Recognizer" on Kaggle. Trained Convolutional Neural Networks on 42000 Training Images and predicted labels on 28000 Test Images with an Validation Accuracy of 99.52% and 99.66% on Kaggle Leaderboard.

models

Models and examples built with TensorFlow