HAR-stacked-residual-bidir-LSTMs in guillaume-chevalier/Awesome-Deep-Learning-Resources

Using deep stacked residual bidirectional LSTM cells (RNN) with TensorFlow, we do Human Activity Recognition (HAR). Classifying the type of movement amongst 6 categories or 18 categories on 2 different datasets.

created at Nov. 26, 2016, 2:41 p.m.

Python

19 +0

319 +0

100 +0

GitHub
Smoothly-Blend-Image-Patches in guillaume-chevalier/Awesome-Deep-Learning-Resources

Using a U-Net for image segmentation, blending predicted patches smoothly is a must to please the human eye.

created at Aug. 25, 2017, 8:33 p.m.

Python

3 +0

0 +0

1 +0

GitHub
Hyperopt-Keras-CNN-CIFAR-100 in guillaume-chevalier/Awesome-Deep-Learning-Resources

Auto-optimizing a neural net (and its architecture) on the CIFAR-100 dataset. Could be easily transferred to another dataset or another classification task.

created at May 27, 2017, 6:15 p.m.

Python

10 +0

106 +0

76 +0

GitHub