taki0112 / AdaBound-Tensorflow
Simple Tensorflow implementation of "Adaptive Gradient Methods with Dynamic Bound of Learning Rate" (ICLR 2019)
☆150Updated 5 years ago
Related projects ⓘ
Alternatives and complementary repositories for AdaBound-Tensorflow
- Simple Tensorflow implementation of "On the Convergence of Adam and Beyond" (ICLR 2018)☆104Updated 5 years ago
- Simple Tensorflow implementation of "On The Variance Of The Adaptive Learning Rate And Beyond"☆97Updated 4 years ago
- A memory efficient implementation of densenet.☆82Updated 4 years ago
- A TensorFlow implementation of Group Normalization on the task of image classification☆208Updated 6 years ago
- Unofficial implementation of Octave Convolutions (OctConv) in TensorFlow / Keras.☆100Updated 4 years ago
- Implementation of OctConv in Pytorch (https://arxiv.org/abs/1904.05049)☆213Updated 5 years ago
- Keras implementation of AdaBound☆130Updated 5 years ago
- TensorFlow implementation of PNASNet-5 on ImageNet☆102Updated 5 years ago
- Implementations of ideas from recent papers☆391Updated 3 years ago
- repo that holds code for improving on dropout using Stochastic Delta Rule☆142Updated 5 years ago
- Corrupted labels and label smoothing☆128Updated 7 years ago
- AdamW optimizer for Keras☆114Updated 5 years ago
- Using the CLR algorithm for training (https://arxiv.org/abs/1506.01186)☆108Updated 6 years ago
- Mish Deep Learning Activation Function for PyTorch / FastAI☆160Updated 4 years ago
- lookahead optimizer for keras☆170Updated 5 years ago
- PyTorch implementation of PNASNet-5 on ImageNet☆317Updated 2 years ago
- Efficient Data Loading Pipeline in Pure Python☆210Updated 4 years ago
- Code for reproducing results of the paper "Layer rotation: a surprisingly powerful indicator of generalization in deep networks?"☆50Updated 5 years ago
- A set of simple examples ported from PyTorch for Tensorflow Eager Execution☆73Updated 6 years ago
- Complementary code for the Targeted Dropout paper☆256Updated 5 years ago
- Use TensorFlow efficiently☆95Updated 3 years ago
- Implementation of Octave Convolution from Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convol…☆56Updated 5 years ago
- An optimizer that trains as fast as Adam and as good as SGD in Tensorflow☆45Updated 5 years ago
- Models and examples built with Chainer☆118Updated 2 years ago
- A simpler version of the self-attention layer from SAGAN, and some image classification results.☆211Updated 5 years ago
- pytorch model summary, statistic parameters number, memory usage, FLOPs and so on☆95Updated 4 years ago
- [ECCV 2018] Sparsely Aggreagated Convolutional Networks https://arxiv.org/abs/1801.05895☆125Updated 6 years ago
- Keras implementation of CoordConv for all Convolution layers☆148Updated 2 years ago
- TensorFlow implementations of Wasserstein GAN with Gradient Penalty (WGAN-GP), Least Squares GAN (LSGAN), GANs with the hinge loss.☆44Updated 5 years ago