TomoyaKung / DLCourse_AS

Related projects: ⓘ

• han-cai / PathLevel-EAS
  Path-Level Network Transformation for Efficient Architecture Search, in ICML 2018.
  ☆113Updated 6 years ago
• wenwei202 / iss-rnns
  Sparse Recurrent Neural Networks -- Pruning Connections and Hidden Sizes (TensorFlow)
  ☆74Updated 4 years ago
• MycChiu / fast-LayerNorm-TF
  Efficient layer normalization GPU kernel for Tensorflow
  ☆111Updated 7 years ago
• qinyao-he / bit-rnn
  Quantize weights and activations in Recurrent Neural Networks.
  ☆95Updated 6 years ago
• yaroslavvb / memory_util
  TensorFlow util for building memory usage timeline from LOG_MEMORY messages
  ☆65Updated 6 years ago
• lrjconan / deep_parsimonious
  Learning Deep Parsimonious Representations, Deep Learning, Clustering, NIPS 2016
  ☆14Updated 4 years ago
• szha / mxnet-jit-batch
  Just-in-time Dynamic Batching with MXNet Gluon.
  ☆52Updated 4 years ago
• MatthieuCourbariaux / deep-learning-multipliers
  Training deep neural networks with low precision multiplications
  ☆63Updated 9 years ago
• guojunq / glsgan
  Generalized Loss-Sensitive Generative Adversarial Networks (GLS-GAN)
  ☆47Updated 7 years ago
• han-cai / EAS
  Efficient Architecture Search by Network Transformation, in AAAI 2018
  ☆170Updated 5 years ago
• eladhoffer / bigBatch
  Code used to generate the results appearing in "Train longer, generalize better: closing the generalization gap in large batch training o…
  ☆148Updated 7 years ago
• houlu369 / Loss-aware-Binarization
  Implementation of ICLR 2017 paper "Loss-aware Binarization of Deep Networks"
  ☆18Updated 5 years ago
• andrewliao11 / dni.pytorch
  Implement Decoupled Neural Interfaces using Synthetic Gradients in Pytorch
  ☆117Updated 6 years ago
• dlsys-course / assignment2-2017
  (Spring 2017) Assignment 2: GPU Executor
  ☆63Updated 7 years ago
• alykhantejani / nninit
  Weight initialization schemes for PyTorch nn.Modules
  ☆70Updated 7 years ago
• musyoku / chainer-sru
  Training RNNs as Fast as CNNs (Simple Recurrent Unit)
  ☆30Updated 6 years ago
• yuandong-tian / ICML17_ReLU
  ☆29Updated 7 years ago
• SkTim / bdfa-torch
  Training neural networks with back-prop, feedback-alignment and direct feedback-alignment
  ☆11Updated 7 years ago
• ottj / QuantizedRNN
  Recurrent Neural Networks With Limited Numerical Precision
  ☆11Updated 7 years ago
• Smerity / search_iclr_2018
  ☆78Updated 6 years ago
• zhuwenxi / pytorch-profiling-tool
  ☆51Updated 6 years ago
• lancopku / meProp
  meProp: Sparsified Back Propagation for Accelerated Deep Learning (ICML 2017)
  ☆110Updated 2 years ago
• zhijian-liu / onnx-profiler
  ☆13Updated this week
• jsuarez5341 / Efficient-Dynamic-Batching
  Solves AI, transcends reality, infiltrates your mind
  ☆36Updated 7 years ago
• anubhavashok / N2N
  ☆53Updated 5 years ago
• hwang595 / ps_pytorch
  implement distributed machine learning with Pytorch + OpenMPI
  ☆52Updated 5 years ago
• hantek / BinaryConnect
  Source code for ``Neural Networks with Few Multiplications'' published at ICLR 2016
  ☆81Updated 8 years ago
• guojunq / lsgan
  This is the project for LS-GAN (Loss-Sensitive GAN)
  ☆212Updated 7 years ago
• dhruvramani / Neural-Architecture-Search-with-RL
  Minimal Tensorflow implementation of the paper "Neural Architecture Search With Reinforcement Learning" presented at ICLR 2017
  ☆41Updated 6 years ago
• KarenUllrich / Tutorial-SoftWeightSharingForNNCompression
  A tutorial on 'Soft weight-sharing for Neural Network compression' published at ICLR2017
  ☆146Updated 7 years ago
• cc-hpc-itwm / TensorQuant
  ☆47Updated 4 years ago