bindog / pytorch-model-parallelLinks
A memory balanced and communication efficient FullyConnected layer with CrossEntropyLoss model parallel implementation in PyTorch
☆84Updated 5 years ago
Alternatives and similar repositories for pytorch-model-parallel
Users that are interested in pytorch-model-parallel are comparing it to the libraries listed below
Sorting:
- Single Path One-Shot NAS MXNet implementation with full training and searching pipeline. Support both Block and Channel Selection. Search…☆151Updated 5 years ago
- MoGA: Searching Beyond MobileNetV3☆227Updated 5 years ago
- [ICCV 2019] Harmonious Bottleneck on Two Orthogonal Dimensions, surpassing MobileNetV2☆102Updated 5 years ago
- Convert image folder to lmdb, adapted from Efficient-PyTorch☆69Updated 2 years ago
- ☆120Updated 5 years ago
- ☆136Updated 6 years ago
- CUDA implementation of NMS for PyTorch☆87Updated 5 years ago
- Synchronized Multi-GPU Batch Normalization☆67Updated 7 years ago
- ☆187Updated 4 years ago
- Accelerated Training for Massive Classification via Dynamic Class Selection (AAAI 2018, Oral)☆100Updated 5 years ago
- A package to make do Network Slimming a little easier☆48Updated 3 years ago
- ☆68Updated 6 years ago
- Code and model for the winner team 'trojans' in ICCV19-Lightweight Face Recognition Challenge☆128Updated 5 years ago
- Code for “Discrimination-aware-Channel-Pruning-for-Deep-Neural-Networks”☆183Updated 4 years ago
- ☆45Updated 6 years ago
- Pytorch Implementationg of “Learning Efficient Convolutional Networks through Network Slimming”☆77Updated 6 years ago
- Face Recognition Loss on Mnist, Pytorch implementation☆95Updated 4 years ago
- pytorch CircleLoss for Face recognition☆25Updated 5 years ago
- Caffe implementation of ICCV 2017 & TPAMI 2018 paper - ThiNet☆46Updated 7 years ago
- Apply the pruning strategy for MobileNet_v2☆52Updated 6 years ago
- official github for paper "CELEB-500K: A LARGE TRAINING DATASET FOR FACE RECOGNITION"☆87Updated 6 years ago
- Implement Towards Effective Low-bitwidth Convolutional Neural Networks☆41Updated 7 years ago
- 73.6% GhostNet 1.0x pre-trained model on ImageNet☆89Updated 5 years ago
- Codes of Centripetal SGD☆63Updated 3 years ago
- Bridging the gap Between Stability and Scalability in Neural Architecture Search☆142Updated 4 years ago
- ☆151Updated 5 years ago
- my customed caffe☆32Updated 6 years ago
- https://arxiv.org/abs/2005.10497☆73Updated 5 years ago
- An implementation of Support Vector Guided Softmax Loss for Face Recognition☆22Updated 6 years ago
- [ICLR 2020]: 'AtomNAS: Fine-Grained End-to-End Neural Architecture Search'☆222Updated 5 years ago