wkcn / MobulaOP
A Simple & Flexible Cross Framework Operators Toolkit
☆164Updated 4 years ago
Alternatives and similar repositories for MobulaOP:
Users that are interested in MobulaOP are comparing it to the libraries listed below
- MXNet Gluon Synchronized Batch Normalization Preview☆77Updated 6 years ago
- A Computation Graph Virtual Machine based ML Framework☆108Updated 11 months ago
- Reproduction of MobileNetV2 using MXNet☆128Updated 5 years ago
- Single Path One-Shot NAS MXNet implementation with full training and searching pipeline. Support both Block and Channel Selection. Search…☆151Updated 4 years ago
- ☆45Updated 2 years ago
- Model shared. Top1:67.408/Top5:87.258☆48Updated 6 years ago
- A MXNet implementation of DenseNet(with BC structure)☆120Updated 7 years ago
- KnowledgeDistillation Layer (Caffe implementation)☆89Updated 7 years ago
- Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search☆150Updated 4 years ago
- [ICCV 2019] Harmonious Bottleneck on Two Orthogonal Dimensions, surpassing MobileNetV2☆102Updated 4 years ago
- Code and Pretrained model for IGCV3☆189Updated 6 years ago
- Benchmark of TVM quantized model on CUDA☆111Updated 4 years ago
- Reproduction of Focal-loss on caffe☆140Updated 7 years ago
- ResNet-18 Caffemodel @ilsvrc12 shrt 256 with Top-1 69% Top-5 89%☆191Updated 5 years ago
- train resnet on imagenet from scratch with caffe☆114Updated 9 months ago
- A code gallery for person re-identification with mxnet-gluon, and I will reproduce many STOA algorithm.☆176Updated 6 years ago
- ☆87Updated 6 years ago
- ☆134Updated 6 years ago
- A memory balanced and communication efficient FullyConnected layer with CrossEntropyLoss model parallel implementation in PyTorch☆85Updated 4 years ago
- ☆111Updated 7 years ago
- A caffe implementation of mobilenet's depthwise convolution layer.☆145Updated 7 years ago
- Code for our CVPR 2018 paper "Optimizing Video Object Detection via a Scale-Time Lattice".☆208Updated 6 years ago
- Simulate quantization and quantization aware training for MXNet-Gluon models.☆46Updated 4 years ago
- loss layer of implementation☆125Updated 7 years ago
- Caffe implementation of FAIR paper "Focal Loss for Dense Object Detection" for SSD.☆171Updated 7 years ago
- Synchronized Multi-GPU Batch Normalization☆67Updated 6 years ago
- Deformable Convolutional Networks on caffe☆160Updated 6 years ago
- Deformable Convolutional Networks☆160Updated 7 years ago
- Reproduce of CornerNet☆22Updated 5 years ago
- Diagonalwise Refactorization: An Efficient Training Method for Depthwise Convolutions (in Caffe)☆34Updated 7 years ago