onnx / onnx-caffe2
Caffe2 implementation of Open Neural Network Exchange (ONNX)
☆165Updated 6 years ago
Related projects: ⓘ
- ONNX model format support for Apache MXNet☆96Updated 5 years ago
- Original Python version of Intel® Nervana™ Graph☆215Updated last year
- neon tutorials☆93Updated last year
- Open single and half precision gemm implementations☆364Updated last year
- Benchmarking State-of-the-Art Deep Learning Software Tools☆170Updated 6 years ago
- Sublinear memory optimization for deep learning, reduce GPU memory cost to train deeper nets☆308Updated 7 years ago
- High Efficiency Convolution Kernel for Maxwell GPU Architecture☆134Updated 7 years ago
- ☆257Updated this week
- Binarized Neural Network TF training code + C matrix / eval library.☆98Updated 6 years ago
- ☆405Updated 5 years ago
- ☆73Updated this week
- ☆82Updated this week
- (New version is out: https://github.com/hpi-xnor/BMXNet-v2) BMXNet: An Open-Source Binary Neural Network Implementation Based on MXNet☆350Updated 4 years ago
- Demos interesting image-in, image-out networks running on both NVIDIA and AMD GPUs, with NNVM☆49Updated 6 years ago
- Spatially Adaptive Computation Time for Residual Networks☆246Updated last year
- THE Deep Learning Benchmarks☆352Updated 7 years ago
- ☆119Updated this week
- ☆94Updated this week
- neon model zoo☆176Updated last year
- Automatic Caffe parameter search via Spearmint Bayesian optimisation☆96Updated 8 years ago
- residual-SqueezeNet☆154Updated 5 years ago
- Tools to convert Caffe models to neon's serialization format☆39Updated last year
- mobilenet-mxnet☆145Updated 6 years ago
- Compress graph files for tensorflow.☆38Updated 7 years ago
- Basic library that can run networks created with Torch☆173Updated 4 years ago
- Caffe for Sparse Convolutional Neural Network☆238Updated last year
- MultiGPU enabled image generative models (GAN and DCGAN)☆209Updated 3 years ago
- Facebook's CUDA extensions.☆281Updated 5 years ago
- Boda: A C++ Framework for Efficient Experiments in Computer Vision☆63Updated 5 years ago