Pinned Repositories
autograd
Efficiently computes derivatives of numpy code.
autograd-1
coding an autograd from scratch
blocksparse
Efficient GPU kernels for block-sparse matrix multiplication and convolution
bolt
Bolt is a deep learning library with high performance and heterogeneous flexibility.
clDNN
Compute Library for Deep Neural Networks (clDNN)
CNN-Inference-Engine-Quick-View
A quick view of high-performance convolution neural networks (CNNs) inference engines on mobile devices.
distiller
Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller
Dual-Kawase-Blur
Qt implementation of Dual Kawase Blur using OpenGL
libsvm-3.0.extended.wdi
The original LibSVM Python version does not have the interface to computethe value of |w|^2, which can be used for computing the distance of a given sampletowards the hyperplane. We modified the C++ files and corresponding python functions, also re-built the dll file. The modified svm-model object contains the following additional attributes: w_2(|w|^2)+),rho, nSV(no of support vectors for each class), probA, probB. Please refer to readme.wdi file for detailed information.
warpuv's Repositories
warpuv/libsvm-3.0.extended.wdi
The original LibSVM Python version does not have the interface to computethe value of |w|^2, which can be used for computing the distance of a given sampletowards the hyperplane. We modified the C++ files and corresponding python functions, also re-built the dll file. The modified svm-model object contains the following additional attributes: w_2(|w|^2)+),rho, nSV(no of support vectors for each class), probA, probB. Please refer to readme.wdi file for detailed information.
warpuv/autograd
Efficiently computes derivatives of numpy code.
warpuv/autograd-1
coding an autograd from scratch
warpuv/blocksparse
Efficient GPU kernels for block-sparse matrix multiplication and convolution
warpuv/bolt
Bolt is a deep learning library with high performance and heterogeneous flexibility.
warpuv/clDNN
Compute Library for Deep Neural Networks (clDNN)
warpuv/CNN-Inference-Engine-Quick-View
A quick view of high-performance convolution neural networks (CNNs) inference engines on mobile devices.
warpuv/distiller
Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller
warpuv/Dual-Kawase-Blur
Qt implementation of Dual Kawase Blur using OpenGL
warpuv/EMA-VFI
[CVPR 2023] Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolatio
warpuv/graftr
graftr: an interactive shell to view and edit PyTorch checkpoints.
warpuv/LSQFakeQuantize-PyTorch
FakeQuantize with Learned Step Size(LSQ+) as Observer in PyTorch
warpuv/maxas
Assembler for NVIDIA Maxwell architecture
warpuv/onnx-modifier
A tool to modify onnx models in a visualization fashion, based on Netron and flask.
warpuv/EfficientDL
warpuv/onnx-utils
Utility scripts for editing or modifying onnx models. Utility scripts to summarize onnx model files along with visualization for loop operator body.
warpuv/onnx2pytorch
Transform ONNX model to PyTorch representation
warpuv/PyTorch_CIFAR10
Pretrained TorchVision models on CIFAR10 dataset (with weights)
warpuv/pytorch_compiler_tutorial
Codebase associated with the PyTorch compiler tutorial
warpuv/RCAN
PyTorch code for our ECCV 2018 paper "Image Super-Resolution Using Very Deep Residual Channel Attention Networks"
warpuv/Resnet-18_mindspore
Image classification done with Mindspore technology
warpuv/smoothquant
[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
warpuv/Support-Vector-Machines-Succinctly
warpuv/theorem_proving_in_lean4
warpuv/TorchIntegral
Integral Neural Networks in PyTorch