There are 0 repository under flops topic.
Image Restoration Toolbox (PyTorch). Training and testing codes for DPIR, USRNet, DnCNN, FFDNet, SRMD, DPSR, BSRGAN, SwinIR
🛠 Toolbox to extend PyTorch functionalities
Estimate/count FLOPS for a given neural network using pytorch
A small OpenCL benchmark program to measure peak GPU/CPU performance.
Seamless analysis of your PyTorch models (RAM usage, FLOPs, MACs, receptive field, etc.)
AI and Memory Wall
A simple program to calculate and visualize the FLOPs and Parameters of Pytorch models, with handy CLI and easy-to-use Python API.
Easily benchmark PyTorch model FLOPs, latency, throughput, allocated gpu memory and energy consumption
Count number of parameters / MACs / FLOPS for ONNX models.
Profile PyTorch models for FLOPs and parameters, helping to evaluate computational efficiency and memory usage.
FLOPs calculator with tf.profiler for neural network architecture written in tensorflow 2.2+ (tf.keras)
A toolkit for scaling law research ⚖
【一个小工具】用最短的代码完成对模型的分析,包含 ImageNet Val、FLOPs、Params、Throuthput、CAM 等
各种算法评价指标的实现(mAP/Flops/params/fps/error-rate/accuracy)
FLOPs and other statistics COunter for tf.keras neural networks
Computing FLOPs with Intel Software Development Emulator (Intel SDE)
FLOPs and other statistics COunter for Pytorch neural networks
Discrete Flow Matching implemented in PyTorch
CPU Benchmarking Tool which calculates IOPS and FLOPS.
Dynamic Frame Interpolation in Wavelet Domain (TIP 2023)
MethodsCmp: A Simple Toolkit for Counting the FLOPs/MACs, Parameters and FPS of Pytorch-based Methods
Calculating FLOPs of Pre-trained Models in NLP
Utilities to perform deep learning models benchmarking (number of parameters, FLOPS and inference latency)
A general and accurate RAM / MACs / FLOPs profiler for ONNX models (Currently work-in-progress)
This repository contains various RGBD models and aims to provide a benchmark for evaluating their FLOPs, MACs, and the number of parameters. We will continue to add more functionalities in the future
PyTorch module FLOPS counter
Simple giga FLOPS measurement tool for ARM with NEON and Intel x86
Floppy is a Python framework for analyzing and counting floating-point operations (FLOPs).
Theoretical-practical study of the main numerical calculation methods used in scientific computing, focusing on the efficient implementation of these methods in serial computers and addressing code optimization techniques and resilience to numerical errors.