convnet burden

We have hosted the application convnet burden in order to run this application in our online workstations with Wine or directly.

Quick description about convnet burden:

convnet-burden is a MATLAB toolbox / script collection estimating computational cost (FLOPs) and memory consumption of various convolutional neural network architectures. It lets users compute approximate burdens (in FLOPs, memory) for standard image classification CNN models (e.g. ResNet, VGG) based on network definitions. The tool helps researchers compare the computational efficiency of architectures or quantify resource needs. Estimation of memory consumption (e.g. feature map sizes, parameter storage). Support for multiple network definitions/architectures. Estimation of memory consumption (e.g. feature map sizes, parameter storage). Estimation of FLOPs (floating point operations) for CNN architectures.

Features:

• Estimation of FLOPs (floating point operations) for CNN architectures
• Setup scripts / comparisons across architectures
• Estimation of memory consumption (e.g. feature map sizes, parameter storage)
• Support for multiple network definitions / architectures
• MATLAB code interface (compute_burdens.m)
• Setup scripts / comparisons across architectures

Programming Language: MATLAB.
Categories: