内容简介:Implementation of the estimation of model size and flop counts for convolutional neural networks.ref:The estimation of flops only consider layers: Convolution, Deconvolution, FullyConnected, Pooling, relu
MXNET-Python Tool For Calculate Flops And Model Size
Implementation of the estimation of model size and flop counts for convolutional neural networks.
ref: https://github.com/albanie/convnet-burden
The estimation of flops only consider layers: Convolution, Deconvolution, FullyConnected, Pooling, relu
Running
python calculateFlops.py -s symbols/caffenet-symbol.json -ds data,1,3,224,224 -ls prob_label,1,1000 ('flops: ', '723.007176', ' MFLOPS') ('model size: ', '232.563873291', ' MB') python calculateFlops.py -s symbols/squeezenet_v1.0-symbol.json -ds data,1,3,224,224 -ls prob_label,1,1000 ('flops: ', '861.603864', ' MFLOPS') ('model size: ', '4.76235961914', ' MB') python calculateFlops.py -s symbols/resnet-101-symbol.json -ds data,1,3,224,224 -ls softmax_label,1,1000 ('flops: ', '7818.240488', ' MFLOPS') ('model size: ', '169.912773132', ' MB') python calculateFlops.py -s symbols/resnext-101-64x4d-symbol.json -ds data,1,3,224,224 -ls softmax_label,1,1000 ('flops: ', '15491.88196', ' MFLOPS') ('model size: ', '318.356620789', ' MB') python calculateFlops.py -s symbols/fcn8s-symbol.json -ds data,1,3,384,384 -ls softmax_label,1,21,384,384 ('flops: ', '120420.573296', ' MFLOPS') ('model size: ', '513.037715912', ' MB') python calculateFlops.py -s symbols/fcn32s-symbol.json -ds data,1,3,384,384 -ls softmax_label,1,21,384,384 ('flops: ', '120265.786832', ' MFLOPS') ('model size: ', '519.382160187', ' MB')
以上就是本文的全部内容,希望本文的内容对大家的学习或者工作能带来一定的帮助,也希望大家多多支持 码农网
猜你喜欢:- MXNET-Scala 实现估算卷积神经网络浮点数运算量
- 卷积有多少种?一文读懂深度学习中的各种卷积
- ChannelNets: 省力又讨好的channel-wise卷积,在channel维度进行卷积滑动 | NIPS 2018
- 卷积神经网络介绍
- 卷积神经网络随记
- 数学小记之卷积
本站部分资源来源于网络,本站转载出于传递更多信息之目的,版权归原作者或者来源机构所有,如转载稿涉及版权问题,请联系我们。