计算FLOPs相关

[aoaforever]

您好！我有两个问题需要请教：

1. 请问代码里为什么需要除以sum(num_ress) ?
2. 为什么对FRCNN网络的flops还需要加上7.4 ?
   期待您的解答，谢谢！！

def cal_FLOPs(which_model,num_ress):
    if which_model =='classSR_3class_fsrcnn_net':
        flops = ((141 * num_ress[0] + 304 * num_ress[1] + 468 * num_ress[2]) / sum(num_ress))+7.4
        percent=flops/468
    elif which_model=='classSR_3class_carn':
        flops = (0.38 * num_ress[0] + 0.77 * num_ress[1] + 1.15 * num_ress[2]) / sum(num_ress)
        percent = flops / 1.15
    elif which_model=='classSR_3class_srresnet':
        flops = (1.66 * num_ress[0] + 3.44 * num_ress[1] + 5.20 * num_ress[2]) / sum(num_ress)
        percent = flops / 5.20
    elif which_model=='classSR_3class_rcan':
        flops = (10.33 * num_ress[0] + 19.90 * num_ress[1] + 32.60 * num_ress[2]) / sum(num_ress)
        percent = flops / 32.60
    return flops,percent

[Xiangtaokong]

1.除总patch数目，算平均的flops 2.加的是分类器的计算量。后面几个模型比分类器大太多，基本算着没影响，就没加

…

---原始邮件--- 发件人: ***@***.***> 发送时间: 2022年10月17日(周一) 晚上9:54 收件人: ***@***.***>; 抄送: ***@***.***>; 主题: [XPixelGroup/ClassSR] 计算FLOPs相关 (Issue #50) 您好！我有两个问题需要请教： 请问代码里为什么需要除以sum(num_ress) ? 为什么对FRCNN网络的flops还需要加上7.4 ? 期待您的解答，谢谢！！ def cal_FLOPs(which_model,num_ress): if which_model =='classSR_3class_fsrcnn_net': flops = ((141 * num_ress[0] + 304 * num_ress[1] + 468 * num_ress[2]) / sum(num_ress))+7.4 percent=flops/468 elif which_model=='classSR_3class_carn': flops = (0.38 * num_ress[0] + 0.77 * num_ress[1] + 1.15 * num_ress[2]) / sum(num_ress) percent = flops / 1.15 elif which_model=='classSR_3class_srresnet': flops = (1.66 * num_ress[0] + 3.44 * num_ress[1] + 5.20 * num_ress[2]) / sum(num_ress) percent = flops / 5.20 elif which_model=='classSR_3class_rcan': flops = (10.33 * num_ress[0] + 19.90 * num_ress[1] + 32.60 * num_ress[2]) / sum(num_ress) percent = flops / 32.60 return flops,percent — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>