[{"createTime":1735734952000,"id":1,"img":"hwy_ms_500_252.jpeg","link":"https://activity.huaweicloud.com/cps.html?fromacct=261f35b6-af54-4511-a2ca-910fa15905d1&utm_source=V1g3MDY4NTY=&utm_medium=cps&utm_campaign=201905","name":"华为云秒杀","status":9,"txt":"华为云38元秒杀","type":1,"updateTime":1735747411000,"userId":3},{"createTime":1736173885000,"id":2,"img":"txy_480_300.png","link":"https://cloud.tencent.com/act/cps/redirect?redirect=1077&cps_key=edb15096bfff75effaaa8c8bb66138bd&from=console","name":"腾讯云秒杀","status":9,"txt":"腾讯云限量秒杀","type":1,"updateTime":1736173885000,"userId":3},{"createTime":1736177492000,"id":3,"img":"aly_251_140.png","link":"https://www.aliyun.com/minisite/goods?userCode=pwp8kmv3","memo":"","name":"阿里云","status":9,"txt":"阿里云2折起","type":1,"updateTime":1736177492000,"userId":3},{"createTime":1735660800000,"id":4,"img":"vultr_560_300.png","link":"https://www.vultr.com/?ref=9603742-8H","name":"Vultr","status":9,"txt":"Vultr送$100","type":1,"updateTime":1735660800000,"userId":3},{"createTime":1735660800000,"id":5,"img":"jdy_663_320.jpg","link":"https://3.cn/2ay1-e5t","name":"京东云","status":9,"txt":"京东云特惠专区","type":1,"updateTime":1735660800000,"userId":3},{"createTime":1735660800000,"id":6,"img":"new_ads.png","link":"https://www.iodraw.com/ads","name":"发布广告","status":9,"txt":"发布广告","type":1,"updateTime":1735660800000,"userId":3},{"createTime":1735660800000,"id":7,"img":"yun_910_50.png","link":"https://activity.huaweicloud.com/discount_area_v5/index.html?fromacct=261f35b6-af54-4511-a2ca-910fa15905d1&utm_source=aXhpYW95YW5nOA===&utm_medium=cps&utm_campaign=201905","name":"底部","status":9,"txt":"高性能云服务器2折起","type":2,"updateTime":1735660800000,"userId":3}]
<>计算网络模型参数总量
<>方法1:pytorch自带方法,计算模型参数总量
total = sum([param.nelement() for param in model.parameters()])
print(“Number of parameter: %.2fM” % (total/1e6))
例子:
红色断点放到下一行,并用debug运行。结果为:
<>方法2:用工具包thop
要安装:pip install thop
在程序里输入:
from thop import profile
from thop import clever_format
input1 = torch.randn(1,1, 16,16)
input2 = torch.randn(1,1, 16,16)
input3 = torch.randn(1,1, 16,16)
flops, params = profile(model, inputs=(input1,input2,input2 ))
print(flops, params) # 1819066368.0 11689512.0
flops, params = clever_format([flops, params], “%.3f”)
print(flops, params) # 1.819G 11.690M
例如:
红色断点放到下一行,并用debug运行。结果为:
3.642M和 7.265K 分别代表FLOPs和参数量。
<>方法3:用torchstat
和thop一样,要安装包:pip install torchstat
但torchstat貌似只能测试一个输入的,像thop一样多输入的不行。torchstat 详细展示网络各层的参数,计算量,内存读写等等。
在程序里输入:
from torchstat import stat
stat(model, (1, 16, 16))
例如:
红色断点放到下一行,并用debug运行。结果为:
备注:例子里面(16,16)指的是图片的宽和长。
<>小结
以上三种方式,计算的结果会有些许差异,但是不会差太多。
方法1不需要另外装包。但只能计算模型的参数量。方法2和方法3需要额外安装包,不过这个包不难装,我用pip 清华源一次装好。
方法2可以适合单输入和多输入的模型。
方法3貌似只适合但输入的模型。方法3有层间的分析。