检查 Flux.jl 模型中的参数总数？答案

【问题标题】：Check the total number of parameters in a Flux.jl Model?检查 Flux.jl 模型中的参数总数？
【发布时间】：2021-06-27 13:47:23
【问题描述】：

我知道使用 Flux.jl 我可以通过 julia> Flux.params(model) 获取参数，但输出并没有告诉我模型本身中实际存在多少总参数。是否有检查这个的函数或计算这个的编程方式？

【问题讨论】：

sum(length, params(model))
谢谢！是否可以查看每层的细分？我想我可以遍历模型层并执行sum(length, params(model[4]))?另外，请随时转换为答案，我会接受。

标签： julia flux.jl

【解决方案1】：

正如@mcabbott 在评论中提到的，您可以将整个模型传递给 params 函数以获取总计数 (sum(length, params(model))) 或循环遍历每一层，如下所示：

julia> model = Chain(
         resnet[1:end-2],
         Dense(2048, 1000),  
         Dense(1000, 256),
         Dense(256, 2),        # we get 2048 features out, and we have 2 classes
       )
Chain(Chain(Conv((7, 7), 3=>64), MaxPool((3, 3), pad=1, stride=2), Metalhead.ResidualBlock((Conv((1, 1), 64=>64), Conv((3, 3), 64=>64), Conv((1, 1), 64=>256)), (BatchNorm(64), BatchNorm(64), BatchNorm(256)), Chain(Conv((1, 1), 64=>256), BatchNorm(256))), Metalhead.ResidualBlock((Conv((1, 1), 256=>64), Conv((3, 3), 64=>64), Conv((1, 1), 64=>256)), (BatchNorm(64), BatchNorm(64), BatchNorm(256)), identity), Metalhead.ResidualBlock((Conv((1, 1), 256=>64), Conv((3, 3), 64=>64), Conv((1, 1), 64=>256)), (BatchNorm(64), BatchNorm(64), BatchNorm(256)), identity), Metalhead.ResidualBlock((Conv((1, 1), 256=>128), Conv((3, 3), 128=>128), Conv((1, 1), 128=>512)), (BatchNorm(128), BatchNorm(128), BatchNorm(512)), Chain(Conv((1, 1), 256=>512), BatchNorm(512))), Metalhead.ResidualBlock((Conv((1, 1), 512=>128), Conv((3, 3), 128=>128), Conv((1, 1), 128=>512)), (BatchNorm(128), BatchNorm(128), BatchNorm(512)), identity), Metalhead.ResidualBlock((Conv((1, 1), 512=>128), Conv((3, 3), 128=>128), Conv((1, 1), 128=>512)), (BatchNorm(128), BatchNorm(128), BatchNorm(512)), identity), Metalhead.ResidualBlock((Conv((1, 1), 512=>128), Conv((3, 3), 128=>128), Conv((1, 1), 128=>512)), (BatchNorm(128), BatchNorm(128), BatchNorm(512)), identity), Metalhead.ResidualBlock((Conv((1, 1), 512=>256), Conv((3, 3), 256=>256), Conv((1, 1), 256=>1024)), (BatchNorm(256), BatchNorm(256), BatchNorm(1024)), Chain(Conv((1, 1), 512=>1024), BatchNorm(1024))), Metalhead.ResidualBlock((Conv((1, 1), 1024=>256), Conv((3, 3), 256=>256), Conv((1, 1), 256=>1024)), (BatchNorm(256), BatchNorm(256), BatchNorm(1024)), identity), Metalhead.ResidualBlock((Conv((1, 1), 1024=>256), Conv((3, 3), 256=>256), Conv((1, 1), 256=>1024)), (BatchNorm(256), BatchNorm(256), BatchNorm(1024)), identity), Metalhead.ResidualBlock((Conv((1, 1), 1024=>256), Conv((3, 3), 256=>256), Conv((1, 1), 256=>1024)), (BatchNorm(256), BatchNorm(256), BatchNorm(1024)), identity), Metalhead.ResidualBlock((Conv((1, 1), 1024=>256), Conv((3, 3), 256=>256), Conv((1, 1), 256=>1024)), (BatchNorm(256), BatchNorm(256), BatchNorm(1024)), identity), Metalhead.ResidualBlock((Conv((1, 1), 1024=>256), Conv((3, 3), 256=>256), Conv((1, 1), 256=>1024)), (BatchNorm(256), BatchNorm(256), BatchNorm(1024)), identity), Metalhead.ResidualBlock((Conv((1, 1), 1024=>512), Conv((3, 3), 512=>512), Conv((1, 1), 512=>2048)), (BatchNorm(512), BatchNorm(512), BatchNorm(2048)), Chain(Conv((1, 1), 1024=>2048), BatchNorm(2048))), Metalhead.ResidualBlock((Conv((1, 1), 2048=>512), Conv((3, 3), 512=>512), Conv((1, 1), 512=>2048)), (BatchNorm(512), BatchNorm(512), BatchNorm(2048)), identity), Metalhead.ResidualBlock((Conv((1, 1), 2048=>512), Conv((3, 3), 512=>512), Conv((1, 1), 512=>2048)), (BatchNorm(512), BatchNorm(512), BatchNorm(2048)), identity), MeanPool((7, 7)), #103), Dense(2048, 1000), Dense(1000, 256), Dense(256, 2))

julia> paramCount = 0
0

julia> for layer in model
           paramCount += sum(length, params(layer))
       end

julia> paramCount
25840234

在此示例中，我只是增加计数，但您可以将每个层的计数附加到一个数组中，例如单独跟踪每个层的计数。

【讨论】：