EfficientNet B0-B7 网络参数：

EfficientNet-B0 网络参数

STEM_W = 32
STRIDES = [1, 2, 2, 2, 1, 2, 1]
DEPTHS = [1, 2, 2, 3, 3, 4, 1]
WIDTHS = [16, 24, 40, 80, 112, 192, 320]
EXP_RATIOS = [1, 6, 6, 6, 6, 6, 6]
KERNELS = [3, 3, 5, 3, 5, 5, 3]
HEAD_W = 1280

EfficientNet-B1 网络参数

STEM_W = 32
STRIDES = [1, 2, 2, 2, 1, 2, 1]
DEPTHS = [2, 3, 3, 4, 4, 5, 2]   
WIDTHS = [16, 24, 40, 80, 112, 192, 320]  
EXP_RATIOS = [1, 6, 6, 6, 6, 6, 6]
KERNELS = [3, 3, 5, 3, 5, 5, 3]
HEAD_W = 1280

EfficientNet-B2 网络参数

STEM_W = 32                                 #开始通道数
STRIDES = [1, 2, 2, 2, 1, 2, 1]             #步长
DEPTHS = [2, 3, 3, 4, 4, 5, 2]              #网络层数
WIDTHS = [16, 24, 48, 88, 120, 208, 352]    #通道数
EXP_RATIOS = [1, 6, 6, 6, 6, 6, 6]          #系数
KERNELS = [3, 3, 5, 3, 5, 5, 3]             #卷积核大小
HEAD_W = 1408

EfficientNet-B3 网络参数

STEM_W = 40
STRIDES = [1, 2, 2, 2, 1, 2, 1]
DEPTHS = [2, 3, 3, 5, 5, 6, 2]
WIDTHS = [24, 32, 48, 96, 136, 232, 384]
EXP_RATIOS = [1, 6, 6, 6, 6, 6, 6]
KERNELS = [3, 3, 5, 3, 5, 5, 3]
HEAD_W = 1536

EfficientNet-B4 网络参数

STEM_W = 48
STRIDES = [1, 2, 2, 2, 1, 2, 1]
DEPTHS = [2, 4, 4, 6, 6, 8, 2]
WIDTHS = [24, 32, 56, 112, 160, 272, 448]
EXP_RATIOS = [1, 6, 6, 6, 6, 6, 6]
KERNELS = [3, 3, 5, 3, 5, 5, 3]
HEAD_W = 1792

EfficientNet-B5 网络参数

STEM_W = 48
STRIDES = [1, 2, 2, 2, 1, 2, 1]
DEPTHS = [3, 5, 5, 7, 7, 9, 3]
WIDTHS = [24, 40, 64, 128, 176, 304, 512]
EXP_RATIOS = [1, 6, 6, 6, 6, 6, 6]
KERNELS = [3, 3, 5, 3, 5, 5, 3]
HEAD_W = 2048

EfficientNet-B6 网络参数

STEM_W = 56
STRIDES = [1, 2, 2, 2, 1, 2, 1]
DEPTHS = [3, 6, 6, 8, 8, 11, 3]
WIDTHS = [32, 40, 72, 144, 200, 344, 576]
EXP_RATIOS = [1, 6, 6, 6, 6, 6, 6]
KERNELS = [3, 3, 5, 3, 5, 5, 3]
HEAD_W = 2304

EfficientNet-B7 网络参数

STEM_W = 64
STRIDES = [1, 2, 2, 2, 1, 2, 1]
DEPTHS = [4, 7, 7, 10, 10, 13, 4]
WIDTHS = [32, 48, 80, 160, 224, 384, 640]
EXP_RATIOS = [1, 6, 6, 6, 6, 6, 6]
KERNELS = [3, 3, 5, 3, 5, 5, 3]
HEAD_W = 2560

仅用于学习，如有侵权，请告知。
参考链接：
https://update.blog.csdn.net/article/details/108590020
https://zhuanlan.zhihu.com/p/258386372