Created
January 5, 2018 16:48
-
-
Save lanpa/ce2f43c6e870ae2424ef1cc5c7cb4ab1 to your computer and use it in GitHub Desktop.
output
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
graph(%0 : Float(1, 3, 224, 224) | |
%1 : Float(64, 3, 11, 11) | |
%2 : Float(64) | |
%3 : Float(192, 64, 5, 5) | |
%4 : Float(192) | |
%5 : Float(384, 192, 3, 3) | |
%6 : Float(384) | |
%7 : Float(256, 384, 3, 3) | |
%8 : Float(256) | |
%9 : Float(256, 256, 3, 3) | |
%10 : Float(256) | |
%11 : Float(4096, 9216) | |
%12 : Float(4096) | |
%13 : Float(4096, 4096) | |
%14 : Float(4096) | |
%15 : Float(1000, 4096) | |
%16 : Float(1000)) { | |
%17 : Float(1, 64, 55, 55) = Conv[dilations=[1, 1], group=1, kernel_shape=[11, 11], pads=[2, 2, 2, 2], strides=[4, 4]](%0, %1, %2), scope: AlexNet/Sequential[features]/Conv2d[0] | |
%18 : Float(1, 64, 55, 55) = Relu(%17), scope: AlexNet/Sequential[features]/ReLU[1] | |
%19 : Float(1, 64, 27, 27) = MaxPool[kernel_shape=[3, 3], pads=[0, 0, 0, 0], strides=[2, 2]](%18), scope: AlexNet/Sequential[features]/MaxPool2d[2] | |
%20 : Float(1, 192, 27, 27) = Conv[dilations=[1, 1], group=1, kernel_shape=[5, 5], pads=[2, 2, 2, 2], strides=[1, 1]](%19, %3, %4), scope: AlexNet/Sequential[features]/Conv2d[3] | |
%21 : Float(1, 192, 27, 27) = Relu(%20), scope: AlexNet/Sequential[features]/ReLU[4] | |
%22 : Float(1, 192, 13, 13) = MaxPool[kernel_shape=[3, 3], pads=[0, 0, 0, 0], strides=[2, 2]](%21), scope: AlexNet/Sequential[features]/MaxPool2d[5] | |
%23 : Float(1, 384, 13, 13) = Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1]](%22, %5, %6), scope: AlexNet/Sequential[features]/Conv2d[6] | |
%24 : Float(1, 384, 13, 13) = Relu(%23), scope: AlexNet/Sequential[features]/ReLU[7] | |
%25 : Float(1, 256, 13, 13) = Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1]](%24, %7, %8), scope: AlexNet/Sequential[features]/Conv2d[8] | |
%26 : Float(1, 256, 13, 13) = Relu(%25), scope: AlexNet/Sequential[features]/ReLU[9] | |
%27 : Float(1, 256, 13, 13) = Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1]](%26, %9, %10), scope: AlexNet/Sequential[features]/Conv2d[10] | |
%28 : Float(1, 256, 13, 13) = Relu(%27), scope: AlexNet/Sequential[features]/ReLU[11] | |
%29 : Float(1, 256, 6, 6) = MaxPool[kernel_shape=[3, 3], pads=[0, 0, 0, 0], strides=[2, 2]](%28), scope: AlexNet/Sequential[features]/MaxPool2d[12] | |
%30 : Float(1, 9216) = Flatten[axis=1](%29), scope: AlexNet | |
%31 : Float(1, 9216), %32 : UNKNOWN_TYPE = Dropout[is_test=1, ratio=0.5](%30), scope: AlexNet | |
%33 : Float(1, 4096) = Gemm[alpha=1, beta=1, broadcast=1, transB=1](%31, %11, %12), scope: AlexNet/Linear[fc1] | |
%34 : Float(1, 4096) = Relu(%33), scope: AlexNet/ReLU[relu1] | |
%35 : Float(1, 4096), %36 : UNKNOWN_TYPE = Dropout[is_test=1, ratio=0.5](%34), scope: AlexNet | |
%37 : Float(1, 4096) = Gemm[alpha=1, beta=1, broadcast=1, transB=1](%35, %13, %14), scope: AlexNet/Linear[fc2] | |
%38 : Float(1, 4096) = Relu(%37), scope: AlexNet/ReLU[relu2] | |
%39 : Float(1, 1000) = Gemm[alpha=1, beta=1, broadcast=1, transB=1](%38, %15, %16), scope: AlexNet/Linear[fc3] | |
return (%39); | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment