Hugging Face's logo

lrh12580
/
UvmPinAsync

Model card Files
xet
 Community
UvmPinAsync / workloads /realworld /output.log
lrh12580
first commit
5cb6c4b
raw
history blame contribute delete
20.5 kB
layer filters size input output
 0 conv 64 7 x 7 / 2 256 x 256 x 3 -> 128 x 128 x 64 0.308 BFLOPs
 1 max 2 x 2 / 2 128 x 128 x 64 -> 64 x 64 x 64
 2 conv 64 1 x 1 / 1 64 x 64 x 64 -> 64 x 64 x 64 0.034 BFLOPs
 3 conv 64 3 x 3 / 1 64 x 64 x 64 -> 64 x 64 x 64 0.302 BFLOPs
 4 conv 256 1 x 1 / 1 64 x 64 x 64 -> 64 x 64 x 256 0.134 BFLOPs
 5 res 1 64 x 64 x 64 -> 64 x 64 x 256
 6 conv 64 1 x 1 / 1 64 x 64 x 256 -> 64 x 64 x 64 0.134 BFLOPs
 7 conv 64 3 x 3 / 1 64 x 64 x 64 -> 64 x 64 x 64 0.302 BFLOPs
 8 conv 256 1 x 1 / 1 64 x 64 x 64 -> 64 x 64 x 256 0.134 BFLOPs
 9 res 5 64 x 64 x 256 -> 64 x 64 x 256
 10 conv 64 1 x 1 / 1 64 x 64 x 256 -> 64 x 64 x 64 0.134 BFLOPs
 11 conv 64 3 x 3 / 1 64 x 64 x 64 -> 64 x 64 x 64 0.302 BFLOPs
 12 conv 256 1 x 1 / 1 64 x 64 x 64 -> 64 x 64 x 256 0.134 BFLOPs
 13 res 9 64 x 64 x 256 -> 64 x 64 x 256
 14 conv 128 1 x 1 / 1 64 x 64 x 256 -> 64 x 64 x 128 0.268 BFLOPs
 15 conv 128 3 x 3 / 2 64 x 64 x 128 -> 32 x 32 x 128 0.302 BFLOPs
 16 conv 512 1 x 1 / 1 32 x 32 x 128 -> 32 x 32 x 512 0.134 BFLOPs
 17 res 13 64 x 64 x 256 -> 32 x 32 x 512
 18 conv 128 1 x 1 / 1 32 x 32 x 512 -> 32 x 32 x 128 0.134 BFLOPs
 19 conv 128 3 x 3 / 1 32 x 32 x 128 -> 32 x 32 x 128 0.302 BFLOPs
 20 conv 512 1 x 1 / 1 32 x 32 x 128 -> 32 x 32 x 512 0.134 BFLOPs
 21 res 17 32 x 32 x 512 -> 32 x 32 x 512
 22 conv 128 1 x 1 / 1 32 x 32 x 512 -> 32 x 32 x 128 0.134 BFLOPs
 23 conv 128 3 x 3 / 1 32 x 32 x 128 -> 32 x 32 x 128 0.302 BFLOPs
 24 conv 512 1 x 1 / 1 32 x 32 x 128 -> 32 x 32 x 512 0.134 BFLOPs
 25 res 21 32 x 32 x 512 -> 32 x 32 x 512
 26 conv 128 1 x 1 / 1 32 x 32 x 512 -> 32 x 32 x 128 0.134 BFLOPs
 27 conv 128 3 x 3 / 1 32 x 32 x 128 -> 32 x 32 x 128 0.302 BFLOPs
 28 conv 512 1 x 1 / 1 32 x 32 x 128 -> 32 x 32 x 512 0.134 BFLOPs
 29 res 25 32 x 32 x 512 -> 32 x 32 x 512
 30 conv 256 1 x 1 / 1 32 x 32 x 512 -> 32 x 32 x 256 0.268 BFLOPs
 31 conv 256 3 x 3 / 2 32 x 32 x 256 -> 16 x 16 x 256 0.302 BFLOPs
 32 conv 1024 1 x 1 / 1 16 x 16 x 256 -> 16 x 16 x1024 0.134 BFLOPs
 33 res 29 32 x 32 x 512 -> 16 x 16 x1024
 34 conv 256 1 x 1 / 1 16 x 16 x1024 -> 16 x 16 x 256 0.134 BFLOPs
 35 conv 256 3 x 3 / 1 16 x 16 x 256 -> 16 x 16 x 256 0.302 BFLOPs
 36 conv 1024 1 x 1 / 1 16 x 16 x 256 -> 16 x 16 x1024 0.134 BFLOPs
 37 res 33 16 x 16 x1024 -> 16 x 16 x1024
 38 conv 256 1 x 1 / 1 16 x 16 x1024 -> 16 x 16 x 256 0.134 BFLOPs
 39 conv 256 3 x 3 / 1 16 x 16 x 256 -> 16 x 16 x 256 0.302 BFLOPs
 40 conv 1024 1 x 1 / 1 16 x 16 x 256 -> 16 x 16 x1024 0.134 BFLOPs
 41 res 37 16 x 16 x1024 -> 16 x 16 x1024
 42 conv 256 1 x 1 / 1 16 x 16 x1024 -> 16 x 16 x 256 0.134 BFLOPs
 43 conv 256 3 x 3 / 1 16 x 16 x 256 -> 16 x 16 x 256 0.302 BFLOPs
 44 conv 1024 1 x 1 / 1 16 x 16 x 256 -> 16 x 16 x1024 0.134 BFLOPs
 45 res 41 16 x 16 x1024 -> 16 x 16 x1024
 46 conv 256 1 x 1 / 1 16 x 16 x1024 -> 16 x 16 x 256 0.134 BFLOPs
 47 conv 256 3 x 3 / 1 16 x 16 x 256 -> 16 x 16 x 256 0.302 BFLOPs
 48 conv 1024 1 x 1 / 1 16 x 16 x 256 -> 16 x 16 x1024 0.134 BFLOPs
 49 res 45 16 x 16 x1024 -> 16 x 16 x1024
 50 conv 256 1 x 1 / 1 16 x 16 x1024 -> 16 x 16 x 256 0.134 BFLOPs
 51 conv 256 3 x 3 / 1 16 x 16 x 256 -> 16 x 16 x 256 0.302 BFLOPs
 52 conv 1024 1 x 1 / 1 16 x 16 x 256 -> 16 x 16 x1024 0.134 BFLOPs
 53 res 49 16 x 16 x1024 -> 16 x 16 x1024
 54 conv 512 1 x 1 / 1 16 x 16 x1024 -> 16 x 16 x 512 0.268 BFLOPs
 55 conv 512 3 x 3 / 2 16 x 16 x 512 -> 8 x 8 x 512 0.302 BFLOPs
 56 conv 2048 1 x 1 / 1 8 x 8 x 512 -> 8 x 8 x2048 0.134 BFLOPs
 57 res 53 16 x 16 x1024 -> 8 x 8 x2048
 58 conv 512 1 x 1 / 1 8 x 8 x2048 -> 8 x 8 x 512 0.134 BFLOPs
 59 conv 512 3 x 3 / 1 8 x 8 x 512 -> 8 x 8 x 512 0.302 BFLOPs
 60 conv 2048 1 x 1 / 1 8 x 8 x 512 -> 8 x 8 x2048 0.134 BFLOPs
 61 res 57 8 x 8 x2048 -> 8 x 8 x2048
 62 conv 512 1 x 1 / 1 8 x 8 x2048 -> 8 x 8 x 512 0.134 BFLOPs
 63 conv 512 3 x 3 / 1 8 x 8 x 512 -> 8 x 8 x 512 0.302 BFLOPs
 64 conv 2048 1 x 1 / 1 8 x 8 x 512 -> 8 x 8 x2048 0.134 BFLOPs
 65 res 61 8 x 8 x2048 -> 8 x 8 x2048
 66 avg 8 x 8 x2048 -> 2048
 67 conv 1000 1 x 1 / 1 1 x 1 x2048 -> 1 x 1 x1000 0.004 BFLOPs
 68 softmax 1000
Loading weights from ../../../../../data/darknet/resnet50.weights...Done!
../data/dog.jpg: Predicted in 0.016876 seconds.
layer filters size input output
 0 conv 64 7 x 7 / 2 256 x 256 x 3 -> 128 x 128 x 64 0.308 BFLOPs
 1 max 2 x 2 / 2 128 x 128 x 64 -> 64 x 64 x 64
 2 conv 64 1 x 1 / 1 64 x 64 x 64 -> 64 x 64 x 64 0.034 BFLOPs
 3 conv 64 3 x 3 / 1 64 x 64 x 64 -> 64 x 64 x 64 0.302 BFLOPs
 4 conv 256 1 x 1 / 1 64 x 64 x 64 -> 64 x 64 x 256 0.134 BFLOPs
 5 res 1 64 x 64 x 64 -> 64 x 64 x 256
 6 conv 64 1 x 1 / 1 64 x 64 x 256 -> 64 x 64 x 64 0.134 BFLOPs
 7 conv 64 3 x 3 / 1 64 x 64 x 64 -> 64 x 64 x 64 0.302 BFLOPs
 8 conv 256 1 x 1 / 1 64 x 64 x 64 -> 64 x 64 x 256 0.134 BFLOPs
 9 res 5 64 x 64 x 256 -> 64 x 64 x 256
 10 conv 64 1 x 1 / 1 64 x 64 x 256 -> 64 x 64 x 64 0.134 BFLOPs
 11 conv 64 3 x 3 / 1 64 x 64 x 64 -> 64 x 64 x 64 0.302 BFLOPs
 12 conv 256 1 x 1 / 1 64 x 64 x 64 -> 64 x 64 x 256 0.134 BFLOPs
 13 res 9 64 x 64 x 256 -> 64 x 64 x 256
 14 conv 128 1 x 1 / 1 64 x 64 x 256 -> 64 x 64 x 128 0.268 BFLOPs
 15 conv 128 3 x 3 / 2 64 x 64 x 128 -> 32 x 32 x 128 0.302 BFLOPs
 16 conv 512 1 x 1 / 1 32 x 32 x 128 -> 32 x 32 x 512 0.134 BFLOPs
 17 res 13 64 x 64 x 256 -> 32 x 32 x 512
 18 conv 128 1 x 1 / 1 32 x 32 x 512 -> 32 x 32 x 128 0.134 BFLOPs
 19 conv 128 3 x 3 / 1 32 x 32 x 128 -> 32 x 32 x 128 0.302 BFLOPs
 20 conv 512 1 x 1 / 1 32 x 32 x 128 -> 32 x 32 x 512 0.134 BFLOPs
 21 res 17 32 x 32 x 512 -> 32 x 32 x 512
 22 conv 128 1 x 1 / 1 32 x 32 x 512 -> 32 x 32 x 128 0.134 BFLOPs
 23 conv 128 3 x 3 / 1 32 x 32 x 128 -> 32 x 32 x 128 0.302 BFLOPs
 24 conv 512 1 x 1 / 1 32 x 32 x 128 -> 32 x 32 x 512 0.134 BFLOPs
 25 res 21 32 x 32 x 512 -> 32 x 32 x 512
 26 conv 128 1 x 1 / 1 32 x 32 x 512 -> 32 x 32 x 128 0.134 BFLOPs
 27 conv 128 3 x 3 / 1 32 x 32 x 128 -> 32 x 32 x 128 0.302 BFLOPs
 28 conv 512 1 x 1 / 1 32 x 32 x 128 -> 32 x 32 x 512 0.134 BFLOPs
 29 res 25 32 x 32 x 512 -> 32 x 32 x 512
 30 conv 256 1 x 1 / 1 32 x 32 x 512 -> 32 x 32 x 256 0.268 BFLOPs
 31 conv 256 3 x 3 / 2 32 x 32 x 256 -> 16 x 16 x 256 0.302 BFLOPs
 32 conv 1024 1 x 1 / 1 16 x 16 x 256 -> 16 x 16 x1024 0.134 BFLOPs
 33 res 29 32 x 32 x 512 -> 16 x 16 x1024
 34 conv 256 1 x 1 / 1 16 x 16 x1024 -> 16 x 16 x 256 0.134 BFLOPs
 35 conv 256 3 x 3 / 1 16 x 16 x 256 -> 16 x 16 x 256 0.302 BFLOPs
 36 conv 1024 1 x 1 / 1 16 x 16 x 256 -> 16 x 16 x1024 0.134 BFLOPs
 37 res 33 16 x 16 x1024 -> 16 x 16 x1024
 38 conv 256 1 x 1 / 1 16 x 16 x1024 -> 16 x 16 x 256 0.134 BFLOPs
 39 conv 256 3 x 3 / 1 16 x 16 x 256 -> 16 x 16 x 256 0.302 BFLOPs
 40 conv 1024 1 x 1 / 1 16 x 16 x 256 -> 16 x 16 x1024 0.134 BFLOPs
 41 res 37 16 x 16 x1024 -> 16 x 16 x1024
 42 conv 256 1 x 1 / 1 16 x 16 x1024 -> 16 x 16 x 256 0.134 BFLOPs
 43 conv 256 3 x 3 / 1 16 x 16 x 256 -> 16 x 16 x 256 0.302 BFLOPs
 44 conv 1024 1 x 1 / 1 16 x 16 x 256 -> 16 x 16 x1024 0.134 BFLOPs
 45 res 41 16 x 16 x1024 -> 16 x 16 x1024
 46 conv 256 1 x 1 / 1 16 x 16 x1024 -> 16 x 16 x 256 0.134 BFLOPs
 47 conv 256 3 x 3 / 1 16 x 16 x 256 -> 16 x 16 x 256 0.302 BFLOPs
 48 conv 1024 1 x 1 / 1 16 x 16 x 256 -> 16 x 16 x1024 0.134 BFLOPs
 49 res 45 16 x 16 x1024 -> 16 x 16 x1024
 50 conv 256 1 x 1 / 1 16 x 16 x1024 -> 16 x 16 x 256 0.134 BFLOPs
 51 conv 256 3 x 3 / 1 16 x 16 x 256 -> 16 x 16 x 256 0.302 BFLOPs
 52 conv 1024 1 x 1 / 1 16 x 16 x 256 -> 16 x 16 x1024 0.134 BFLOPs
 53 res 49 16 x 16 x1024 -> 16 x 16 x1024
 54 conv 512 1 x 1 / 1 16 x 16 x1024 -> 16 x 16 x 512 0.268 BFLOPs
 55 conv 512 3 x 3 / 2 16 x 16 x 512 -> 8 x 8 x 512 0.302 BFLOPs
 56 conv 2048 1 x 1 / 1 8 x 8 x 512 -> 8 x 8 x2048 0.134 BFLOPs
 57 res 53 16 x 16 x1024 -> 8 x 8 x2048
 58 conv 512 1 x 1 / 1 8 x 8 x2048 -> 8 x 8 x 512 0.134 BFLOPs
 59 conv 512 3 x 3 / 1 8 x 8 x 512 -> 8 x 8 x 512 0.302 BFLOPs
 60 conv 2048 1 x 1 / 1 8 x 8 x 512 -> 8 x 8 x2048 0.134 BFLOPs
 61 res 57 8 x 8 x2048 -> 8 x 8 x2048
 62 conv 512 1 x 1 / 1 8 x 8 x2048 -> 8 x 8 x 512 0.134 BFLOPs
 63 conv 512 3 x 3 / 1 8 x 8 x 512 -> 8 x 8 x 512 0.302 BFLOPs
 64 conv 2048 1 x 1 / 1 8 x 8 x 512 -> 8 x 8 x2048 0.134 BFLOPs
 65 res 61 8 x 8 x2048 -> 8 x 8 x2048
 66 avg 8 x 8 x2048 -> 2048
 67 conv 1000 1 x 1 / 1 1 x 1 x2048 -> 1 x 1 x1000 0.004 BFLOPs
 68 softmax 1000
Loading weights from ../../../../../data/darknet/resnet50.weights...Done!
../data/dog.jpg: Predicted in 0.017422 seconds.
layer filters size input output
 0 conv 64 7 x 7 / 2 256 x 256 x 3 -> 128 x 128 x 64 0.308 BFLOPs
 1 max 2 x 2 / 2 128 x 128 x 64 -> 64 x 64 x 64
 2 conv 64 1 x 1 / 1 64 x 64 x 64 -> 64 x 64 x 64 0.034 BFLOPs
 3 conv 64 3 x 3 / 1 64 x 64 x 64 -> 64 x 64 x 64 0.302 BFLOPs
 4 conv 256 1 x 1 / 1 64 x 64 x 64 -> 64 x 64 x 256 0.134 BFLOPs
 5 res 1 64 x 64 x 64 -> 64 x 64 x 256
 6 conv 64 1 x 1 / 1 64 x 64 x 256 -> 64 x 64 x 64 0.134 BFLOPs
 7 conv 64 3 x 3 / 1 64 x 64 x 64 -> 64 x 64 x 64 0.302 BFLOPs
 8 conv 256 1 x 1 / 1 64 x 64 x 64 -> 64 x 64 x 256 0.134 BFLOPs
 9 res 5 64 x 64 x 256 -> 64 x 64 x 256
 10 conv 64 1 x 1 / 1 64 x 64 x 256 -> 64 x 64 x 64 0.134 BFLOPs
 11 conv 64 3 x 3 / 1 64 x 64 x 64 -> 64 x 64 x 64 0.302 BFLOPs
 12 conv 256 1 x 1 / 1 64 x 64 x 64 -> 64 x 64 x 256 0.134 BFLOPs
 13 res 9 64 x 64 x 256 -> 64 x 64 x 256
 14 conv 128 1 x 1 / 1 64 x 64 x 256 -> 64 x 64 x 128 0.268 BFLOPs
 15 conv 128 3 x 3 / 2 64 x 64 x 128 -> 32 x 32 x 128 0.302 BFLOPs
 16 conv 512 1 x 1 / 1 32 x 32 x 128 -> 32 x 32 x 512 0.134 BFLOPs
 17 res 13 64 x 64 x 256 -> 32 x 32 x 512
 18 conv 128 1 x 1 / 1 32 x 32 x 512 -> 32 x 32 x 128 0.134 BFLOPs
 19 conv 128 3 x 3 / 1 32 x 32 x 128 -> 32 x 32 x 128 0.302 BFLOPs
 20 conv 512 1 x 1 / 1 32 x 32 x 128 -> 32 x 32 x 512 0.134 BFLOPs
 21 res 17 32 x 32 x 512 -> 32 x 32 x 512
 22 conv 128 1 x 1 / 1 32 x 32 x 512 -> 32 x 32 x 128 0.134 BFLOPs
 23 conv 128 3 x 3 / 1 32 x 32 x 128 -> 32 x 32 x 128 0.302 BFLOPs
 24 conv 512 1 x 1 / 1 32 x 32 x 128 -> 32 x 32 x 512 0.134 BFLOPs
 25 res 21 32 x 32 x 512 -> 32 x 32 x 512
 26 conv 128 1 x 1 / 1 32 x 32 x 512 -> 32 x 32 x 128 0.134 BFLOPs
 27 conv 128 3 x 3 / 1 32 x 32 x 128 -> 32 x 32 x 128 0.302 BFLOPs
 28 conv 512 1 x 1 / 1 32 x 32 x 128 -> 32 x 32 x 512 0.134 BFLOPs
 29 res 25 32 x 32 x 512 -> 32 x 32 x 512
 30 conv 256 1 x 1 / 1 32 x 32 x 512 -> 32 x 32 x 256 0.268 BFLOPs
 31 conv 256 3 x 3 / 2 32 x 32 x 256 -> 16 x 16 x 256 0.302 BFLOPs
 32 conv 1024 1 x 1 / 1 16 x 16 x 256 -> 16 x 16 x1024 0.134 BFLOPs
 33 res 29 32 x 32 x 512 -> 16 x 16 x1024
 34 conv 256 1 x 1 / 1 16 x 16 x1024 -> 16 x 16 x 256 0.134 BFLOPs
 35 conv 256 3 x 3 / 1 16 x 16 x 256 -> 16 x 16 x 256 0.302 BFLOPs
 36 conv 1024 1 x 1 / 1 16 x 16 x 256 -> 16 x 16 x1024 0.134 BFLOPs
 37 res 33 16 x 16 x1024 -> 16 x 16 x1024
 38 conv 256 1 x 1 / 1 16 x 16 x1024 -> 16 x 16 x 256 0.134 BFLOPs
 39 conv 256 3 x 3 / 1 16 x 16 x 256 -> 16 x 16 x 256 0.302 BFLOPs
 40 conv 1024 1 x 1 / 1 16 x 16 x 256 -> 16 x 16 x1024 0.134 BFLOPs
 41 res 37 16 x 16 x1024 -> 16 x 16 x1024
 42 conv 256 1 x 1 / 1 16 x 16 x1024 -> 16 x 16 x 256 0.134 BFLOPs
 43 conv 256 3 x 3 / 1 16 x 16 x 256 -> 16 x 16 x 256 0.302 BFLOPs
 44 conv 1024 1 x 1 / 1 16 x 16 x 256 -> 16 x 16 x1024 0.134 BFLOPs
 45 res 41 16 x 16 x1024 -> 16 x 16 x1024
 46 conv 256 1 x 1 / 1 16 x 16 x1024 -> 16 x 16 x 256 0.134 BFLOPs
 47 conv 256 3 x 3 / 1 16 x 16 x 256 -> 16 x 16 x 256 0.302 BFLOPs
 48 conv 1024 1 x 1 / 1 16 x 16 x 256 -> 16 x 16 x1024 0.134 BFLOPs
 49 res 45 16 x 16 x1024 -> 16 x 16 x1024
 50 conv 256 1 x 1 / 1 16 x 16 x1024 -> 16 x 16 x 256 0.134 BFLOPs
 51 conv 256 3 x 3 / 1 16 x 16 x 256 -> 16 x 16 x 256 0.302 BFLOPs
 52 conv 1024 1 x 1 / 1 16 x 16 x 256 -> 16 x 16 x1024 0.134 BFLOPs
 53 res 49 16 x 16 x1024 -> 16 x 16 x1024
 54 conv 512 1 x 1 / 1 16 x 16 x1024 -> 16 x 16 x 512 0.268 BFLOPs
 55 conv 512 3 x 3 / 2 16 x 16 x 512 -> 8 x 8 x 512 0.302 BFLOPs
 56 conv 2048 1 x 1 / 1 8 x 8 x 512 -> 8 x 8 x2048 0.134 BFLOPs
 57 res 53 16 x 16 x1024 -> 8 x 8 x2048
 58 conv 512 1 x 1 / 1 8 x 8 x2048 -> 8 x 8 x 512 0.134 BFLOPs
 59 conv 512 3 x 3 / 1 8 x 8 x 512 -> 8 x 8 x 512 0.302 BFLOPs
 60 conv 2048 1 x 1 / 1 8 x 8 x 512 -> 8 x 8 x2048 0.134 BFLOPs
 61 res 57 8 x 8 x2048 -> 8 x 8 x2048
 62 conv 512 1 x 1 / 1 8 x 8 x2048 -> 8 x 8 x 512 0.134 BFLOPs
 63 conv 512 3 x 3 / 1 8 x 8 x 512 -> 8 x 8 x 512 0.302 BFLOPs
 64 conv 2048 1 x 1 / 1 8 x 8 x 512 -> 8 x 8 x2048 0.134 BFLOPs
 65 res 61 8 x 8 x2048 -> 8 x 8 x2048
 66 avg 8 x 8 x2048 -> 2048
 67 conv 1000 1 x 1 / 1 1 x 1 x2048 -> 1 x 1 x1000 0.004 BFLOPs
 68 softmax 1000
Loading weights from ../../../../../data/darknet/resnet50.weights...Done!
layer filters size input output
 0 conv 64 7 x 7 / 2 256 x 256 x 3 -> 128 x 128 x 64 0.308 BFLOPs
 1 max 2 x 2 / 2 128 x 128 x 64 -> 64 x 64 x 64
 2 conv 64 1 x 1 / 1 64 x 64 x 64 -> 64 x 64 x 64 0.034 BFLOPs
 3 conv 64 3 x 3 / 1 64 x 64 x 64 -> 64 x 64 x 64 0.302 BFLOPs
 4 conv 256 1 x 1 / 1 64 x 64 x 64 -> 64 x 64 x 256 0.134 BFLOPs
 5 res 1 64 x 64 x 64 -> 64 x 64 x 256
 6 conv 64 1 x 1 / 1 64 x 64 x 256 -> 64 x 64 x 64 0.134 BFLOPs
 7 conv 64 3 x 3 / 1 64 x 64 x 64 -> 64 x 64 x 64 0.302 BFLOPs
 8 conv 256 1 x 1 / 1 64 x 64 x 64 -> 64 x 64 x 256 0.134 BFLOPs
 9 res 5 64 x 64 x 256 -> 64 x 64 x 256
 10 conv 64 1 x 1 / 1 64 x 64 x 256 -> 64 x 64 x 64 0.134 BFLOPs
 11 conv 64 3 x 3 / 1 64 x 64 x 64 -> 64 x 64 x 64 0.302 BFLOPs
 12 conv 256 1 x 1 / 1 64 x 64 x 64 -> 64 x 64 x 256 0.134 BFLOPs
 13 res 9 64 x 64 x 256 -> 64 x 64 x 256
 14 conv 128 1 x 1 / 1 64 x 64 x 256 -> 64 x 64 x 128 0.268 BFLOPs
 15 conv 128 3 x 3 / 2 64 x 64 x 128 -> 32 x 32 x 128 0.302 BFLOPs
 16 conv 512 1 x 1 / 1 32 x 32 x 128 -> 32 x 32 x 512 0.134 BFLOPs
 17 res 13 64 x 64 x 256 -> 32 x 32 x 512
 18 conv 128 1 x 1 / 1 32 x 32 x 512 -> 32 x 32 x 128 0.134 BFLOPs
 19 conv 128 3 x 3 / 1 32 x 32 x 128 -> 32 x 32 x 128 0.302 BFLOPs
 20 conv 512 1 x 1 / 1 32 x 32 x 128 -> 32 x 32 x 512 0.134 BFLOPs
 21 res 17 32 x 32 x 512 -> 32 x 32 x 512
 22 conv 128 1 x 1 / 1 32 x 32 x 512 -> 32 x 32 x 128 0.134 BFLOPs
 23 conv 128 3 x 3 / 1 32 x 32 x 128 -> 32 x 32 x 128 0.302 BFLOPs
 24 conv 512 1 x 1 / 1 32 x 32 x 128 -> 32 x 32 x 512 0.134 BFLOPs
 25 res 21 32 x 32 x 512 -> 32 x 32 x 512
 26 conv 128 1 x 1 / 1 32 x 32 x 512 -> 32 x 32 x 128 0.134 BFLOPs
 27 conv 128 3 x 3 / 1 32 x 32 x 128 -> 32 x 32 x 128 0.302 BFLOPs
 28 conv 512 1 x 1 / 1 32 x 32 x 128 -> 32 x 32 x 512 0.134 BFLOPs
 29 res 25 32 x 32 x 512 -> 32 x 32 x 512
 30 conv 256 1 x 1 / 1 32 x 32 x 512 -> 32 x 32 x 256 0.268 BFLOPs
 31 conv 256 3 x 3 / 2 32 x 32 x 256 -> 16 x 16 x 256 0.302 BFLOPs
 32 conv 1024 1 x 1 / 1 16 x 16 x 256 -> 16 x 16 x1024 0.134 BFLOPs
 33 res 29 32 x 32 x 512 -> 16 x 16 x1024
 34 conv 256 1 x 1 / 1 16 x 16 x1024 -> 16 x 16 x 256 0.134 BFLOPs
 35 conv 256 3 x 3 / 1 16 x 16 x 256 -> 16 x 16 x 256 0.302 BFLOPs
 36 Traceback (most recent call last):
 File "run_real_all.py", line 646, in <module>
 main()
 File "run_real_all.py", line 638, in main
 result_dict = process_results(workload_dict, iterations)
 File "run_real_all.py", line 187, in process_results
 result_dict[para][workload][config].append(process_file(log_file, config))
 File "run_real_all.py", line 155, in process_file
 result_dict['allocation'] += int(words[3])
IndexError: list index out of range