torchstat
torchstat copied to clipboard
‘Total MAdd’ and 'Total Flops' results should exchange with each other
MAdd means that the multiply and add operations are counted as 1 operation while FLOPs count them as 2. Should the results of 'Total MAdd' and 'Total Flops' exchange with each other?
I have the same question. And why compute_flops need to multiply batch_size but compuute_MAdd didn't. I think there is no need to multiply batch_size, because we only consider one image situation. Is that right?
same question
same question
+1
+1
+1
+1
+1
Same question. I reimplement the SwiftNetRN-18 with the MXNet framework, resulting in over 200 GFLOPs of input size 1024*2048 that is similar to (May be) BUGs in paper: wrong Gflops #14
+1!!!! I think ‘Total MAdd’ and 'Total Flops' results should exchange with each other.
Same question
收到了!谢谢!