You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi. Thanks for your work. I am reading your paper and trying to reimplement, and I feel confused about some details.
You mentioned in your paper that the slimming ratio ρ∈[0.35 : 0.05 : 1.25], which have 18 paths.
However, in your code, there are only 14 paths ρ∈[0.35 : 0.05 : 1] as mentioned in
. And also, when conducting gate training, the gate function only has a 4-dimension output, meaning that there is only 4 paths and the slimming ratio is restricted to ρ∈[0.35 : 0.05 : 0.5].
Hi. Thanks for your work. I am reading your paper and trying to reimplement, and I feel confused about some details.
You mentioned in your paper that the slimming ratio ρ∈[0.35 : 0.05 : 1.25], which have 18 paths.
However, in your code, there are only 14 paths ρ∈[0.35 : 0.05 : 1] as mentioned in
DS-Net/dyn_slim/models/dyn_slim_net.py
Line 36 in 15cd303
. And also, when conducting gate training, the gate function only has a 4-dimension output, meaning that there is only 4 paths and the slimming ratio is restricted to ρ∈[0.35 : 0.05 : 0.5].
DS-Net/dyn_slim/models/dyn_slim_blocks.py
Line 204 in 15cd303
Why the dynamic path for larger network is not used?
The text was updated successfully, but these errors were encountered: