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! I have a puzzle that if you prune some filters in a specific layer, consequently you also need to prune channels in the next layer accordingly.But your codes just zerorize filters for each layer instead of considering the ordered relationship between two layers i.e. remove both filters in the ith layer and channels in the i+1th layer. Especially when the pruning process ends, if all targeted filters are pruned in the whole network, Error will be occured in the inference process, cause the reason overhead.
The text was updated successfully, but these errors were encountered:
oh got it. Filters pruned in the previous layer generate zero featuremaps in the next layer,thus there's no impact pruning the relative channels in the filters of next layer. 3ks
Hi! I have a puzzle that if you prune some filters in a specific layer, consequently you also need to prune channels in the next layer accordingly.But your codes just zerorize filters for each layer instead of considering the ordered relationship between two layers i.e. remove both filters in the ith layer and channels in the i+1th layer. Especially when the pruning process ends, if all targeted filters are pruned in the whole network, Error will be occured in the inference process, cause the reason overhead.
The text was updated successfully, but these errors were encountered: