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
Can you reshape the responding kernels after channel pruning, the convolutional cores is full of zero but can not reduce the computation in the tflite which i think could be completely removed
#203
Closed
Anonymity2022 opened this issue
Jan 21, 2019
· 1 comment
Is your feature request related to a problem? Please describe.
A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
Describe the solution you'd like
A clear and concise description of what you want to happen.
Describe alternatives you've considered
A clear and concise description of any alternative solutions or features you've considered.
Additional context
Add any other context or screenshots about the feature request here.
The text was updated successfully, but these errors were encountered:
Directly reshaping the convolutional kernel after pruning is more complicated, since you need to consider all the BN/ReLU/Pooling layers before and after this convolutional layer, and adjust their input (or output) tensors' shape. We have not found out an elegant way to do so. If you have experience in this, we highly welcome your contribution, e.g. propose a pull request.
Is your feature request related to a problem? Please describe.
A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
Describe the solution you'd like
A clear and concise description of what you want to happen.
Describe alternatives you've considered
A clear and concise description of any alternative solutions or features you've considered.
Additional context
Add any other context or screenshots about the feature request here.
The text was updated successfully, but these errors were encountered: