TinyNeuralNetwork icon indicating copy to clipboard operation
TinyNeuralNetwork copied to clipboard

oneshotpruner fails when possible channel padding exists

Open liamsun2019 opened this issue 3 years ago • 2 comments

Hi author,

For a certain model, oneshotpruner fails when there's channel padding with following error message:

ERROR (tinynn.graph.modifier) All node's sparsity in one subgraph must be the same

Please let me know if you need the model description file. Thanks.

liamsun2019 avatar May 17 '22 07:05 liamsun2019

This problem is difficult to solve in the current pruning architecture, in two to three weeks we will release a new pruning architecture that will fix this problem.

dinghuanghao avatar May 17 '22 09:05 dinghuanghao

Big thanks. Wait for your fix.

liamsun2019 avatar May 17 '22 11:05 liamsun2019