![]() ![]() This will lead to smaller graphs with less parameters and actual speed-ups on your device. ![]() When a pruned model is used, the appropriate -net should be selected as well. This dictionary can be used as -pretrained_model_path in the python scripts to create a new and smaller graph in Tensorflow. Running the scripts with the appropriate paths(in script), will result in a pickled dictionary with the new network structure and weights. The networks weights are not updated during pruning, only the regularization paramters connected to the structures.Īfter running the pruning script a new weights file can be generated with one of the following scripts, according to the pruned structure: The to regularize structure can be chosen with the -net parameter. The pruning script traines the network with a regulizer applied to the chosen structure. ![]()
0 Comments
Leave a Reply. |