Finetuning the Pruned Model - Finetuning the Pruned Model - 1.1 English - UG1333

Run the following command to attempt to recover the accuracy loss from pruning:

$ ./vai_p_caffe finetune -config config.prototxt

Finetuning a pruned model is essentially the same as training the model from scratch. The solver parameters such as initial learning rate, learning rate decay type, etc. may be different. A pruning iteration is composed of the prune and finetune tasks executed sequentially. In general, to achieve a greater weight reduction without significant accuracy loss, several pruning iterations need to be performed.

The configuration file needs to be modified after every pruning iteration

1. Increase the rate parameter relative to the baseline model.
2. Modify the weights parameter to the best model obtained in the previous finetuning step.

A modified configuration file is shown below:

workspace: "examples/decent_p/"
gpu: "0,1,2,3"
test_iter: 100
acc_name: "top-1"
 
model: "examples/decent_p/float.prototxt"
 
#weights: "examples/decent_p/float.caffemodel"
weights: "examples/decent_p/regular_rate_0.1/_iter_10000.caffemodel"
 
solver: "examples/decent_p/solver.prototxt"
 
# change rate from 0.1 to 0.2
#rate: 0.1
rate: 0.2
pruner {
  method: REGULAR
}