suitable prune rule about yolov3-channel-pruning HOT 3 CLOSED

if the auther has already test the result, can you upload the result, and there are more information can discuss which can lead to the results we want.

from yolov3-channel-pruning.

in @talebolano code, the prune rule is:

python prune.py --cfg yolov3.cfg --weights checkpoints/yolov3_sparsity_100.weights --percent 0.3

the --percent 0.3 is following, I wonder whether this it the suitable value, or more test result.

from yolov3-channel-pruning.

It is the same...... This parameter is " --s 0.01" is the default parameter in the code.

The prune rule is (1)避免剪掉所有channel的最高阈值(每个BN层的gamma的最大值的最小值即为阈值上限)
(2)剪枝的时候会先对 bias 做处理，用其后的卷积层或者 BN 层来吸收这个参数，然后再将权重赋值给 compact model，
这样做的话就能保证 pruned_model （只对 weight 置 0 的模型）和 Compact_model 对相同的输入有相同的输出

The prune ratio mainly depend on the application.

from yolov3-channel-pruning.