Usage of this repo about yolov3_lite HOT 2 OPEN

@abhigoku10
hello,

1. I used some method like: prune weights < threshold; give every 3*3 weights a mask, and skip the compute when mask ==0; use L1 regula to delete some feature maps in cfg file; use openmp to realize threads compute in cpu
2. because the pruned weights is also float 32, so weights file is same big as before, but you can use hoffman convert to compress weights file
3. natuerlich, in convolutional.c files, the author has some functions to plot the weights map, you can find them ：）

from yolov3_lite.

@ArtyZe thanks for response ,

1. thanks , openmp shall be used onlyin the case of cpu
2. since the weight size before and after pruning are the same but the performance(fps) is improved right??have you used huffman to compress the weights

3.thanks for the pointers

4.after performing pruning did you re-train the model i.e iterative pruning and training , if so what is the loss value and iteration u have reached
Thanks in advance

from yolov3_lite.