kewang-seu

Results 3 comments of kewang-seu

Memory of Model Increases and Inference Stays the Same After Pruning

> Hi, > > I have a similar issue. I used the high level pruner "MagnitudePruner" for Mask-rcnn pruning, with `iterative_steps = 1`. The number of model paramers is reducec...

ch_sparsity is 1.0 in main.py

Is the increase of sparsity equal in step length？Is "iterative-steps" parameter the number of iteration？

infer.py精度与eval.py精度差距过大

您好，请问这个问题解决了吗？我用COCO预训练模型在eval和infer时，精度也出现了很大差异，推理的结果非常差，几乎检测不到目标，但从eval的精度来看，还是可以的。这是为什么呢？