Closed buryang closed 5 years ago
@psyyz10 Could you please take a look at this issue?
@buryang
--cp_nb_rlouts_ming
to other value.--ddpg_noise_std_init=0.5
.--cp_nb_rlouts
to a smaller value.@buryang I know that paper, but what the hidden layer size means? Maybe we do not use that variable.
@psyyz10
Hi, thanks for your open-source code.
In the ChannelPruning Auto, which channel pruning method are you using? The original AMC paper prune the channels in the convolutional kernel with lowest magnitude. It seems that you use LASSO to select the channels. Please correct me if I misunderstand the code.
In the channel-pruning-gpu repo, you implement the discrimination-aware channel pruning. Do you have the implementation of LASSO based channel pruning on GPU?
Thanks.
@Jinyyyy
ChannelPrunedGpuLearner
, which uses proximal gradient descent to select channels under the L1-regularization and is implemented on GPU.
Hi, I‘m trying to compress my Unet network which for regression. I just use 1-lambda*l2_loss for Acc, and till now trained 40 roll outs,the Acc reach only 0.22 but the Acc of original model is 0.96, is it normal? In addition, the hidden layer size in the AMC paper is 300, why is your code changed to 64? Then sckit-learn training is slow, can you save the intermediate checkpoints of actor-critic models?