peyer
peyer
thanks a lot
I'm sorry , but when I train the pnet again using your gen_pnet_data.py and lr = 0.01 , the output become nan again . I feel so bad .
@huynhthedang , I got the same problem. The cls_prob and the pred_delta after 2 databatch become very big , ~10^24 .
I only change the path to my data path , and I have modified mxnet/src/regression_output-inl.h according to mxnet_diff.patch
@Seanlinx I try to inspect every op's input and output , but I haven't searched the method to go into op's forward function , dou you know how to do...
I actually use the latest version of mxnet . I will download the v0.7 one to try again. I know how to use print in negativemining op , but in...
@Seanlinx I still have a very confusing problem . In the LinearRegression op , does it compute (conv4_2 - bbox_target)^2 = bbox_loss ? If that , then in negativemining op...
@Seanlinx Thanks a lot . I maybe know how to continue
For training P_Net , I set the pos : part : neg = 1 : 2 : 5 , then I train the P_Net with other training params keeping ,...
@Seanlinx I use your gen_pnet_data.py , then pos : part : neg = 2 :3 : 6 , then I start the train_P_net.py , it has worked . I only...