XCJ_lalala issues

Results 5 issues of


                                            XCJ_lalala

Could anyone tell me why is the MOTP is so low？

Is there anyone write the caltech version in pytorch can share with me？thanks a lot！

Does anyone reproduce the caltech result using author's weight?

Does anyone reproduce the caltech result using author's weight(net_e110_l0.0082234138241.hdf5)? Could you share with me the result file which can be evaluated by matlab? Thank you very much!!!!!!

batchsize 16 on one 2080ti cause OOM exception

I encounter with a problem when setting batchsize 16 on one 2080ti 11G causes OOM. So I have to put 8 on two GPUs respectively. But the paper says the...

What‘ the version of tensorflow and cuda?

I encounter a problem when I try to run the train.py like this Traceback (most recent call last): File "C:/Users/Administrator/Desktop/FastFPN-master/FastFPN-master/train/train.py", line 22, in import libs.nets.pyramid_network as pyramid_network File "C:/Users/Administrator/Desktop/FastFPN-master/FastFPN-master/train\..\libs\nets\pyramid_network.py", line...