* add small scale config

* add model zoo

* remove metric type

* fix train diff for fairmot

* set use_shared_memory to True for fairmot training

* mot video decode to images

* add infer_dir for mot

* fix export and unite pose infer

* remove task in mot source

* set image_dir

* update doc

* fix ffmpeg video infer, fix doc, test=document_fix

* fix ffmpeg installl, test=document_fix

* add fairmot

* rename pretrain_weights

* add comments; reuse focal loss and convnorm

* update comments