* decode with cache

* update

* update

* add frame_rate for mot infer video

* add doc of frame_rate for mot video infer, test=document_fix

* add gfl model and PicoDet

* add python train time eval

* add mpii infer support

* 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

Besides removing unnecessary imports, this also fixes the missing logger module in test_architectures.py within the static directory.

* add sparsercnn

* update sparsercnn

* Add DETR

* drop return_pad_mask in PadBatch

add dark deploy supported, mpii deploy supported;

* add random resize and crop

* update

* update

* support --eval for s2anet

* add spine dataset and config yml for s2anet

* add doc for s2anet

* update doc

* fix typo, test=document_fix

* add some comments, and update import

* add DarkPsoe support

* modify Top-Down bbox_file str to bbox.json

* decord video infer

* add video infer write results

* support no label training

* fix load_crowd

* update to fit rbox

* add empty_ratio

* update configs

* support mask rcnn

* clean drop_empty for mot & keypoint

* refine is_crowd

* fix mot_source

* fix mot_source, test=document_fix

* add video infer for TestMOTReader

* format, test=documment_fix

* add fairmot

* rename pretrain_weights

* add comments; reuse focal loss and convnorm

* update comments

* fix hsv randomaffine

* fix nms return_index

* fix gt_ide by tid_start_index

* add config for jde and deepsort, add engine metric tools

* add mot_metrics

* fix configs engine and others

* fix configs others

* move configs

* fix ap_per_class, fix doc

* fix test_mode, seqs

* fix test_mode to metric

* fix JDE arch metric

* clean requirement

* add to requirement