* add yolo_box_compute cuda

* move multiclass_nms(arm) to host

* add lod in scale op

* add yolo_box_cuda cmake config

* modify shuffle_channel_fuse and transpose_softmax_transpose_fuse to support run ssd model. test=develop

* reshape and transpose op don't have xshape output.

* modify yolo_box_compute_cuda, use tensor to manage cuda memory test=develop

* add yolo_box use kernel test=develop

* paddle lite cuda init
can run model with leaky_relu

* add the missing file.
test=develop

* add the load from memory interface.
test=develop

* refine this pr. fix comments
fix ci error
test=develop

test=develop

ad ops for faster rcnn, including affine_channel, anchor_generator, generate_proposals and roi_align (#1895)

* add ops for faster rcnn

* disable test for generate_proposals and roi_align, test=develop

* remove .swp file

* remove log in tensor slice

* finish the unit test for roi_align, test=develop

* add npu script and tester

* fix npu armv7 so and refine tests

test=develop

* update fix and refine log

test=develop

* refine npu generate api

* refine npu subgraph

* refine npu gen and clean code

* fix model laod

* refine node2rm in subgraph

* refine the build npu functions

test=develop

* add transpose-softmax-transpose fuse pass

test=develop

* enable supported lite-npu ops

test=develop

* paddle lite cuda init
can run model with leaky_relu

* add the missing file.
test=develop

* add npu script and tester

* fix npu armv7 so and refine tests

test=develop

* update fix and refine log

test=develop

* fix building ios tiny publish lib error

* support setting cluster and threads in MobileConfig

* fix build error, test=develop

* fix building server publish error, test=develop

add model_run_test_image
    add range_max_quant op
    add flatten op
    add flatten2 op
fix:
    fix density_prior_box density_size type from float to int
    fix prior_box and density_prior_box some check for get_attr
test=develop

test=develop

test=develop

test=develop