* fix cpu conv_add and conv_add_relu

* fix cpu conv_add and conv_add_relu

1. add optimize parameter to load function. 2. add transpose operation if the input of fetch op is not [0, 2, 3, 1]. (#1651)

* develop nearestinterp op  fix bug in element add close #1647

* remove log
remove log

1. reshape output transpose should be 0, 1, 2, 3. 2.mps conv should be disabled when groups is larger than 1. 3. slice should re-tranpose its input if needed. (#1646)

* fix memcpy size in opencl fetch kernel

* add opencl Scale op

1.add groups to conv3x3. 2.add original size to tensor and tenture and adjust concat layer to handle tensor truncation logic. (#1643)

* V2-conv-hellocase pass & V1 verify-pass

* V1 paralvl equal to 2

* softmax channel =2 bug

* softmaxbug update2

* io update2

* V1-dwconv relu bug

* opendevice bug fixed

1.add flatten2, slice and nearest_interp op. 2.truncate tensor with more than 4 dimensions to 4. (#1634)

1.parse tensor desc info from params file. 2.ensure tensor desc is consistent between params file and model file. (#1631)

* V2-conv-hellocase pass & V1 verify-pass

* V1 paralvl equal to 2

* softmax channel =2 bug

* softmaxbug update2

* io update2

* V1-dwconv relu bug

* optimize GPU conv performance and structure

* add CL macro for test_conv_gpu

* fix build failure

* change funtion name

* change funtion name

* fix load_when_predict mode in opencl

* remove dafault opencl kernel path

* optimize GPU conv performance and structure

* add CL macro for test_conv_gpu

* fix build failure

* change funtion name

* change funtion name

* fix load_when_predict mode in opencl

* update concat and split kernel and related files in FPGA v2(v3) track

* update

* update

* update kernel and related files in FPGA v2 track

* update

* update

* update kernel and related files for static quantization in FPGA v2 track

* update

* update feed and fetch kernel in FPGA v2 track

* update io file

* update feed fetch and softmax kernel in FPGA v2 track

* Update ocr test case

* format code

* format code

* V2-conv-hellocase pass & V1 verify-pass

* V1 paralvl equal to 2

* softmax channel =2 bug

* softmaxbug update2

* io update2

* V2-conv-hellocase pass & V1 verify-pass

* V1 paralvl equal to 2

* shift filter conversion process to loading phase

* fix winograd edge case

* update concat and split kernel and related files in FPGA v2(v3) track

* update

* update

* update kernel and related files in FPGA v2 track

* update

* update

* update kernel and related files for static quantization in FPGA v2 track

* update

* update feed and fetch kernel in FPGA v2 track

* update io file

* update concat and split kernel and related files in FPGA v2(v3) track

* update

* update

* update kernel and related files in FPGA v2 track

* update

* update

* update kernel and related files for static quantization in FPGA v2 track

* update

* update feed and fetch kernel in FPGA v2 track

* add comments for imagetools

* format code

* optimize GPU conv performance and structure

* add CL macro for test_conv_gpu

* fix build failure

* change funtion name

* change funtion name

* implement winograd for metal depthwise 3x3 naively

* keep half4 in non-winograd depthwise 3x3 to ensure precision

* optimize GPU conv performance and structure

* add CL macro for test_conv_gpu

* fix build failure