- 03 9月, 2019 3 次提交
-
-
由 Huie 提交于
* 1.add density_prior_box for gpu. 2.add flatten2 for gpu. 3.add concat 4 inputs size for gpu. 4.fix pool. 5.fix transpose2 test=develop * 1.fix GetGPUTime test=develop
-
由 StarryRain 提交于
* add opencl depthwise_conv_trans_op * test=develop
-
由 huzhiqiang 提交于
* add images to readme.md and readme_cn.md test=develop * change the image style test=develop * chage the image style * chage the image style * chage the image style * change image style * change image style * change image style test=develop
-
- 02 9月, 2019 3 次提交
-
-
由 Yuan Shuai 提交于
* enhance benchmark * update code format. test=develop
-
由 juncaipeng 提交于
* 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 box_clip op and fix tensor slice bug * remove add four op twice * rewrite the implement for box_coder and sequence_expand, add faster_rcnn_test, test=develop * fix test bug of box_clip in x86 server, test=develop
-
由 juncaipeng 提交于
* fix elementwise_op bug when the shape of input y is 1, test=develop * fix elementwise ops bug when the shape of input y is 1, test=develop
-
- 01 9月, 2019 3 次提交
-
-
由 Yuan Shuai 提交于
* Fix timer of arm cpu profiler. test=develop * Fix un-added op in cmake.test=develop * fix cmake error * fix cmake error, test=develop * Fix pass sequence. test=develop * replace option with lite_option. test=develop * disable profile mode by default. test=develop * Fix error option name. test=develop
-
由 NazgulLee 提交于
-
由 huzhiqiang 提交于
-
- 31 8月, 2019 1 次提交
-
-
由 guofei 提交于
-
- 30 8月, 2019 6 次提交
-
-
由 liu zhengxi 提交于
* add stack op and add reduce_mean op and their unit tests * modify stack op output name and modify the for loop in reduce_mean op * add HasAttr for slice op
-
由 Pei Yang 提交于
add nearest_interp cuda kernel for Paddle-Lite
-
由 hong19860320 提交于
* [NPU] add NPU supporting for Java API test=develop * [NPU] refine build script for NPU compiling test=develop * [NPU] fix compiling script for NPU test=develop
-
由 zhupengyang 提交于
test=develop
-
由 Xiaoyang LI 提交于
* fix ios build script, test=develop * add ios tiny publish target, test=develop * fix ios build scrip, test=develop * merge build_ios.sh to build.sh, test=develop * ios support BUILD_EXTRA, test=develop
-
由 Zhen Wang 提交于
* Add precision and persistable attrs for the tensor. And fix cxx light and full api demo. * update precision2string methods. test=develop * move the save logic to the front of the run in mobilenetv1_full_api.cc, test=develop. * add comments for UpdateVarsOfProgram. test=develop
-
- 29 8月, 2019 11 次提交
-
-
由 tensor-tang 提交于
-
由 tensor-tang 提交于
-
由 Wilber 提交于
* 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
-
由 sangoly 提交于
-
由 Yanzhan Yang 提交于
* refine toolchain test=develop * fix wrap compilation error * fix yolov3 armv8 compilation test=develop * revert to armv7 as default test=develop * fix fpga compilation test=develop
-
由 liu zhengxi 提交于
-
由 Zhaolong Xing 提交于
* 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
-
由 sangoly 提交于
-
由 tensor-tang 提交于
test=develop
-
由 juncaipeng 提交于
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
-
由 tensor-tang 提交于
* 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
-
- 28 8月, 2019 13 次提交
-
-
由 juncaipeng 提交于
* modify cast op, test=develop * modify cast op and remove warning in argmax_test, test=develop
-
由 Yanzhan Yang 提交于
-
由 Yanzhan Yang 提交于
-
由 Yan Chunwei 提交于
-
由 zhupengyang 提交于
test=developt branch
-
由 Yanzhan Yang 提交于
-
由 huzhiqiang 提交于
-
由 zhupengyang 提交于
* add transpose-softmax-transpose fuse pass test=develop * enable supported lite-npu ops test=develop
-
由 huzhiqiang 提交于
add x86 math:sequence_scale,sequence_padding,sequence2batch,sequence_pooling. test=develop (#1884)
-
由 hong19860320 提交于
* [NPU] fix conv2d npu bridge, supports bias from input map test=develop * [NPU] support more dimensions for the bias of conv2d NPU bridge test=develop
-
由 sangoly 提交于
-
由 sangoly 提交于
-
由 Huie 提交于
2.add flatten2 for gpu. 3.add concat 4 inputs size for gpu. 4.fix pool. 5.fix transpose2 test=develop
-