- 21 9月, 2020 5 次提交
-
-
由 huzhiqiang 提交于
-
由 zhupengyang 提交于
-
由 Santa An 提交于
-
由 huzhiqiang 提交于
-
由 石晓伟 提交于
* add clear_blocks interface for flatbuffers view, test=develop * fix a bug, test=develop * enhanced the error messages, test=develop
-
- 20 9月, 2020 1 次提交
-
-
由 weihaoji 提交于
-
- 18 9月, 2020 4 次提交
-
-
由 HappyAngel 提交于
* add reduce op on arm. test=develop * fix format. test=develop * fix acccording to comments. test=develop
-
由 HappyAngel 提交于
* fix bilinear_resize result not equal with fluid. test=develop * fix cv build error. test=develop * fix format. test=develop
-
由 HappyAngel 提交于
* fix conv_3x3s1_dw v7-compute nan. test=develop * fix compute. tets=develop * set sgemm basic_test is false. test=develop
-
由 Qi Li 提交于
* [X86] add box_coder kernel and fix compile on MAC, test=develop * [DOC] remove debug info, test=develop * [X86] add new op of density_prior_box, test=develop
-
- 17 9月, 2020 6 次提交
-
-
由 HappyAngel 提交于
* add scatter op on arm. test=develop * fix cmake error. test=develop * test=develop
-
由 ysh329 提交于
[PROFILE] Add ENV var controls whether write output tensor of each op to files; Rename output tensor name when mem_reuse pass enabled by default etc. (#4348) * Add ENV var controls whether write output tensor of each op to files; * Rename output tensor name when mem_reuse pass enabled by default etc.
-
由 huzhiqiang 提交于
-
由 zhupengyang 提交于
-
由 huzhiqiang 提交于
-
由 hong19860320 提交于
-
- 15 9月, 2020 4 次提交
-
-
由 hong19860320 提交于
-
由 石晓伟 提交于
-
由 ysh329 提交于
* [PROFILE] Write output tensor to file for each OP when precision profiler enabled. test=develop * create output tensor files dir. test=develop
-
由 Cwndmiao 提交于
[LITE][XPU] 1. Add sequence_unpad kernel for XPU; 2. Bugfix in sequence_unpad kernel for x86, as InferShapeImpl() is now empty in lite/operators/sequence_unpad_op.cc; 3. Refine TargetWrapperXPU; (#4237)
-
- 14 9月, 2020 9 次提交
-
-
由 石晓伟 提交于
* [cherry-pick] not build naive_buffer when build light framework, test=develop (#4251) * fix opt fatal errors, test=develop (#4293) * fix cmake dependencies, test=develop
-
由 zhaoyang-star 提交于
* [Bugfix][OpenCL] fix depthwise_conv2d_3x3 with dilation > 1. test=develop
-
由 hong19860320 提交于
-
由 石晓伟 提交于
-
由 myq406450149 提交于
-
由 ysh329 提交于
-
由 HappyAngel 提交于
* add sequence_expand_as op on arm. test=develop * fix format. test=develop
-
由 cc 提交于
* Optimize obtaining quantized scale in inference, test=develop
-
由 huzhiqiang 提交于
-
- 11 9月, 2020 2 次提交
-
-
由 HappyAngel 提交于
add cv_ut. test=develop add Anakin implement add image_profiler test
-
由 cc 提交于
-
- 10 9月, 2020 2 次提交
- 09 9月, 2020 4 次提交
-
-
由 Wangzheee 提交于
[OP][HOST][KERNEL]Add uniform_random operator, and add host kernel for uniform_random. test=develop (#4264)
-
由 石晓伟 提交于
-
由 hong19860320 提交于
-
由 zhupengyang 提交于
-
- 08 9月, 2020 3 次提交
-
-
由 石晓伟 提交于
-
由 石晓伟 提交于
* platform portability of tls, test=develop * update build_ios.sh, test=develop * add static keyword for tls, test=develop * rename the alias of tls, test=develop
-
由 hong19860320 提交于
[NPU] Disable scale_activation_fuse_pass which causes the wrong result in yolov3_mobilenetv3 (#4266)
-