- 16 12月, 2019 4 次提交
-
-
由 TianXiaogang 提交于
* fix: update backend fpga patch
-
由 Yuan Shuai 提交于
[LITE][OPENCL] Add relu image2d kernel unit test, Fix conv2d_1x1, relu, layout using new Image2D Layout (#2564) * add 3 layout for opencl image. test=develop * add relu image2d test. test=develop
-
由 Jiaying Zhao 提交于
* [LITE][OPENCL] Add depthwise_conv_3x3 opencl kernel * [LITE][OPENCL] Add depthwise_conv_3x3 opencl kernel. test=develop * [LITE][OPENCL] Add Pool opencl kernel. test=develop
-
由 石晓伟 提交于
* update profiler, test=develop * warm up times of profiler, test=develop
-
- 15 12月, 2019 1 次提交
-
-
由 Wilber 提交于
optimize search_grnn
-
- 13 12月, 2019 1 次提交
-
-
由 hong19860320 提交于
[LITE][NPU][XPU] Refine subgraph pass, and support NPU/XPU model generation at execution time (#2576)
-
- 12 12月, 2019 4 次提交
-
-
由 huzhiqiang 提交于
-
由 xiebaiyuan 提交于
* add opencl conv1x1 image impl and unit test pass with relu & bias, add layout_compute --> buffer2image float32 --> with unit test pass suite checked test for more situation , test=develop * add opencl conv1x1 image impl and unit test pass with relu & bias, add layout_compute --> buffer2image float32 --> with unit test pass suite checked test for more situation , test=develop * fix white space cpp lint , test=develop
-
由 xiebaiyuan 提交于
* fix 1x1_wrapped crashed in huawei && reinit super image . test = develop * fix 1x1_wrapped crashed in huawei && reinit super image . test = mobile
-
由 huzhiqiang 提交于
-
- 11 12月, 2019 2 次提交
-
-
由 TianXiaogang 提交于
-
由 Yuan Shuai 提交于
* add 3 layout for opencl image. test=develop
-
- 10 12月, 2019 7 次提交
-
-
由 huzhiqiang 提交于
-
由 qnqinan 提交于
* update proposal and psroipool kernel file in FPGA V2 track * update, test=develop * update FPGA v2 pe cpp file and ew kernel files, test=develop * fix a bug of sigmoid kernel in FPGA v2 track, test=develop * fix bugs of concat, reshape and slice op and add usleep in fpga regpoll, test=develop * add interupt clear operation before op compute in FPGA V2 track, test=develop * fix a bug in ewadd in FPGA v2, test=mobile
-
由 huzhiqiang 提交于
-
由 Wilber 提交于
For multiple-use parameters, only copy once
-
由 Wilber 提交于
修改了选kernel的逻辑,默认从模型文件中读取出lod_tensor的data type,在static_kernel_pick pass中如果kernel输入输出的类型与读取的data type完全一致,则选择该Kernel的概率增大。 - 增加 从模型文件__model__读取lod_tensor的data type到cpp::vardesc - program中增加unordered_map<string, type>字段,并在 Program::PrepareWorkspace中对该字段赋值 - 修改了node.h文件,将const Type* 更改为Type*,并在SSAGraph::Build过程中为符合条件的type*赋值 - static_kernel_pick_pass中添加新规则,如果kernel的输入类型输出类型与__model__中存储的类型的一致,则score*=2。 - 支持模型中用到sequence_reverse_float kernel(输入输出均为float)和sequence_reverse_int64 kernel(输入输出均为int64),能够根据输入输出type选kernel
-
由 yiicy 提交于
-
由 zhupengyang 提交于
test=develop
-
- 09 12月, 2019 4 次提交
-
-
由 yiicy 提交于
-
由 yiicy 提交于
-
由 zhupengyang 提交于
test=develop
-
由 huzhiqiang 提交于
* add static library in tiny_publish * move flto and ffunction-sections cmake option into the tiny publish so result of java,cxx,python
-
- 08 12月, 2019 1 次提交
-
-
由 liu zhengxi 提交于
-
- 07 12月, 2019 2 次提交
-
-
由 zhupengyang 提交于
test=develop
-
由 juncaipeng 提交于
* add arm split lod tensor, test=develop * add arm merge lod tensor, test=develop * update split merge lod tensor, test=develop * add reduce_prob op, test=develop * support mask_rcnn succeed, test=develop
-
- 06 12月, 2019 1 次提交
-
-
由 Wilber 提交于
- fix fill_constant bug. - cast op support int64_t->int32_t
-
- 04 12月, 2019 3 次提交
-
-
由 Wilber 提交于
update cuda kernels to run content-dnn model
-
由 Zhaolong Xing 提交于
* init resnet cuda int8 support test=develop * refine cuda unit test test=develop * add the forgeted file. test=develop
-
由 石晓伟 提交于
-
- 03 12月, 2019 5 次提交
-
-
由 yiicy 提交于
* [Demo] add cxx mobilenetv1-ssd detection demo, test=develop * add makefile to mobile detection demo, test=develop * [Demo] add cxx mobilenetv1-ssd detection demo, test=develop * [demo] fix mobile_detection code style, test=develop * [Demo] fix demo code style, test=develop * [Demo] fix detection demo makefile dependency, test=develop
-
由 Zhaolong Xing 提交于
test=develop
-
由 TianXiaogang 提交于
* feat: add sgemm4x4 for armv8 * fix: fix armv7 gemm choose condition
-
由 juncaipeng 提交于
* set the bias of int8 conv as float, test=develop
-
由 zhupengyang 提交于
test=develop
-
- 02 12月, 2019 2 次提交
-
-
由 liu zhengxi 提交于
-
由 liu zhengxi 提交于
-
- 30 11月, 2019 1 次提交
-
-
由 zhupengyang 提交于
test=develop
-
- 29 11月, 2019 2 次提交
-
-
由 Yuan Shuai 提交于
[LITE][PASS] Fix static kernel pick pass, if op is not int8, but kernel is int8. test=develop (#2526)
-
由 zhupengyang 提交于
test=develop
-