- 14 2月, 2020 1 次提交
-
-
由 xiaogang 提交于
fix fpga lite_tensor compile bug add fake quantize_abs_max op test=develop
-
- 13 2月, 2020 1 次提交
-
-
由 huzhiqiang 提交于
-
- 12 2月, 2020 1 次提交
-
-
由 HappyAngel 提交于
* fix con+relu6/leakyRelu fusion in Fp32, test=develop * note m=397 in sgemv_int8 ut, test=develop * fix ios build error. test=develop
-
- 06 2月, 2020 1 次提交
-
-
由 juncaipeng 提交于
* optimize quant_dequant_fuse_pass, test=develop * update, test=develop * update, test=develop * fix bug for accessing the removed node, test=develop * set the bias of int8 conv as float, test=develop * support weight quantization, test=develop * up, test=develop * up, test=develop * up, test=develop
-
- 22 1月, 2020 1 次提交
-
-
由 HappyAngel 提交于
-
- 16 1月, 2020 1 次提交
-
-
由 HappyAngel 提交于
1. add conv_5x5s2_dw to support any padding 2. add 1x1s2pooling impl 3. fix conv dw 3x3 s1p01 bug
-
- 14 1月, 2020 1 次提交
-
-
由 myq406450149 提交于
* Support bitman backend
-
- 09 1月, 2020 1 次提交
-
-
由 Wilber 提交于
* temporarily remove x86 fuse test=develop * remove useless logs test=develop
-
- 06 1月, 2020 1 次提交
-
-
由 石晓伟 提交于
-
- 03 1月, 2020 2 次提交
-
-
由 Wilber 提交于
temporarily remove cuda fc fuse because we don't support cuda fc now
-
由 hong19860320 提交于
-
- 02 1月, 2020 1 次提交
-
-
由 GaoWei8 提交于
* Enhance fc_fuse_pass to enable fusing relu to fc_op test=develop * restrict fusing relu in x86 test=develop
-
- 31 12月, 2019 1 次提交
-
-
由 hong19860320 提交于
* Fix the compiling error which occurs when specify the ddk_root path and build for huawei NPU. * Refine the registration of op bridges and make it similar to the registration of op and kernel. * Refine the interfaces of the graph and node for op bridges, and support creating constant and data node automatically according to the attribute 'persistable' of the target tensor. * Add the unit test of the scale and softmax op bridge for NPU.
-
- 24 12月, 2019 1 次提交
-
-
由 hong19860320 提交于
* Support multiple types for XPU and NPU op bridges * Add lookup_table, gather, slice, stack and scale op bridges for supporting BERT * Fix the definition of lookup_table kernel for X86
-
- 23 12月, 2019 1 次提交
-
-
由 Wilber 提交于
add sequence_pool_concat fuse pass add fuse kernel
-
- 20 12月, 2019 1 次提交
-
-
由 Wilber 提交于
add var_conv_2d + relu fuse pass
-
- 18 12月, 2019 1 次提交
-
-
由 juncaipeng 提交于
* Support Mask RCNN2 (#2588)
-
- 17 12月, 2019 2 次提交
-
-
由 HappyAngel 提交于
* add cv image process * fix arm liunx build error * add LITE_WITH_CV defien to make cv, test=develop * fix cv format, annd add describe in utils/cv * delete some Meaningless comments, test=develop * set LITE_WITH_CV=OFF in build.sh, test=develop * delete cv_enum.h in utils/cv, push the contents in cv_ennum.h to paddle_image_preprocess.h, test=develop * according to reviews to redefine paddle_image_preprocess.h, test=develop * add detailed note of flipParam, test=develop * fix format in paddle_image_preprocess.h, test=develop * fix error when build x86. test=develop lite_with_X86 does not contain lite_with_cv * fix cmake error in llite/CMakeLists.txt, missing mkdir cxx, test=develop * according to review change, test=develop * chang grb to rgb, test=develop * add elemetnwise mul constant elimination and deconv+relu, deconv+batchnorm fusion, test=develop * fix format, test=develop
-
由 guofei 提交于
test=develop
-
- 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)
-
- 10 12月, 2019 2 次提交
-
-
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
-
- 03 12月, 2019 1 次提交
-
-
由 Zhaolong Xing 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
* [NPU] add reduce_mean op bridge and unit test test=develop * refine xpu_pass place order; add bridges use test=develop
-
- 26 11月, 2019 1 次提交
-
-
由 zhupengyang 提交于
* [XPU] update conv padding test=develop * [XPU] exclude xpu for passes test=develop * fix conv padding compute test=develop * [NPU] update 2-pad to 4-pad for conv and conv_transpose test=develop * reuse UpdatePadding code test=develop
-
- 22 11月, 2019 1 次提交
-
-
由 hong19860320 提交于
[LITE][ALL] Refine NPU and XPU passes, fix the pass matching based on the bound targets and excluded targets (#2477)
-
- 18 11月, 2019 1 次提交
-
-
由 Yuan Shuai 提交于
* Fix bug target for kHost and kARM not equal. test=develop * Fix license. test=develop * add debug -g option. test=develop * enable opencl demo. test=develop * Fix model_optimize_tool found no opencl kernel. test=develop * add more vlog. test=develop * remove macro LITE_WITH_OPENCL, LITE_WITH_FPGA in passes. test=develop * Fix valid_places in mobilenetv1_test. test=develop * Fix bug of find no real output of fetch, after tool OPs of optimzer passes. test=develop * Fix vlog as log message in model_optimize_tool. test=develop * fix miscs. test=develop * fix comment. test=develop * Fix misspell of opencl, fpga kernels name in lite/api/CMakeLists.txt. test=develop * add opencl macro in full_api of demo. test=develop
-
- 08 11月, 2019 1 次提交
-
-
由 hong19860320 提交于
[LITE][NPU] Add fusion_elementwise_add_activation bridge, remove the limitation of the dimensions of input tensors in the graph compute kernel, and refine log message (#2395) test=develop
-
- 06 11月, 2019 1 次提交
-
-
由 juncaipeng 提交于
* add channel_wise_dequantized_max_abs op and ChannelWiseDequantOpFuser, test=develop
-
- 05 11月, 2019 2 次提交
-
-
由 zhupengyang 提交于
test=develop
-
由 lijianshe02 提交于
* fix step rnn model run bugs test=develop
-
- 01 11月, 2019 1 次提交
-
-
由 石晓伟 提交于
-
- 31 10月, 2019 1 次提交
-
-
由 Yuan Shuai 提交于
* Fix conv bn bug. test=develop * Fix bug in pattern_matcher. test=develop
-
- 30 10月, 2019 2 次提交
-
-
由 hong19860320 提交于
-
由 Xiaoyang LI 提交于
-
- 29 10月, 2019 2 次提交
-
-
由 Yuan Shuai 提交于
* Fix bug target for kHost and kARM not equal. test=develop * Fix license. test=develop
-
由 hong19860320 提交于
* Add supporting for Huawei offical DDK * Fix the param of graph op in NPU graph computing kernel
-
- 28 10月, 2019 1 次提交
-
-
由 hong19860320 提交于
* Initial support for XPU * Fix compiling errors of XPU * Move XPU op kernel bridges from backends to kernels to fix deps order * Change the namespace and directory of XPU bridges * Add XPU SDK * Fix header files and namespace of XPU SDK * Add unit tests for relu and conv2d ops * Restore the modification of paddle_api_test * Supports simple model which contains only a relu layer * Add compiling scripts for XPU * Fix compiling errors of XPU * Add comments for XPU LoadModel and BuildModel
-
- 26 10月, 2019 1 次提交
-
-
由 Yuan Shuai 提交于
Fix conv_bn fuser with no elemwise op added, Fix conv_elem with original conv with conv_bias (#2211) * Fix conv_bn fuser with no elemwise op added. test=develop * fix match not bug. test=develop * Fix conv-bn pass. test=develop * Fix conv-bn pass. test=develop * Fix conv-bn pass. test=develop * Fix conv-bn pass. test=develop * Fix conv-bn pass. test=develop * Fix conv-bn fuse pass. test=develop * Fix conv-bn fuser consider the case: enable_int8=true without conv_bias. test=develop * Fix back, consider enable_int8. test=develop * Fix Bug for conv-bn quant pass. test=develop * Fix conv-elemwise considering origin conv with conv_bias. test=develop * Fix code format. test=develop * simplify. test=develop * simplify. test=develop * Fix conv_elem. test=develop
-