Skip to content

P
Paddle-Lite

PaddlePaddle / Paddle-Lite

通知 332
Star 4
Fork 1
P
Paddle-Lite
切换分支/标签
历史 查找文件
云IDE
克隆
Z
zhangyang 推送
correct FPGA kernels c3248eaa
1177次提交
名称 最后提交 最后更新
..
kernel correct FPGA kernels
math Merge branch 'develop' of https://github.com/PaddlePaddle/paddle-mobile into develop
batchnorm_op.cpp remove unused code
batchnorm_op.h modify cmake add paddle mobile interface
box_coder_op.cpp remove unused code
box_coder_op.h modify cmake add paddle mobile interface
concat_op.cpp fpga concat kernel
concat_op.h fpga concat kernel
conv_op.cpp remove unused code
conv_op.h modify cmake add paddle mobile interface
conv_transpose_op.cpp commit conv transpose
conv_transpose_op.h commit conv transpose
depthwise_conv_op.cpp remove unused code
depthwise_conv_op.h modify cmake add paddle mobile interface
dropout_op.cpp add fpga ops and kernels
dropout_op.h add fpga ops and kernels
elementwise_add_op.cpp remove unused code
elementwise_add_op.h modify cmake add paddle mobile interface
feed_op.cpp add MACRO in feed_op.cpp for FPGA track
feed_op.h feed op type mismatch
fetch_op.cpp register Feed and Fetch ops
fetch_op.h register Feed and Fetch ops
fusion_conv_add.cpp remove unused code
fusion_conv_add.h format files
fusion_conv_add_bn_op.cpp add 3 FPGA ops for conv
fusion_conv_add_bn_op.h
fusion_conv_add_bn_relu_op.cpp
fusion_conv_add_bn_relu_op.h
fusion_conv_add_relu_op.cpp
fusion_conv_add_relu_op.h
fusion_conv_bn_op.cpp
fusion_conv_bn_op.h
fusion_conv_bn_relu_op.cpp
fusion_conv_bn_relu_op.h
fusion_dwconv_bn_relu_op.cpp
fusion_dwconv_bn_relu_op.h
fusion_elementwise_add_relu_op.cpp
fusion_elementwise_add_relu_op.h
fusion_fc_op.cpp
fusion_fc_op.h
fusion_fc_relu_op.cpp
fusion_fc_relu_op.h
im2sequence_op.cpp
im2sequence_op.h
lrn_op.cpp
lrn_op.h
mul_op.cpp
mul_op.h
multiclass_nms_op.cpp
multiclass_nms_op.h
op_param.cpp
op_param.h
pool_op.cpp
pool_op.h
prelu_op.cpp
prelu_op.h
prior_box_op.cpp
prior_box_op.h
relu_op.cpp
relu_op.h
reshape_op.cpp
reshape_op.h
resize_op.cpp
resize_op.h
scale_op.cpp
scale_op.h
sigmoid_op.cpp
sigmoid_op.h
slice_op.cpp
slice_op.h
softmax_op.cpp
softmax_op.h
transpose_op.cpp
transpose_op.h

项目简介

Multi-platform high performance deep learning inference engine (『飞桨』多平台高性能深度学习预测引擎）

发行版本 20

v2.7-beta

全部发行版

贡献者 87

B C H Q H 石 Z Y H X S
全部贡献者

开发语言

  • C++ 82.3 %
  • Swift 4.1 %
  • CMake 3.0 %
  • Metal 2.6 %
  • C 2.3 %