获取文件夹内容时发生错误.
名称 最后提交 最后更新
CMakeLists.txt Upgrade of Model_optimize_tool (#2624)
activation_compute.cc add rsqrt op, test=develop (#2176)
activation_compute.h add rsqrt op, test=develop (#2176)
affine_channel_compute.cc create backends directory and move hardware backends into it (#1954)
affine_channel_compute.h ad ops for faster rcnn, including affine_channel, anchor_generator, generate_proposals and roi_align (#1895)
anchor_generator_compute.cc create backends directory and move hardware backends into it (#1954)
anchor_generator_compute.h ad ops for faster rcnn, including affine_channel, anchor_generator, generate_proposals and roi_align (#1895)
argmax_compute.cc add elementwise_sub and modify argmax (#1964)
argmax_compute.h publish lite (#1800)
argmax_compute_test.cc add elementwise_sub and modify argmax (#1964)
assign_compute.cc create backends directory and move hardware backends into it (#1954)
assign_compute.h add floor op,elementwise_div op and assign op test=develop (#1882)
assign_value_compute.cc add assign_value and hard_sigmoid, add fluid_type (#1983)
assign_value_compute.h add assign_value and hard_sigmoid, add fluid_type (#1983)
axpy_compute.cc create backends directory and move hardware backends into it (#1954)
axpy_compute.h publish lite (#1800)
axpy_compute_test.cc publish lite (#1800)
batch_norm_compute.cc create backends directory and move hardware backends into it (#1954)
batch_norm_compute.h publish lite (#1800)
batch_norm_compute_test.cc enable native compiling on raspberry pi and rk3399 (#2021)
beam_search_compute.cc create backends directory and move hardware backends into it (#1954)
beam_search_compute.h create backends directory and move hardware backends into it (#1954)
beam_search_decode_compute.cc Transformer pr (#2214)
beam_search_decode_compute.h publish lite (#1800)
box_clip_compute.cc create backends directory and move hardware backends into it (#1954)
box_clip_compute.h
box_coder_compute.cc
box_coder_compute.h
calib_compute.cc
calib_compute.h
calib_compute_test.cc
cast_compute.cc
cast_compute.h
collect_fpn_proposals_compute.cc
collect_fpn_proposals_compute.h
compare_compute.cc
compare_compute.h
concat_compute.cc
concat_compute.h
concat_compute_test.cc
conditional_block_compute.cc
conditional_block_compute.h
conv_compute.cc
conv_compute.h
conv_depthwise.cc
conv_depthwise.h
conv_direct.cc
conv_direct.h
conv_gemmlike.cc
conv_gemmlike.h
conv_transpose_compute.cc
conv_transpose_compute.h
conv_winograd.cc
conv_winograd.h
crop_compute.cc
crop_compute.h
decode_bboxes_compute.cc
decode_bboxes_compute.h
decode_bboxes_compute_test.cc
density_prior_box_compute.cc
density_prior_box_compute.h
distribute_fpn_proposals_compute.cc
distribute_fpn_proposals_compute.h
dropout_compute.cc
dropout_compute.h
dropout_compute_test.cc
elementwise_compute.cc
elementwise_compute.h
elementwise_compute_test.cc
expand_compute.cc
expand_compute.h
fc_compute.cc
fc_compute.h
fill_constant_compute.cc
gather_compute.cc
gather_compute.h
generate_proposals_compute.cc
generate_proposals_compute.h
grid_sampler_compute.cc
grid_sampler_compute.h
gru_compute.cc
gru_compute.h
gru_unit_compute.cc
gru_unit_compute.h
im2sequence_compute.cc
im2sequence_compute.h
increment_compute.cc
increment_compute.h
instance_norm_compute.cc
instance_norm_compute.h
interpolate_compute.cc
interpolate_compute.h
is_empty_compute.cc
is_empty_compute.h
layer_norm_compute.cc
layer_norm_compute.h
layer_norm_compute_test.cc
layout_compute.cc
layout_compute.h
lod_reset_compute.cc

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

全部贡献者

开发语言

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