ncnn:ncnn是针对移动平台进行了优化的高性能神经网络推理框架
140 浏览量
2021-05-10
18:35:47
上传
评论
收藏 12.01MB ZIP 举报
ncnn:ncnn是针对移动平台进行了优化的高性能神经网络推理框架 （1346个子文件） 
.astylerc 623B squeezenet_v1.1.bin 4.71MB squeezenet_v1.1.param.bin 4KB squeezenet_v1.1.caffemodel 4.72MB tf_types.cc 16KB tf_attributes.cc 4KB .clang-format 4KB ncnn_generate_shader_spv_header.cmake 42KB ios.toolchain.cmake 21KB ncnn_add_layer.cmake 20KB iossimxc.toolchain.cmake 2KB iossimxc-x64.toolchain.cmake 2KB iosxc.toolchain.cmake 1KB iosxc-arm64.toolchain.cmake 1KB ncnn_add_shader.cmake 1KB c906.toolchain.cmake 1KB himix200.toolchain.cmake 1KB hisiv500.toolchain.cmake 1KB hisiv300.toolchain.cmake 1KB hisiv600.toolchain.cmake 1022B himix100.toolchain.cmake 1002B riscv64-unknown-linux-gnu.toolchain.cmake 941B jetson.toolchain.cmake 938B v831.toolchain.cmake 935B ncnn_generate_shader_comp_header.cmake 882B mips-mti-linux-gnu.toolchain.cmake 790B host-c.clang.toolchain.cmake 764B host-c.gcc.toolchain.cmake 758B arm-linux-gnueabi-c.toolchain.cmake 688B riscv64-unknown-elf.toolchain.cmake 673B riscv32-unknown-elf.toolchain.cmake 673B aarch64-linux-gnu-c.toolchain.cmake 620B mipsisa64r6el-linux-gnuabi64.toolchain.cmake 616B arm-linux-gnueabi.toolchain.cmake 580B arm-linux-gnueabihf.toolchain.cmake 568B mipsisa32r6el-linux-gnu.toolchain.cmake 532B powerpc64le-linux-gnu.toolchain.cmake 530B host.gcc.toolchain.cmake 526B mips64el-linux-gnuabi64.toolchain.cmake 523B ncnn_generate_rvv_source.cmake 520B ncnn_generate_arm82_source.cmake 514B aarch64-linux-gnu.toolchain.cmake 512B ncnn_generate_avx2_source.cmake 511B riscv64-linux-gnu.toolchain.cmake 510B mipsel-linux-gnu.toolchain.cmake 507B host.clang-m32.toolchain.cmake 484B host.gcc-m32.toolchain.cmake 478B host.gcc-c++03.toolchain.cmake 459B run_test.cmake 275B pi3.toolchain.cmake 170B build-android.cmd 3KB padding_pack4to8.comp 22KB normalize_reduce_sum4_fp16_to_fp32_pack8.comp 17KB padding_pack1to8.comp 17KB padding_pack8to4.comp 15KB normalize_reduce_sum4_fp32_pack8.comp 14KB crop_pack4to8.comp 14KB convolution_pack8_1x1s1d1.comp 13KB padding_pack8.comp 13KB padding_pack4.comp 12KB normalize_reduce_sum4_fp16_to_fp32_pack4.comp 12KB normalize_reduce_sum4_fp16_to_fp32.comp 12KB padding_pack8to1.comp 11KB padding_pack1to4.comp 11KB padding_pack4to1.comp 11KB permute_pack8.comp 11KB normalize_reduce_sum4_fp32.comp 11KB permute_pack4to8.comp 11KB normalize_reduce_sum4_fp32_pack4.comp 11KB permute_pack1to8.comp 10KB binaryop_broadcast.comp 10KB permute_pack8to1.comp 10KB reshape_pack8.comp 10KB crop_pack8to4.comp 10KB binaryop_broadcast_pack8.comp 10KB permute_pack4.comp 10KB reshape_pack4to8.comp 9KB binaryop_broadcast_pack4.comp 9KB convolution_pack8_3x3s1d1_winograd23_transform_output.comp 9KB deconvolutiondepthwise_group_pack8.comp 9KB convolution_pack8_3x3s1d1_winograd23_gemm.comp 9KB deconvolution_pack8.comp 8KB deconvolutiondepthwise_group_pack4to8.comp 8KB innerproduct_gemm_wp8.comp 8KB convolutiondepthwise_group_pack8.comp 8KB permute_pack8to4.comp 8KB deconvolution_pack4to8.comp 8KB packing_pack1to8_fp16_to_fp32.comp 8KB padding.comp 8KB packing_pack1to8_fp32_to_fp16.comp 8KB convolution_pack8.comp 8KB convolution_pack4_1x1s1d1.comp 8KB packing_pack8to1_fp32_to_fp16.comp 8KB convolutiondepthwise_group_pack4to8.comp 8KB packing_pack1to8.comp 8KB packing_pack8to1_fp16_to_fp32.comp 8KB flatten_pack8.comp 8KB convolution_pack4_3x3s1d1_winograd23_transform_output.comp 8KB packing_pack8to1.comp 7KB convolution_pack8_3x3s1d1_winograd23_transform_input.comp 7KB共 1346 条
- 1
- 2
- 3
- 4
- 5
- 6
- 14
资源评论
