You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
 
 
nihui aed05aa851
pnnx fuse more function to module (#4351)
3 years ago
..
pass_level0 save foldable constants in file for reducing memory usage (#4337) 3 years ago
pass_level1 implement MultiheadAttention kdim vdim (#4347) 3 years ago
pass_level2 pnnx convert torch bitwise left_shift right_shift (#4349) 3 years ago
pass_level3 pnnx convert torch bitwise left_shift right_shift (#4349) 3 years ago
pass_level4 PNNX is an open standard for PyTorch model interoperability (#3262) 4 years ago
pass_level5 pnnx fuse more function to module (#4351) 3 years ago
pass_ncnn pnnx fuse more function to module (#4351) 3 years ago
CMakeLists.txt pnnx fuse more function to module (#4351) 3 years ago
ir.cpp pnnx convert torch bitwise left_shift right_shift (#4349) 3 years ago
ir.h save foldable constants in file for reducing memory usage (#4337) 3 years ago
main.cpp pnnx fp16 option for ncnn and onnx weight type (#4350) 3 years ago
onnx.proto pnnx save onnx zero (#4077) 3 years ago
pass_level0.cpp save foldable constants in file for reducing memory usage (#4337) 3 years ago
pass_level0.h save foldable constants in file for reducing memory usage (#4337) 3 years ago
pass_level1.cpp match inplace slice copy pattern, rewrite copy uses (#4338) 3 years ago
pass_level1.h pnnx export weight inside moduleop (#3902) 3 years ago
pass_level2.cpp pnnx fuse more function to module (#4351) 3 years ago
pass_level2.h pnnx fuse more function to module (#4351) 3 years ago
pass_level3.cpp save foldable constants in file for reducing memory usage (#4337) 3 years ago
pass_level3.h save foldable constants in file for reducing memory usage (#4337) 3 years ago
pass_level4.cpp pnnx fold constant (#3521) 4 years ago
pass_level4.h PNNX is an open standard for PyTorch model interoperability (#3262) 4 years ago
pass_level5.cpp pnnx fuse more function to module (#4351) 3 years ago
pass_level5.h save foldable constants in file for reducing memory usage (#4337) 3 years ago
pass_ncnn.cpp pnnx fp16 option for ncnn and onnx weight type (#4350) 3 years ago
pass_ncnn.h PNNX is an open standard for PyTorch model interoperability (#3262) 4 years ago
save_ncnn.cpp pnnx fp16 option for ncnn and onnx weight type (#4350) 3 years ago
save_ncnn.h pnnx fp16 option for ncnn and onnx weight type (#4350) 3 years ago
save_onnx.cpp pnnx fp16 option for ncnn and onnx weight type (#4350) 3 years ago
save_onnx.h pnnx fp16 option for ncnn and onnx weight type (#4350) 3 years ago
save_onnx_cxxabi_bridge.cpp pnnx save onnx zero (#4077) 3 years ago
storezip.cpp PNNX is an open standard for PyTorch model interoperability (#3262) 4 years ago
storezip.h PNNX is an open standard for PyTorch model interoperability (#3262) 4 years ago
utils.cpp PNNX is an open standard for PyTorch model interoperability (#3262) 4 years ago
utils.h PNNX is an open standard for PyTorch model interoperability (#3262) 4 years ago