Giters
OpenPPL
/
ppl.nn
A primitive library for neural network
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
1277
Watchers:
35
Issues:
119
Forks:
215
OpenPPL/ppl.nn Issues
Linux ARM cpu平台,ppl 跑conv winogradb4f3 出现结果mismatch
Updated
a month ago
Comments count
1
请问一下 No Pad优化的实现在代码中哪个位置呢
Updated
2 months ago
请问算子融合的实现主要在哪里呢?
Updated
2 months ago
pplnn cpu 推理 异常crash
Updated
2 months ago
不支持 SpaceToDepth 算子
Updated
2 months ago
Comments count
1
cuda build error
Updated
2 months ago
Comments count
1
build pplnn error
Closed
2 months ago
When I run build.sh to compile the project, a compilation error occured.
Updated
3 months ago
Comments count
1
ARM平台是否可以跑int8的推理
Updated
5 months ago
多模型pipeline的示例
Closed
8 months ago
推理误差排查
Closed
8 months ago
关于全局engine,其他线程引用导致的性能下降问题
Closed
10 months ago
Comments count
4
Crash with ONNX Split operator
Updated
a year ago
Got wrong output shape when run a Gemm op(transB=0) use cuda
Closed
a year ago
Comments count
4
(Ask) why InferInheritedType handle int8 to fp16 out?
Updated
a year ago
Comments count
3
Floating point exception (core dumped) ?
Updated
a year ago
Comments count
4
使用x86 engine运行resnet50 fp16 onnx模型 core dump
Closed
a year ago
The compilation passed, but an error was reported in test phase
Updated
2 years ago
Comments count
2
Install Error
Updated
2 years ago
Comments count
1
获取模型推理结果(GetOutputs)耗时长
Closed
2 years ago
Comments count
2
Segmentation fault at ppl::nn::x86::X86Kernel::DumpOutputTensors
Closed
2 years ago
Comments count
5
如何使用cmake的将ppl.nn和依赖ppl.nn的代码一同编译?
Closed
2 years ago
Comments count
3
malloc_consolidate(): invalid chunk size
Closed
2 years ago
Comments count
2
pplnn save-input 得到的NDARRAY的 shape不正确
Closed
2 years ago
Comments count
1
linux compile error protobuf static assertion failed
Closed
2 years ago
Comments count
3
pplnn run mobilenet v2 model failed. (use cuda)
Closed
2 years ago
Comments count
7
Onnx run error
Closed
2 years ago
Comments count
2
Slice op question
Closed
2 years ago
Comments count
1
请问支持int8在高通芯片上cDSP进行推理吗?
Closed
2 years ago
交叉编译RISCV平台可执行文件报错
Closed
2 years ago
Comments count
1
Floating point exception (core dumped)
Closed
2 years ago
Comments count
1
Floating point exception (core dumped) occured when using cuda engine
Closed
2 years ago
Comments count
1
x86支持fp16推理吗?支持的话输入数据是要转为fp16类型或者还是用fp32数据推理过程会自动转为fp16?pplnn目前只支持T4 gpu吗 别的gpu支持吗
Closed
2 years ago
ppl推理问题 runtime.Run()执行次数不同,单次推理时间不同,对于resent50,Run10次,单次ppl_speed是4.7,Run1000次,单次ppl_speed是23.4
Closed
2 years ago
PPL.NN slower than onnxruntime
Closed
2 years ago
ubuntu python build failed....
Closed
2 years ago
Comments count
1
x86 build failed;
Closed
2 years ago
Bilieaner resize support
Closed
2 years ago
Comments count
1
macOS arm M1 build error
Closed
2 years ago
macOS arm m1 build error
Closed
2 years ago
Comments count
3
error
Closed
2 years ago
Comments count
1
【gemm_fp32_fma performance】常用shape下,gemm_fp32_fma和tensorflow1.15 eigen matmul性能几乎持平?
Closed
2 years ago
Comments count
9
cuda convolution kernel input question.
Closed
2 years ago
Comments count
12
compile error
Closed
2 years ago
Comments count
2
TypeError: pyppl.nn.cuda.EngineFactory: No constructor defined!
Closed
2 years ago
Comments count
1
[CUDA] `RuntimeBuilder.Preprocess()` causes subsequent CUDA function calls to fail
Closed
2 years ago
Comments count
9
Error when both CUDA and x86 engines are enabled.
Closed
2 years ago
Comments count
3
error using DBNet models
Closed
2 years ago
ImportError: cannot import name 'nn' from 'pyppl' (unknown location)
Closed
2 years ago
Comments count
5
link error in minimum cmake project
Closed
2 years ago
Comments count
4
Previous
Next