bolt
bolt copied to clipboard
Bolt is a deep learning library with high performance and heterogeneous flexibility.
Hello, thank you for your team’s awesome work! I have some questions about using the bolt framework. Here's my working environment: - target platform: Android-aarch64 - build platform: Linux -...
1. X2bolt -d onnx -m model -i PTQ #输出为model_ptq_input.bolt 2. ./post_training_quantization -p model_ptq_input.bolt -i INT8_FP32 -b true -q NOQUANT -c 0 -o false 3. 推理报错如下: [ERROR] thread 121948 file /home/xxx/project/bolt/compute/tensor/src/fully_connected.cpp...
请问二值化的linear和matmul操作是否支持?
CONVOLUTION_ALGORITHM_GEMM不支持nchw排布的输入,如果模型第一层是dilated conv,选到CONVOLUTION_ALGORITHM_GEMM会计算错误:https://github.com/huawei-noah/bolt/blob/master/compute/tensor/src/cpu/arm/convolution.cpp#L72
展开前: ``` c #define DOT_A4B16C4(a, b, c) \ { \ c.x += (a.x * b.s0 + a.y * b.s1 + a.z * b.s2 + a.w * b.s3); \ c.y +=...
bolt的开发人员你们好,我在使用的过程中遇到如下问题,希望你们可以抽空帮忙看一下 问题1:在使用C API时,我发现并没有多少示例代码,而且我根据API也没有发现设置运行时浮点精度的方式(即模型为fp32的,但是按照fp16的精度计算),难道只有将模型转换为fp16的才能跑fp16代码吗? 问题2:如果只有fp16的模型才能跑fp16代码,那么请问如何设置输入,因为fp16的tensor也是fp16的,难道需要外部给进去fp16的数据吗?
We have sucessully build bolt inference library without model converter on Raspberry 3 model B(armv7). #67 ```bash export CFLAGS="-march=armv7-a -mfpu=neon-vfpv4 " export CXXFLAGS="-march=armv7-a -mfpu=neon-vfpv4 " ./install.sh --target=linux-armv7_blank --converter=off -t 4...
对bolt进行了benchmark测试,install 阶段也关闭了 profile功能,只看模型总耗时,发现达不到文章里提到的性能,不知道是我哪里用错了,请帮忙看一下 如图所示  文章里提到对squeezent1.1在高通888 half情况下耗时为3.949ms,我在小米11 高通888实测fp16case耗时为avg_time:7.443091ms/data; 为了验证,我实际测试了一下 https://github.com/huawei-noah/bolt/blob/master/docs/USER_HANDBOOK.md中提到的 resnet50这个网络,利用X2BOLT工具,我的命令如下./benchmark -a GPU -w 10 -l 10 -m ResNet-50_f16.bolt  高通888fp16耗时情况为 Benchmark Result: Output Tensor prob desc: dt:DT_F16 memFormat:DF_NCHW stride(1000,1,1)...
fix build error on linux aarch64 Using `bash ./install.sh --target=linux-aarch64` builds this lib will cause a error. It will download protocolbuffers from https://github.com/protocolbuffers/protobuf/releases/download/v3.1.0/protoc-3.1.0-.zip.