TNN
TNN copied to clipboard
TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its c...
**1. 使用环境(environment)** - OS: Ubuntu - OS Version: Ubuntu 20.04.4 LTS **2. Github版本** - branch:docker - commit(optional): **3. 详细描述bug 情况 (Describe the bug)** A clear and concise description of what...
**1. 环境(environment)** - Build OS and Version: Mac - RunTime OS Version: Android - RunTime DEVICE: ARM/HUAWEI_NPU **2. Github版本** - branch:Master - commit(optional): **3. 编译方式(compile method)** CMake完整编译参数(full cmake arguments) **4....
**1. 使用环境(environment)** **Ubuntu** **3. 详细描述bug 情况 (Describe the bug)** **使用yolov5-3.0训练的onnx模型,调用\tools\onnx2tnn\onnx-converter里的onnx2tnn.py模型转换。-optimize=0 -half=0,生成tnn模型文件。 调用时会报错,但是同样条件下,调用官方提供的yolov5模型正常。** [onnx.zip](https://github.com/Tencent/TNN/files/6921510/onnx.zip) 
**1. 环境(environment)** - Build OS and Version: Ubuntu 20.04 - RunTime OS Version: Android - RunTime DEVICE: OPENCL **2. Github版本** - branch:master - commit(optional): **3. 编译方式(compile method)** CMake完整编译参数(full cmake arguments)...
TNN的模型里的HardSwish层有两种情况,一种是input0和input1的shape完全一样,都是(b, c, h, w),一种情况是input0的shape是(b, c, h, w),input1的shape是(b, c, 1, 1),x86的非AVX实现 `for (int b = 0; b < batch; b++) { for (int c = 0; c < channel; c++) {...
不知道是不是我操作不对造成的,如果方便的话,希望能得到你们的帮助,我可以提供onnx,tnn文件,感谢!
**1. 环境(environment)** - Build OS and Version: Mac - RunTime OS Version: Android - RunTime DEVICE: ARM/OPENCL **2. Github版本** - branch:master - commit(optional): **3. 编译方式(compile method)** 在安卓studio中编译提示cmake有问题: CMake Error at...