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 cross-platform capability, high performance, model compression and code pruning. Based on ncnn and Rapidnet, TNN further strengthens the support and performance optimization for mobile devices, and also draws on the advantages of good extensibility and high performance from existed open source efforts. TNN has been deployed in multiple Apps from Tencent, such as Mobile QQ, Weishi, Pitu, etc. Contributions are welcome to work in collaborative with us and make TNN a better framework.
zyg519
commented
3 months ago
tnn的模型对其工具采用默认opencl版本编译，板子使用opencl3.0库，执行检查工具报错如下： root@NVTEVM:/mnt/sd$ ./model_check -p SqueezeNet/squeezenet_v1.1.tnnproto -m SqueezeNet/squeezenet_v1.1.tnnmodel -d OPENCL proto: SqueezeNet/squeezenet_v1.1.tnnproto model: SqueezeNet/squeezenet_v1.1.tnnmodel device: OPENCL init model config success! tnn precision 1 I/tnn: Init [File source/tnn/device/opencl/opencl_runtime.cc][Line 120] OpenCL version: CL_TARGET_OPENCL_VERSION 200 CL_HPP_TARGET_OPENCL_VERSION 120 CL_HPP_MINIMUM_OPENCL_VERSION 110 E/tnn: LoadLibraryFromPath [File source/tnn/device/opencl/opencl_wrapper.cc][Line 257] load func (clEnqueueAcquireGLObjects) from (/usr/lib/libOpenCL.so) failed! E/tnn: LoadLibraryFromPath [File source/tnn/device/opencl/opencl_wrapper.cc][Line 258] load func (clEnqueueReleaseGLObjects) from (/usr/lib/libOpenCL.so) failed! E/tnn: LoadLibraryFromPath [File source/tnn/device/opencl/opencl_wrapper.cc][Line 259] load func (clCreateFromGLTexture) from (/usr/lib/libOpenCL.so) failed! I/tnn: Init [File source/tnn/device/opencl/opencl_runtime.cc][Line 167] Create common opencl context E/tnn: FeedInputData [File tools/model_check/model_checker.cc][Line 483] Generate Random input... ./model_check: symbol lookup error: ./model_check: undefined symbol: _ZN3tnn8Instance19ForwardWithCallbackESt8functionIFvRSt6vectorIPNS_4BlobESaIS4_EEPNS9LayerInfoEEESB 看着像是版本问题导致的函数加载不成功，请问tnn是否目前尚未支持opencl3.0?