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.
gabby1224
commented
1 year ago
我在windows, x64 Native Tools Command Prompt for vs 2019 上运行了demo: imageclassify, facedetector, posedetector, readingcomprehension, objectdetector, 模型是从darrenyao87-tnn-model 下的，前面4个都能正常出结果， 运行objectdetecor+yolov5/(yolov5s-permute.tnnproto,tnnmodel)时，选的assets/004545（人马狗的图片），说number of objects is 119, predictions上全是密密麻麻的粉红色框框； 然后我又按照文档试了另一个model(mobilenet_v2-ssd)，程序退出： Unhandled exception at 0x000007FECC7757A0 (TNN.dll) in demo_x86_objectdetector.exe
我用自己的model(yolov5-5.0, yolov5s)，改了一些demo得到的：detector中的label，yolo.h中ditect_dim，yolo.cc中GetMat()，其他没有作改变。运行demo_x86_objectdectector, prediction还是奇怪的粉红色框框，只不过数目少了一些。 我需要做啥才能让这个结果是正常的呢，希望得到帮助。
我转换tnn模型的过程是这样的： 我在ubuntu, gpu，pyTorch机器上训练yolov5,得到权重.pt ，用export导出了.onnx，然后用镜像得到tnnproto,tnnmodel, 然后在windows，vs2019运行example/windows/x86中的build_msvc_native.bat