Tengine
Tengine copied to clipboard
OAID
Tengine is a lite, high performance, modular inference engine for embedded device
I trained a detection model (centernet, backbone shufflenet), then I change the format :pth->onnex->tmfile. I tried to use tengine-lite(x86 linux) to debug my code. Here is my code: ``` c++...
Hi， When I do “./convert_tool -f paddle -p model.pdmodel -m model.pdiparams -o result.tmfile”，error info appears as following.  These 10 ops are not supported {elementwise_sub,elementwise_div,relu,split,concat,reshape2,transpose2,nearest_interp_v2,bilinear_interp_v2,arg_max,} Could you please add the...
Hi， Could tengine support Conditional Channel Weighting ，Spatial Weight Computation and Cross-Resolution Weight Computation layer computation already？ If not ，how to implement thest by ourselves？ BR
請問作者在建立 NXP iMX8 Plus 的 BSP 環境是幾版的 我下載 Tengine Lite release v1.4 for NXP 的版本，照著 README.md 進行編譯時，沒有辦法直接編譯成功， sample/console/tengine/linux-arm64-v8a/lib/libtim-vx.so 在編譯時會提示缺少部分 lib， 後來將 TimVX 裡面的某些 lib 加進去後可以編譯成功，但是在板子上執行時還是會執行失敗  想請問作者在建立 NXP iMX8 Plus...
Hi，dear Tengine When I want to test some examples on the ubuntu vim3 with galcore 6.4.6.2.Following the step below, "[khadas@Khadas tengine-lite]# ./example/tm_classification_timvx -m squeezenet_uint8.tmfile -i cat.jpg -r 1 -s 0.017,0.017,0.017...
Hi, As we know, the sota pose estimation net liteHRnet is so famous in the are of pose estimation.So could Tengine support this efficient liteHRnet model to compared with the...
Hi I am trying to compile Tengine with fp16 support on rockchip 3568, which supports the armv8.2 instruction set. When the flag TENGINE_ARCH_ARM_82 is enabled, the compilation failed with the...
Hi， 1、 Moreover regarding to tengine quantified(int8) tool, are you sure there is the implemention of most of op almost up to 100 different op in tengine？ 2、 How many...
**basic:** Os:Ubuntu-18.04LTS gcc:7.5.0 CPU:Intel(R) Celeron(R) CPU J1900 @ 1.99GHz complie command cmake .. make -j4 cmake infomation: Infomation Summary: CMake infomation: CMake version: 3.22.3 CMake generator: Unix Makefiles CMake building...
使用的crnn模型是tengine官方给的crnn_lite_dense.tmfile 量化命令如下： ./quant_tool_uint8 -m ./crnn_lite_dense.tmfile -i ./images/ -o crnnquant5.tmfile -g 1,32,277 -w 127.5,0,0 -s 0.007843,0,0 -z 1 -b 0 ---- Tengine Post Training Quantization Tool ---- Version : v1.2, 08:50:20...
