create-li

**Compiling environment** Linux version 3.10.0-957.el7.x86_64 GCC 5.4 TensorRT-7.0.0.11/ CUDA 10.0 **CMake Infos：** ``` `set(COMMON_INCLUDE ../includes/common) set(YAML_INCLUDE ../includes/yaml-cpp/include) set(YAML_LIB_DIR ../includes/yaml-cpp/libs) include_directories(${CUDA_INCLUDE_DIRS} ${TENSORRT_INCLUDE_DIR} ${OpenCV_INCLUDE_DIRS} ${COMMON_INCLUDE} ${YAML_INCLUDE}) link_directories(${YAML_LIB_DIR}) add_executable(arcface_trt main.cpp arcface.cpp) target_link_libraries(arcface_trt ${OpenCV_LIBRARIES}...

The compilation environment of onnx to tensorrt in arcface project： 1、cuda 10.0 2、tensorrt 6.0 Compilation error: kbool is not a member of nvinfer1::DataType 

How to convert yoloface-500k model to tensorrt

1

caffemodel or darknet model ,How to convert yoloface-500k model to tensorrt

cesium怎么让整个场景的光更亮点？

2

使用enableLighting=true，没有效果，请问环境光照怎么设置

pre-trained VQGAN of 256*256 resolution ratio

3

It takes too long to train STAGE1(about 16days), so I want to add my own dataset for fine-tuning. Can you release pre-trained VQGAN model in STAGE1? Thanks a lot~

自己训练stage2，stage3模型，推理时，设置w不等于0和1时，嘴唇会出现色块，有点偏绿色，紫色等

4

请问，基于vqgan训练stage3后，推理时，w不设置0,1时，就会出现人嘴唇的出现色块，但是w=0,1时就没有问题。

why In stage 3, train the GAN loss to nan and the tensor of the network output image to nan？

6

Modify the cross layer connections of the networks in stages 2 and 3. In stage 3, train the GAN loss to nan and the tensor of the network output image...

eigen and ceres emcmake error

1

I also encountered the same problem, as eigen and ceres cannot compile On ubuntu20.0 ,Emsdk=3.0.0 .emcmake error.