zbw4034

The author's code is compiled on TX2,which is aarch64,you should check cmakelists.txt and cmakeprebuild.sh carefully and make some changes

yolov3从82,94,106层输出三个特征图，之后通过yolo层进行特征融合，这里没有写的83层是yolo层，作者把这部分放到主函数里做了~

Hi,Chen! It`s really exciting to find your project after spending so much time searching for something useful about yolov3-caffe and I really appreciate that you have implemented this and release...

my error is this: [libprotobuf ERROR google/protobuf/text_format.cc:245] Error parsing text-format caffe.NetParameter: 2622:20: Message type "caffe.LayerParameter" has no field named "upsample_param". WARNING: Logging before InitGoogleLogging() is written to STDERR F0627 20:21:10.194875...

and in darknet2caffe.py,i just modified the python path of caffe. the order i type in in the terminal is just "python darknet2caffe.py cfg/yolov3-voc.cfg cfg/yolov3-voc_final.weights cfg/yolov3.prototxt cfg/yolov3.caffemodel" @ChenYingpeng

FINALLY I SUCCEED ! After a whole day searching and trying,I succeed to finish converting.The main reason I failed is that I have install 3 versions of caffe(ssd,R-fcn,standard caffe-master),which makes...

@aaronduino because we want to test our own caffemodel,which is different from the one provided.

@yiboliu31 @Ghustwb 请问你们用的是哪个版本的mobilenetssd？是chuanqi305的那个吗

ok，thx

@myih Hi!I am using tensorrt4.0 and I met the same question:`virtual void nvinfer1::plugin::DetectionOutput::configure(const nvinfer1::Dims*, int, const nvinfer1::Dims*, int, int): Assertion numPriors*numLocClasses*4 == inputDims[param.inputOrder[0]].d[0]' failed` how did you solve it?Could you...