Gotta-C
Gotta-C
how to get calibration.table if the yolov3 backbone was modified? Turns the results when I run INT8: New calibration table will be created to build the engine trt-yolo-app: ../builder/cudnnBuilder2.cpp:685: virtual...
thx a lot and I will try.
I have modify the Cross-compiler to x86_64 and compiled,tested your model and got some errors. Error parsing text-format caffe.NetParameter: 2622:20: Message type "caffe.LayerParameter" has no field named "upsample_param". i guess...
I have tried your model and worked ! But still some errors in darknet2caffe(cfgfile, weightfile, protofile, caffemodel) Traceback (most recent call last): File "darknet2caffe.py", line 429, in darknet2caffe(cfgfile, weightfile, protofile,...
It worked on yolov3.cfg,yolov3.weight now. My dataset only one class,still have the problem.
I used grep checked,only detect.py has classes 80,not that problem.In training,i have modify all the filters to 18,because 1 class,and the weights is only 505k,compared to yolov3.weights is 248M,I have...
weight to caffemodel .May I have your Q number or wechat?
how to modify in yolov3?
> Hi Zeynep Gokce, I had rewrote cfg YOLOv3 with backbone ResNet50 following some instructions but I don't remember the link. I also tried training YOLOv3 with this cfg and...
hi,@cdcseacave . I used open3d to segment plane and filter out some outliers based on DensifyPointCloud result scene_dense.ply . And how can I convert the new .ply to .mvs to...