Takugo comments

Results 16 comments of


                                            Takugo

CenterFace-small指的是什么

同问。没有找到CenterFace-small相关的link。

python ./src/faster.py --demo ./kitti_format/kitti/val.txt --data_dir ./kitti_format --calib_dir ./kitti_format/data/kitti/calib/ --load_model ./kitti_format/exp/KM3D_res18/Model_rtm3d_epoch_300.pth --gpus 0 --arch res_18

I got similar issues. The program just hang there and print nothing after "loaded xxx.pth"

你好，pytorch转onnx是check失败，使用onnxsim进行简化也失败了，请问是什么原因？

> numpy=1.18.3 > torch=1.2.0 > torchvision=0.4.0 用的onnx是哪个版本？

你好，pytorch转onnx是check失败，使用onnxsim进行简化也失败了，请问是什么原因？

我把onnx版本降到1.4.1可以进行torch转onnx，但是onnx simplier还是失败。

Could you provide a command to run "tools/demo.py"?

Same. Ask for a simple script to run demo.py. And it is a bit hard to use.

Tusimple labeling tool

Hi guys, lane detection UFLD repo has already provided labeling tool to generate label map from TuSimple json format

Some questions about large training loss

I also found that there were increasing loss result and it cannot coverage, what about you guys setting of `parser.add_argument()` ?

Some questions about large training loss

This ain't a simple issue.

Some questions about large training loss

> > Hi, I download you code and BSDS500 dataset to learn edge detection model and print the loss of each iteration, however, the training losses are very large and...

How to generate json files from my own data set

Hi guys, I have some lane instance segmentation image dataset, but how to transform it into TuSimple json format. Lane instance has been annotated using polygon coordinates.