usc-infolab / rddc2020 Goto Github PK

Hello Sir, Do you have any tutorial to how set it up. Thank you .
If you dont please record one and share with us.
Massive thanks

Hello, how is your integrated forecasting and integrated model designed? thank you for your reply.

I have already run 100+ epoches, but precision, recall and mAP are all zero continiously. Any help will be so appreciated!

Hello, has your article been published? Where can I see your article?

作者你好，请问设置的iou阈值都很高了0.9999，conf阈值也大于0.2了，为什么还有这么多预测框呢？重叠在一起，感觉不太正常呢

In a file such as last_100_100_640_16.pt what does each number mean? I'm guessing 640 is the input size, and 16 is maybe the batch size, but what are the other numbers?

In the file last_95_448_32_aug2.pt, what does the 95 represent?

Thank you in advance!

Hello,

There is a typo in the command given to train the model. There is an 's' missing to 'weights/yolov5x.pt'.

The command should be :

python3 train.py --data data/road.yaml --cfg models/yolov5x.yaml --weights weights/yolov5x.pt --batch-size 64

Thank you for this great work !

I implement the code successfully and i can inference my datasets. but i donot know how to evaluate the test1 and test2 datasets which are lack of annotations file. Only we get the test results throught uploading the evaluated result to official websites online?
After i check the code, i think the way to get the f1 score is by running this command below:
python test.py --weights weights/IMSC/last_95_640_16.pt --data data/road.yaml
I will be appreciated if any help is offered.
thank you in advance.

I am trying to reproduce your results but after training with default hyperparams I achived poor f1-score.
Could you please share the hyperparams file you used?