Jumponthemoon

In the code of ddd sample,i saw the ground truth of orientation is constructed by the alpha. I did some research about alpha and rotation_y in the label file.Seems like...

Step Preprocess the data (Extract landmark and crop the image by dlib)

4

Would you explain how to use and preprocess lrw dataset in detail?Cause the dataset i downloaded containing .mp4 files and don't know how to deal with it.

Issue when applying mobileNet

1

Hi,i tried the mobilenetV2 you provided in the other repo.It successfully converted to the desired engine.But when i run the runDet command and evaluation command.It throws out the exception: terminate...

Hi there, Shout out to your great work! I'm wondering how many generated images you used for training? I saw there are 100 prompts in the provided txt file, does...

Hi, It is an interesting and amazing work! I have a question about the cross-attention part in the code. I see there are two line to get self-attention and cross-attention...

Cityscapes training and joint training

5

Hi, I'm running the training code for training cityscapes and eval on acdc. I encountered some problems: 1.For warm up training, i found the training is not corrected conducted, it...

Hi, Thank you for your amazing work! I noticed that the code currently focuses on image-based raindrop generation. I'm having some difficulty replicating the realistic raindrop motion seen in the...