BIGJUN777

Results 8 issues of BIGJUN777

Hi, there. Thank you for releasing your great work. I tried to train LAMA on my own dataset these days. During training, as shown in the below picture, R1 gradient...

Hi there, **When I used the _get_landmarks_from_directory( )_ function as recommended [here](https://github.com/1adrianb/face-alignment#process-an-entire-directory-in-one-go), it was strange that the detected results of some images were wrong. Please check the images below:** ![image](https://user-images.githubusercontent.com/35102882/148214858-a01456ca-8e2e-4c0b-8064-f491169adf23.png)...

Hi there, I have some confusing problems below: 1. As mentioned in the paper, there is a 200M of parameters difference between SR_256 and SR_1024. ![image](https://user-images.githubusercontent.com/35102882/180937667-186bd4e0-d61a-4ab3-80e1-0f7fc90c4d71.png) However, based on the...

Hi, there. In the paper, you described rescaling residual connections, while I did not find this in the current [code](https://github.com/openai/guided-diffusion/blob/27c20a8fab9cb472df5d6bdd6c8d11c8f430b924/guided_diffusion/unet.py#L256). Did I miss something?

Hello, I am sorry to ask question frequently. These days, I setup my computer with GPU supported: CUDA8, which is available. And tried to run the tracker_nodes, but got the...

Hello: In the past two weeks, I mainly use the particle_tracker on my jobs, I successfully run the package in ROS and realized object-tracking. But I couldn't get the ideal...

Hi, I came across some problems on Figure3 in your paper. I don't know how you collected the ground truth and corresponding interaction. Could you give me some more details...

Hi there. When I trained on the TikTok dataset which has 340 videos, it was weird that it would generate some cotton-shaped artifacts around the person. Have you encountered this...