Jing Gu

Core dumped error

2

When I used the command: ```./build/tests ~Timing``` It shows: ``` All tests passed (119213 assertions in 5 test cases) Segmentation fault (core dumped) ``` But it is ok when using:...

how to choose the hyperparameter when pre-training

1

It is really great work. I wonder if you could share the hyperparameter that is used to pre-train the DialoGPT, especially the hyperparameters for GPT-small

In the original paper, best window size is 8, why the default window size here is 15?

I need to train glove on Twitter data, will a shorter window size like 6 helps? Thanks

environment set up problem

1

I was setting the environment as in the ```README.md``` file. However, I met an issue when installing Matterport3D simulators when executing ```cmake -DEGL_RENDERING=ON ..```: ``` (envdrop) jinggu@jinggu-MS-7B79:~/Projects/R2R-EnvDrop/build$ cmake -DEGL_RENDERING=ON .....

When doing source image DDIM inversion, should the text prompt be empty?

5

In the paper, when doing DDIM inversion, the text prompt is a description of the real image. But in your code, the text prompt is an empty string. Could you...

It does not work when I change it to stable diffusion 1.5.

1

When I change 'CompVis/stable-diffusion-v1-4' to 'runwayml/stable-diffusion-v1-5', the generated image is either a black image, or an image without keeping the original feature map. Do you have any suggestions on how...

Dose detailed caption improve the performance?

3

I have a few questions about the video caption. 1. I noticed that during the training, the caption in the video CSV is quiet short. Will the performance improve if...

I have a few questions about the video caption. 1. I noticed that during the training, the caption in the video CSV is quiet short. Will the performance improve if...