Learningm

Hard to run eval_video_official.py & some training questions

14

Hi, I encounter some problems when using the code. I followed data/Readme.md and download the chair data then preprocess it. After that, I got nothing inside the output folder (e.g....

How to generate the annotation file?

2

Hi, this work is pretty cool ! I come across several problems when I use the repo. 1) What's the difference between ava_train_v2.2.pkl & ava_train_v2.2_with_fair_0.9.pkl ? What's the meaning of...

Stuck in predicting connectivity when running quick_start.py

3

Hi, when I run quick_start.py, it seems stucking in predicting connectivity step. I tried several models but I failed to pass thourgh this step, shown as following pictures. Could you...

How to reproduce MobilePose v2 result? Which diagonal edge for normalized?

4

Hi, I am interested in these amazing work but I wonder how to reproduce mobilepose v2 result. How to understand the loss **'per vertex MSE normalized on diagonal edge length'**...

Any plan to update the test.py?

1

I download the IconGUI package and find the script structure is different from this repo. Could you update the test.py for inference demo in this repo ?

Dataset link failed

8

Hi, I can not download the dataset from the link you provided, could you update the link? Thanks.

I see the coarse_train config setting is N_iters = 0 in nerf_unbounded_default.py. https://github.com/sunset1995/DirectVoxGO/blob/main/configs/nerf_unbounded/nerf_unbounded_default.py#L16 What's the purpose of this setting? It seems we skip the coarse stage. Another question, how to...

I tried the repo but encountering some problem, it seems missing checkpoints. I found in the colab demo, the model.ckpt-239999 are successfully loaded. INFO:tensorflow:Restoring parameters from train_dir_initFlow_Fence/model.ckpt-239999 INFO:tensorflow:Restoring parameters from...

Hi, your paper use a 160-category TU-berlin dataset for training and testing, where can I download the dataset? Thank you very much.

 How to generate smaller model instead of the 2G+ model ?