Problem with generating labeled videos


I have compeleted the video analysis and tried to generate the labeled videos. However, after running “deeplabcut.create_labeled_video”, there are not any labeling in new videos.

Anyone met the same issue or can solve this issue?

Many thanks!

Is no file created?
can you post the output from the terminal?
What p-cutoff value did you set in the config.yaml file?


Thank you for quick response.

It generated videos that don’t have labelling. So they seems like original videos. The p-cutoff value is default value.

I am using Jupyter Notebook, The output is as following:


Thank you so much!

can you run deeplabcut.plot_trajectories(config_path, ['videopath']) and post the plots here?

I see your images are VERY large… did you change the max_input_size value before training? as otherwise, the network would not have used any data for training, and that is why there are no labels…


Regarding this point, what are the errors you get when you run evaluate_network? How do the images look?

Thank you so much for your suggestion. Through a lot of troubleshooting, this issue has been solved. The solution sounds funny. Because I use to label frames using labeling in small dotsize, e.g. 1, thus in the labeled videos, the labelings are also very small, which is almost unseeable. Once change to larger dotzise, everything works normal.

Also, because I combined multiple images (multiple camers) into one, so the images are very large. Right now, DLC works very well to process these large images. Do you have any other good ideas to analyze these large images or is there any potential problem of using large image?

Thank you so much!

1 Like

Ah! yes, the dot size :slight_smile: glad it’s working. There is no issue on the larger frames, as long as it fits in your GPU! You might have to run lower batch sizes for analysis (i.e. typically you change “batch size” to be 64, etc, but it might require batch size 16, or 32 for your larger images. It just means processing data would be slower, but likely not an issue…

Appreciate! I will try that.:smile:

1 Like