I spent the day manually labeling frames for #DeepLabCut ( #MachineLearning model to track #animals in videos).
Incredibly mind-numbing, but hopefully my new model will be good enough to work through the terabytes of videos.
If the model can actually track up to 18 piglets, that would be amazing!
#AcademicChatter #AnimalBehavior #AnimalBehaviour
#DeepLabCut
From @nvladimus : "We have opened the #mesoSPIM official User Forum" at https://forum.image.sc/tag/mesospim alongside #Fiji #ImageJ #ilastik #BiaPy #napari #DeepLabCut and many other open source softwares for bioimage informatics.
@choldgraf visited the #deeplabcut team @TrackingActions 's lab, EPFL, in early August to learn how they used open-source tools to share work. Learn how a @mystmarkdown mini-hackathon facilitated learning and accelerated contributions to the project https://2i2c.org/blog/2024/deeplabcut-myst-hackathon/ 📖
Seen on the #NeuroMethods slack:
Any suggestions for algorithms to track pupil in mice? (Not #DeepLabCut )
Good morning #ISOT2024!
Today's the last poster session of the meeting @ISOT2024Iceland@twitter.com, so come and stop by to chat.
I'll try to be around during most breaks!
If you're interested in #DeepLabCut (or #MoSeq), definitely come and chat!
I have added a hands-on #tutorial to the Assessing Animal Behavior lecture. The tutorial covers the GUI-based use of #DeepLabCut 💻, a software package for markerless pose estimation of animals 🐭🔍 It’s aimed at #neuroscience students with no or little programming knowledge. Feel free to share it with your students and colleagues ☺️
🌍 https://www.fabriziomusacchio.com/teaching/teaching_assessing_animal_behavior/05_deeplabcut
#Ethology #MachineLearning #behaviourscience #BehavioralScience #animalbehavior
New this week @Nature, Mackenzie and Alexander Mathis (@TrackingActions) were still early in their careers when their #DeepLabCut software created a sensation. Now they’re using it to support other young scientists. 🧪 https://www.nature.com/articles/d41586-024-01474-x
Anyone here working on #PoseEstimation #animalbehavior #neuroethology ?
You may be interested in the free and open-source Python 🐍 package I’m currently working on, together with @adamltyson @bd_peri and others.
It’s called movement, and it’s made for analysing the pose tracks produced by pose estimation frameworks, like #DeepLabCut and #SLEAP.
Website: https://movement.neuroinformatics.dev
GitHub: https://github.com/neuroinformatics-unit/movement
It’s still in early development 🏗️ but we appreciate feedback/feature requests.
Check out the detailed thread on our team’s mastodon account: @neuroinformatics
Well, it's time again: I'm officially looking for a new #PostDoc
Please share far and wide!
My expertise lies in behavioral ecology, focused on mammalian chemical communication. I've also been exploring #DeepLabCut & #MoSeq for automated behavior analysis.
For more info about my research & background, visit my newly revamped website https://tsievert.com/
Shout-out to my friend Ramin at websplash GmbH for the fantastic redesign!
We recently made our lab's handbook for #DeepLabCut public!
It's not finished yet and quite rough on the edges, but you can watch us (well, me) struggle in the process of trying to establish #DeepLabCut in our lab.
The handbook also includes #HowTo.s and scripts to run everything on a HPC cluster.
Long-term aim is to also include guides and scripts for #KeypointMoseq.
Check it out at https://github.com/LassanceLab/DLC_handbook
@egonw Thanks a lot for the advice! I guess my license needs to follow the original #DeepLabCut license, right? In this case GNU Lesser General Public License v3.0.
And thanks for reminding me about the CITATION.cff, I'll get right on it.
I need some feedback from more experienced #OpenData #OpenScience folks.
My lab is trying to be as open as possible, so we just published our progress making a #DeepLabCut model (including all annotated frames).
Please let me know if the README is missing anything crucial or if I missed any other best practices.
https://github.com/LassanceLab/primary_DeepLabCut_model
@kevinbolding Good question, but I'm not 100% sure myself.
I'm new to the neuro world, so bear with me.
We are trying to identify which receptors, pathways, and brain areas are activated upon contact with the odor.
This is then combined with behavioral observations using #DeepLabCut
At least that's the plan. We've encountered a bunch of (administrative) roadblocks, so I can't really give a more sophisticated answer.
@TrackingActions Would you be interested in additional data for the #SuperAnimal TopViewMouse-5k model?
We're just getting started with #DeepLabCut and will work on two Peromyscus species (plus wild Mus musculus and maybe Apodemus)
🤗 We think it’s time for a challenge/friendly competition ! 🪄
Reply below with your best #deeplabcut video/gif (tag #depelabcut ) and our dev team will pick a few winners for some awesome DLC Swag! Tweet/Toot 🐘by May 5th 💜
Just in case you thought #ImageAnalysis was all about cells
https://forum.image.sc/t/is-facial-recognition-of-racoons-possible-with-deeplabcut/76826/2?u=dnmason
Does anybody have experience with #DeepLabCut and a workflow including #GoogleCollab?
I'm looking at the documentation and feeling a bit lost.
Super extra plus points if you have used a pre-trained #ModelZoo and annotated extra frames for better performance.
@ecologies #AnimalBehavior #AnimalBehaviour #ComputerVision @academicchatter
Going forward, #DeepLabCut updates will come via medium (and GitHub of course), but not the bird. This is sad, as the science Twitter community, I believe, was so important in getting out the word early on our very first code release and paper. But, it’s not okay anymore 💔…
📣🚨To get the latest updates on our code releases going forward, please see our medium blog http://www.deeplabcut.medium.com and all resources linked on our homepage: http://DeepLabCut.org - take care #deeplabcutters 🙏🏼💜
Had an amazing time being an (online) TA for the #Neurokit on Modern Approaches to Behavioural Analyses, such as DLC from Cajal_Training! Thanks to Alexander Mathis & Danbee Kim & everyone else for the great time! #onlinehub #londonhub #deeplabcut
Client Info
Server: https://mastodon.social
Version: 2025.07
Repository: https://github.com/cyevgeniy/lmst