Comments (10)
We'd fine-tune the VSCyto3D model with data acquired on Mantis as we discussed at the lab meeting yesterday.
I think @edyoshikun is already training these models without needing code changes. (Recall that VSCyto3D and VSNeuromast are the same architecture trained on different data.) The incompatibility I mentioned in OP for VSCyto3D is between the old config files we published (e.g. on zenodo for the mantis preprint) and the current code base. This is a minor issue since that zenodo record points to a pinned version of VisCy that works properly with the files.
from viscy.
My reading of the code suggests that all of these can be instantiated by passing parameters to UNet21d.
The VSCyto2D models are made from the FCMAE class for both pre-training and fine-tuning.
My suggestion is:
- Merge #71
- Merge #84
- Merge #88
- Tag v0.1.0rc0
- Prepare v0.1.0 release artifacts (weights and config files) based on the new code base
from viscy.
@ziw-liu. This order of operation makes sense to me. Are you renaming what we thought of release 0.2.0 as 0.1.0? Totally fine to call the next release 0.1.0. Please update the milestone for clarity if you mean something else.
from viscy.
@edyoshikun can you confirm the details for the neuromast model and comment on compatibility requirements of the mantis revision?
from viscy.
Correct! Neuromast model was trained with the current HEAD of the main. I confirm.
from viscy.
Hi @ziw-liu We'd fine-tune the VSCyto3D model with data acquired on Mantis as we discussed at the lab meeting yesterday. Please start a PR with changes that enable training of both VSCyto3D and VSNeuromast models with the main. This PR should be a priority since we need it to iterate on the models for mantis Fig. 1 next.
It seems like 2D FCMAE branch will require development such that the weights are compatible with the main. I don't follow this point, can you point to a few lines of code to illustrate? This can be the second PR.
Thanks for iterating quickly on these.
from viscy.
It seems like 2D FCMAE branch will require development such that the weights are compatible with the main. I don't follow this point, can you point to a few lines of code to illustrate?
The network module changed, among other things. For example:
https://github.com/mehta-lab/VisCy/pull/71/files#diff-9af609b0fdd9a3358d7099a616e29f1fefdab379a92388bca856ab99944fc67c
from viscy.
@ziw-liu How about the following order of operation?
- Create a release candidate 0.2.0 that works with current weights of VSCyto3D, VSNeuromast, and VSCyto2D models. My reading of the code suggests that all of these can be instantiated by passing parameters to
UNet21d
. You can rename this modelUNeXt2
to match the nomenclature in the preprint. - Update
FullyConvolutionalMAE
model such that the weights can be transferred from FCAMAE to VSCyto2D models.
from viscy.
Let's also update the Readme.md and add the preprint link here as well.
from viscy.
Let's also update the Readme.md and add the preprint link here as well.
from viscy.
Related Issues (20)
- Contrastive Learning Implementation HOT 1
- Normalization for patches ome-zarr HOT 2
- organize application scripts on GitHub rather than disk
- Illustrative test datasets HOT 4
- Predict module not giving expected output HOT 3
- API for 2D UNeXt2 model construction needs clarity HOT 2
- WIP: refactor contrastive learning code with virtual staining code HOT 6
- Overflow error seen in training and prediction steps
- switching to tensorboard logger for organelle phenotyping
- document published models on Wiki HOT 1
- Unify stem implementation HOT 1
- Time sampling for positive pair
- Support loading data from a specific resolution of a .zarr pyramid HOT 1
- CLI for multiple training tasks HOT 4
- Move to NumPy style docstrings? HOT 1
- Model size mismatch error during prediction HOT 3
- Implicit negative sampling
- Hard-coded stem stride in `ContrastiveEncoder` HOT 1
- Update the projection head (normalization and size).
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from viscy.