fidoptDFCAN
DFCAN, the Fourier channel attention network of the BioSR paper, with its authors' single-image models (wide field to linear SIM, one model a structure), run as their predict.py runs it.
SynthesisCPUversion DL-SR 7f9c886, pre-trained_models.zip of figshare 13531292 (sha256 31a57833)FLUORESCENCE, FLUORESCENCEMIT
Run it
With its KonfAI app, at the benchmark's settings (the fidopt app repositories are private for now: a Hugging Face token with access opens them):
pip install konfai-apps
| Configuration | Command | |
|---|---|---|
| microtubules | Get the app | konfai-apps infer fideus-labs/fidopt-synthesis:DFCAN_MTs -i image.nii.gz -o out |
| F-actin | Get the app | konfai-apps infer fideus-labs/fidopt-synthesis:DFCAN_Factin -i image.nii.gz -o out |
Where it works
Its place on each kind of problem it has results on, among the methods ranked there. A method that leads one problem can trail another: read the one closest to yours.
| Problem | Place | Ranked | Datasets |
|---|---|---|---|
| Wide-field to structured illumination, 2D synthesis | not ranked yet | 1 of 4 | |
| Wide-field to structured illumination, 2D synthesis | not ranked yet | 1 of 4 |
Results
| Dataset | # | Read by | Score | Failed | Time s |
|---|---|---|---|---|---|
| BioSR wide-field to linear SIM, F-actin, 2D | 1 | MAE | 0.0 | 0 | 13 |
| BioSR wide-field to linear SIM, microtubules, 2D | 1 | MAE | 0.0 | 0 | 12 |
- Reference
- Qiao et al., Nature Methods 2021