Cellpose model for Digital Phase Contrast images
Creators
- 1. EPFL SV IBI-SV UPDANGELO
- 2. EPFL SV PTECH PTBIOP
Description
Name: Cellpose model for Digital Phase Contrast images
Data type: Cellpose model, trained via transfer learning from ‘cyto’ model.
Training Dataset: Light microscopy (Digital Phase Contrast) and Manual annotations (10.5281/zenodo.5996883)
Training Procedure: Model was trained using a Cellpose version 0.6.5 with GPU support (NVIDIA GeForce RTX 2080) using default settings as per the Cellpose documentation
python -m cellpose --train --dir TRAINING/DATASET/PATH/train --test_dir TRAINING/DATASET/PATH/test --pretrained_model cyto --chan 0 --chan2 0
The model file (MODEL NAME) in this repository is the result of this training.
Prediction Procedure: Using this model, a label image can be obtained from new unseen images in a given folder with
python -m cellpose --dir NEW/DATASET/PATH --pretrained_model FULL_MODEL_PATH --chan 0 --chan2 0 --save_tif --no_npy
Files
Files
(26.6 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:6e56986eaa3aff0cd58e3e0b2c6d5fef
|
26.6 MB | Download |