Skip to content
Snippets Groups Projects
Commit f09ab2be authored by Fabrice Daian's avatar Fabrice Daian
Browse files

updates

parent 117b0c59
No related branches found
No related tags found
No related merge requests found
Show whitespace changes
Inline Side-by-side
Showing
with 24 additions and 22 deletions
README.md
+ 24
− 22
View file @ f09ab2be
# Code & Data Repository # Code, Models & Data Repository
## *μPIX : Leveraging Generative AI for Enhanced, Personalized and Sustainable Microscopy* ## *μPIX : Leveraging Generative AI for Enhanced, Personalized and Sustainable Microscopy*
### Gabriel Bon, Daniel Sapede, Cédric Matthews, and Fabrice Daian Preprint BioRXiv [![DOI:10.1101/2024.10.25.620201](images/badge_preprint_mupix.svg)](https://doi.org/10.1101/2024.10.25.620201)
#### Gabriel Bon, Daniel Sapede, Cédric Matthews, and Fabrice Daian
----
----
| | Paper |
|--------------------------|--------------------------------------------------------------------------------------------------------------------------------|
| Preprint | [![DOI:10.1101/2024.10.25.620201](images/badge_preprint_mupix.svg)](https://doi.org/10.1101/2024.10.25.620201) |
| Paper | To be published |
##### <u>Dataset & pre-trained µPIX Models</u>
| | Dataset | pre-trained µPIX Models | | | Dataset | pre-trained µPIX Models |
|--------------------------|--------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------| |--------------------------|--------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------|
| CSBDeep | [download](https://sync.lis-lab.fr/index.php/s/sy3SrGgqNafbP5X/download) | [download](https://sync.lis-lab.fr/index.php/s/9SxkR2QH3Z79Bbc/download) | | CSBDeep | [download](https://sync.lis-lab.fr/index.php/s/sy3SrGgqNafbP5X/download) | [download](https://sync.lis-lab.fr/index.php/s/9SxkR2QH3Z79Bbc/download) |
...@@ -18,11 +12,17 @@ ...@@ -18,11 +12,17 @@
| Metrology | [download](https://sync.lis-lab.fr/index.php/s/mYDRTeAQxMxNPPJ/download) | [download](https://sync.lis-lab.fr/index.php/s/degZsCxN7ZXxeB6/download) | | Metrology | [download](https://sync.lis-lab.fr/index.php/s/mYDRTeAQxMxNPPJ/download) | [download](https://sync.lis-lab.fr/index.php/s/degZsCxN7ZXxeB6/download) |
| Demo Notebooks | | ##### <u>Demo Notebooks</u>
|--------------------------|--------------------------------------------------------------------------------------------------------------------------------|
| Inference on Metrology dataset using pre-trained µPIX model | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1EbV04iv141q7ebVUOErJupYboaCV40OD?usp=drive_link) | * Use a pre-trained µPIX model to denoise images (metrology dataset) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1EbV04iv141q7ebVUOErJupYboaCV40OD?usp=drive_link)
* Train a µPIX model from scratch (metrology dataset)
| | Code & System Requirements |
## Install required µPIX Environment and Sources ([Tutorial VIDEO](https://sync.lis-lab.fr/index.php/s/GeNyYdLHMCRTfS9))
<details>
<summary>Click to expand</summary>
| Requirements | |
|--------------------------|--------------------------------------------------------------------------------------------------------------------------------| |--------------------------|--------------------------------------------------------------------------------------------------------------------------------|
| Python | 3.11 | | Python | 3.11 |
| Tensorflow | 2.14 | | Tensorflow | 2.14 |
...@@ -30,10 +30,6 @@ ...@@ -30,10 +30,6 @@
| OS | Linux | | OS | Linux |
----
----
## Install required µPIX Environment and Sources ([Tutorial VIDEO](https://sync.lis-lab.fr/index.php/s/GeNyYdLHMCRTfS9))
...@@ -61,7 +57,7 @@ and then proceed to the installation of required Python packages: ...@@ -61,7 +57,7 @@ and then proceed to the installation of required Python packages:
```bash ```bash
pip install -r mupix/requirements.txt pip install -r mupix/requirements.txt
``` ```
</details>
...@@ -69,6 +65,9 @@ pip install -r mupix/requirements.txt ...@@ -69,6 +65,9 @@ pip install -r mupix/requirements.txt
## Use Case n°1 - Use a pre-trained µPIX model to denoise an image dataset ([Tutorial VIDEO](https://sync.lis-lab.fr/index.php/s/ftw9fdGacJyyfBq)) ## Use Case n°1 - Use a pre-trained µPIX model to denoise an image dataset ([Tutorial VIDEO](https://sync.lis-lab.fr/index.php/s/ftw9fdGacJyyfBq))
<details>
<summary>Click to expand</summary>
µPIX comes with 3 ptre-trained models along with their respective datasets: µPIX comes with 3 ptre-trained models along with their respective datasets:
| | Dataset | pre-trained µPIX Models | | | Dataset | pre-trained µPIX Models |
...@@ -174,9 +173,14 @@ python mupixinfer.py --experiment_path "./experiments/metrology_experiment/" ...@@ -174,9 +173,14 @@ python mupixinfer.py --experiment_path "./experiments/metrology_experiment/"
Once finished, the denoised images are stored inside ```./experiments/metrology_experiment/predictions/``` directory. Once finished, the denoised images are stored inside ```./experiments/metrology_experiment/predictions/``` directory.
</details>
## Use case n°2 - Train a µPIX model from scratch using a custom dataset ## Use case n°2 - Train a µPIX model from scratch using a custom dataset
<details>
<summary>Click to expand</summary>
Move to the `mupix` directory: Move to the `mupix` directory:
```bash ```bash
cd mupix cd mupix
...@@ -348,8 +352,6 @@ If the training stops because it reached the maximum number of epochs defined in ...@@ -348,8 +352,6 @@ If the training stops because it reached the maximum number of epochs defined in
python mupixtraining.py --experiment_path "./experiments/metrology_experiment" --retrain python mupixtraining.py --experiment_path "./experiments/metrology_experiment" --retrain
``` ```
### 2.4 - Inference on the test dataset ### 2.4 - Inference on the test dataset
The `mupixinfer.py` script allows you to use a pre-trained µPIX model to denoise a dataset located in the `test` directory inside the experiment path. The `mupixinfer.py` script allows you to use a pre-trained µPIX model to denoise a dataset located in the `test` directory inside the experiment path.
...@@ -374,7 +376,7 @@ Saved prediction: ./experiments/metrology_experiment/predictions/X_StageData0001 ...@@ -374,7 +376,7 @@ Saved prediction: ./experiments/metrology_experiment/predictions/X_StageData0001
All predictions saved successfully! All predictions saved successfully!
Data predicted at ./experiments/metrology_experiment/predictions ! Data predicted at ./experiments/metrology_experiment/predictions !
``` ```
</details>
......
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment