Spaces:
Sleeping
Sleeping
## MoNuSeg Preparation | |
The original PanNuke dataset has the following style using .xml annotations and .tiff files with a size of $1000 \times 1000$ pixels: | |
```bash | |
βββ testing | |
β βββ images | |
β β βββ TCGA-2Z-A9J9-01A-01-TS1.tif | |
β β βββ TCGA-44-2665-01B-06-BS6.tif | |
... | |
β βββ labels | |
β βββ TCGA-2Z-A9J9-01A-01-TS1.xml | |
β βββ TCGA-44-2665-01B-06-BS6.xml | |
... | |
βββ training | |
βββ images | |
βββ labels | |
``` | |
For our experiments, we resized the dataset images to $1024 \times 1024$ pixels and convert the .xml annotations to binary masks: | |
```bash | |
βββ testing | |
β βββ images | |
β β βββ TCGA-2Z-A9J9-01A-01-TS1.png | |
β β βββ TCGA-44-2665-01B-06-BS6.png | |
... | |
β βββ labels | |
β β βββ TCGA-2Z-A9J9-01A-01-TS1.npy | |
β β βββ TCGA-44-2665-01B-06-BS6.npy | |
... | |
βββ training | |
βββ images | |
βββ labels | |
``` | |
Everythin can be extracted using the [`cell_segmentation/datasets/prepare_monuseg.py`](cell_segmentation/datasets/prepare_monuseg.py) script. | |