search

Holliemin9090 / Mammographic-mass-CAD-via-pseudo-color-mammogram-and-Mask-R-CNN

Fully automatic computer-aided mass detection and segmentation via pseudo-color mammograms and Mask R-CNN
http://arxiv.org/abs/1906.12118
Other
24 stars 9 forks source link

5-fold cross validation #10

Open latoa opened 3 years ago

latoa commented 3 years ago 
   "We used 5-fold cross validation in our paper..."

Could you tell me where (in the code) you are using 5-fold cross validation?

Holliemin9090 commented 3 years ago

The images and masks can be partitioned into training and validation sets in each cross validation. In 'mamo_CAD.py': For example, these following directories can point to the cross validation folder where the data are MAMOGRAM_IMAGE_DIR ="/cross_validation1/image/" MAMOGRAM_MASK_DIR = "/cross_validation1/mask/"

In the image and mask folder, the files can be partitioned into "/train/" and "/val/" folders.