search

Innse / MOTCat

33 stars 3 forks source link

What script is used in CLAM? How big of a GPU is needed to run MOTCat? #7

Closed lichencan closed 3 months ago

lichencan commented 6 months ago

"Use the WSI processing tool provided by CLAM to extract resnet-50 pretrained 1024-dim feature for each 256 256 patch (20x), which we then save as .pt files for each WSI. So, we get one pt_files folder storing .pt files for all WSIs of one study." use：python create_patches_fp.py --source DATA_DIRECTORY --save_dir RESULTS_DIRECTORY --patch_size 256 --preset tcga.csv --seg --patch --stitch and python create_patches_fp.py --source DATA_DIRECTORY --save_dir RESULTS_DIRECTORY --patch_size 256 --seg --process_list process_list_edited.csv Thank you very much for your project, and I look forward to your reply.

Innse commented 3 months ago

Hi. First, features of patches with a size of 512x512 are extracted at level 0 using CLAM. These features are then resized to 256x256, resulting in 20x features. Regarding GPU, MOTCat typically requires a GPU with a memory capacity of less than 1,000MB, making it compatible with most GPUs available today.