cellpose

cellpose is an anatomical segmentation algorithm written in Python 3 by Carsen Stringer and Marius Pachitariu. For support, please open an issue.

We make pip installable releases of cellpose, here is the pypi. You can install it as pip install cellpose[gui].

You can try it out without installing at cellpose.org. Also check out these resources:

Cellpose 2.0

• paper on biorxiv

• talk

• twitter thread

• human-in-the-loop training protocol video

Cellpose 1.0

• paper on biorxiv (see figure 1 below) and in nature methods

• twitter `thread`_

• Marius’s `talk`_

Basics:

• Installation
  • Built-in model directory
  • M1 Mac installation
  • AMD GPU ROCm installation
  • Common issues
  • Dependencies
• GUI
  • Starting the GUI
  • Using the GUI
  • Segmentation options
  • Training your own cellpose model
  • Contributing training data
  • Keyboard shortcuts
• Inputs
  • 3D segmentation
• Settings
  • Channels
  • Diameter
  • Resample
  • Flow threshold
  • Mask threshold
  • 3D settings
• Outputs
  • _seg.npy output
  • PNG output
  • Native ImageJ ROI archive output
  • (Legacy ImageJ Interface) ROI manager compatible output for ImageJ
  • Plotting functions
• Models
  • Model Zoo
  • Full built-in models
    • Cytoplasm model (‘cyto’)
    • Nucleus model (‘nuclei’)
    • Cytoplasm 2.0 model (‘cyto2’)
  • Other built-in models
    • TissueNet models
    • LiveCell models
  • User-trained models
• Training
• OpenVINO
• FAQ

Examples:

• In a notebook
• Command line
  • Command Line Usage

Reference:

• Cellpose API Guide
  • Cellpose class
    • Cellpose
      • Cellpose.eval()
  • CellposeModel
    • CellposeModel
      • CellposeModel.eval()
      • CellposeModel.loss_fn()
      • CellposeModel.train()
  • SizeModel
    • SizeModel
      • SizeModel.eval()
      • SizeModel.train()
  • Metrics
    • aggregated_jaccard_index()
    • average_precision()
    • boundary_scores()
    • flow_error()
    • mask_ious()
  • Flows to masks
    • compute_masks()
    • follow_flows()
    • get_masks()
    • labels_to_flows()
    • map_coordinates()
    • masks_to_flows()
    • masks_to_flows_cpu()
    • masks_to_flows_gpu()
    • remove_bad_flow_masks()
    • steps2D()
    • steps3D()
  • Image transforms
    • average_tiles()
    • convert_image()
    • make_tiles()
    • move_axis()
    • move_min_dim()
    • normalize99()
    • normalize_img()
    • pad_image_ND()
    • random_rotate_and_resize()
    • reshape()
    • reshape_and_normalize_data()
    • reshape_train_test()
    • resize_image()
    • unaugment_tiles()
  • Plot functions
    • disk()
    • dx_to_circ()
    • image_to_rgb()
    • interesting_patch()
    • mask_overlay()
    • mask_rgb()
    • outline_view()
    • show_segmentation()
  • I/O functions
    • add_model()
    • get_image_files()
    • imread()
    • masks_flows_to_seg()
    • remove_model()
    • save_masks()
    • save_rois()
    • save_server()
    • save_to_png()
  • Utils functions
    • TqdmToLogger
      • TqdmToLogger.flush()
      • TqdmToLogger.write()
    • circleMask()
    • distance_to_boundary()
    • download_url_to_file()
    • fill_holes_and_remove_small_masks()
    • get_mask_perimeters()
    • get_masks_unet()
    • get_perimeter()
    • masks_to_edges()
    • masks_to_outlines()
    • outlines_list()
    • outlines_list_multi()
    • outlines_list_single()
    • remove_edge_masks()
    • stitch3D()
  • Network classes
    • CPnet
    • batchconvstyle
    • convdown
    • convup
    • downsample
    • make_style
    • resdown
    • resup
    • upsample
  • Core functions
    • use_gpu()
  • All models functions
    • Cellpose
      • Cellpose.eval()
    • CellposeModel
      • CellposeModel.eval()
      • CellposeModel.loss_fn()
      • CellposeModel.train()
    • SizeModel
      • SizeModel.eval()
      • SizeModel.train()
• Cellpose CLI
  • Command Line Usage
    • Named Arguments
    • Hardware Arguments
    • Input Image Arguments
    • Model Arguments
    • Algorithm Arguments
    • Output Arguments
    • Training Arguments