cellpose v2.0.4

Cellpose 2.0 is here! Now you can train models in the loop with the Cellpose graphical interface. Upgrade to the latest version with

pip install cellpose --upgrade

Check out the twitter thread and preprint for details.

Read how to use human-in-the-loop yourself in the gui docs, and check out the full human-in-the-loop video.

Also, read more about the model zoo and how to use user-trained models in the models docs.

Cellpose v1.0.2

fixes some bugs with the GUI and the colab and min_train_masks

last stable release of Cellpose 1.0.

pip install cellpose==1.0.2

cellpose v1.0

stable release

• fixes some bugs in 0.8 with plotting and flow visualization in GUI
• merges pull request for stitch_threshold bug (#390)
• allows images with empty masks, depending on new flag --min_train_masks that is set to 5 by default. if fewer than min_train_masks in an image it is not used
• resample set to default True as in older releases
• model reloading per image turned off in CLI and class so that model is faster
• optional _masks.tif loading in GUI
• warning for user if masks are to be saved in np.uint32

cellpose v0.8.0

• now install omnipose with pip! pip install omnipose
• added PR #416 which removed global logging settings, now turn on logging in a notebook with from cellpose.io import logger_setup; logger,log_file=logger_setup(), and from the command line with --verbose
• added support for >2^16 masks with np.uint32, if there are <2^16 masks then the masks are returned as np.uint16 still
• fixed bug with torch.long on windows

cellpose | omnipose v0.7.3

Fixes to the following bugs:

• --no_npy inverted settings
• omni not passed through to remove_bad_flow_masks

Omnipose (cellpose v0.7.2)

Introducing Omnipose, a collaboration between the Stringer, Wiggins, and Mougous labs written by @kevinjohncutler. Read more about it in our preprint and on the Omnipose README. Important new features are:

• cyto2_omni model for slight improvement over the 'cyto2' Cellpose model
• bact_omni model for bacteria phase contrast segmentation (huge improvement over Cellpose models trained on bacteria, which you can demo with the bact model)
• omni option to use Omnipose mask reconstruction with your Cellpose model to help reduce over-segmentation (off by default)
• cluster option to force DBSCAN clustering in Omnipose mask reconstruction. This is off by default and turned on automatically when the average cell diameter is less than diam_threshold. Note theat scikit-learn is necessary for DBSCAN, and a CLI prompt will ask you to download it when you run --omni.

Several saving options have been included as well:

• in_folders saves outputs into separate folders named masks, outlines, etc. (off by default)
• dir_above saves output in the directory above the image directory (useful to have images next to masks etc.) (off by default)
• save_txt turns on ImageJ outline saving (now off by default)
• save_ncolor uses @kevinjohncutler's N-color algorithm to save masks with repeating but non-touching integers (typically 4 or fewer, 5 or 6 when necessary), which allows segmentations of thousands of cells to be presented without as many colors (which can become very hard to distinguish otherwise). Use in combination with a color map to visualize output.

Several bug fixes and pull requests are included in this release as well.

cellpose v0.6.1

fixes bugs with

• 2D resizing of flows
• training with CUDA in torch
• __main__.py relative imports -> absolute imports

cellpose v0.6

Pytorch is now the default deep neural network software for cellpose. Mxnet will still be supported. To install mxnet (CPU), run pip install mxnet-mkl. To use mxnet in a notebook, declare torch=False when creating a model, e.g. model = models.Cellpose(torch=False). To use mxnet on the command line, add the flag --mxnet, e.g. python -m cellpose --dir ~/images/ --mxnet. The pytorch implementation is 20% faster than the mxnet implementation when running on the GPU and 20% slower when running on the CPU.

Dynamics are computed using bilinear interpolation by default instead of nearest neighbor interpolation. Set interp=False in model.eval to turn off. The bilinear interpolation will be slightly slower on the CPU, but it is faster than nearest neighbor if using torch and the GPU is enabled.

cellpose v0.5

• sped up 3D segmentation by reducing padding
• tile_overlap as a parameter
• fixed bug with batch_size in CLI

cellpose v0.1.0.1

• automated testing implemented
• dynamics are run at rescaled size (will be faster for images with cells larger than 30 pixels in diameter)
• pyinstaller binaries created from this release