Data from Automated plankton image analysis using convolutional neural networks

Datasets and code from Luo et al., "Automated plankton image analysis using convolutional neural networks." Limnology and Oceanography Methods.

Data include:

1) 42,564 item training library, sorted in 108 classes,

2) 42,548 item test set for filtering thresholds, sorted into 38 groups. These images are independent from the training library, and are used for setting the thresholds for post-classification filtering.
CSV file: Luo_etal_FT_images_pred.csv contains the image name, predicted class, predicted probability, and validated group. Note that the file class_to_group.csv is needed to match up the class names to the group names.

3) 75,000 item fully random, validated set for confusion matrix calculations, sorted into 38 groups. This set is a representation of the full dataset, selected at random after classification. 
CSV file: Luo_etal_confusionmatrix_images.csv contains the image name, predicted class, predicted probability, and validated group. Note that the file class_to_group.csv is needed to match up the class names to the group names.

Scripts and programs:

1) Segmentation.zip contains the scripts and executables for the segmentation program.

2) Plankton_template.zip contains the archived version of the SparseConvNet program used in manuscript (current version available at: https://github.com/btgraham/SparseConvNet or https://github.com/facebookresearch/SparseConvNet)
Note that google-sparsehash is necessary for running SparseConvNet.
Also, plankton_epoch-150.cnn are the weights from the training used in the manuscript, and should be placed in the /weights folder if you want to replicate the classifications.