how to train my own dataset ?

[cdongxian]

No description provided.

[agadetsky]

Dear @cdongxian,

To add your own dataset you have to implement the dataset initialization pipeline in get_datasets function

turtle/dataset_preparation/data_utils.py

Line 70 in 9b8bbb7

def get_datasets(dataset, transform, root_dir='./data'):

Also, don't forget to specify the number of classes in your newly added dataset in datasets_to_c dictionary. You can specify the ground truth number or, in case you don't know it, a meaningful estimate of the number of clusters in your dataset.

turtle/utils.py

Line 99 in 9b8bbb7

datasets_to_c = {

After that, follow the README instructions in the repo to precompute representations. If you have ground truth labels for your dataset, then also use precompute_labels.py to precompute the labels for evaluation purposes in run_turtle.py script. If you don't have them, follow solutions of the similar issues, i.e., #1 and #5.

After everything above is prepared, you can run training using run_turtle.py script, specifying your dataset in the command line.

Let me know if that has resolved your issue.

Best,
Artyom