Question on DESC2.0.3 K-means initialization

[marvinquiet]

Hi,

Thank you for the great work in applying Autoencode in single-cell data clustering as well as removing the batch effect. When I tried the K-means initialization on the DESC2.0.3 version, I got TypeError: train() got an unexpected keyword argument 'n_clusters'.

Here is how I call the function:

adata = desc.train(adata,
                       dims=[adata.shape[1], 128, 32],
                       tol=0.005,
                       n_clusters=10,
                       n_neighbors=10, louvain_resolution=[0.8],
                       batch_size=256,
                       save_dir=result_dir,
                       do_tsne=True, learning_rate=300, # learning_rate for tSNE
                       do_umap=True, num_Cores_tsne=4,
                       save_encoder_weights=True,
                       use_GPU=False)

My environment information is:
TF 1.15.0 and scanpy==1.5.1 anndata==0.7.4 umap==0.4.6 numpy==1.19.2 scipy==1.5.2 pandas==1.1.3 scikit-learn==0.23.2 statsmodels==0.12.0 python-igraph==0.8.3 louvain==0.7.0.

Could you please give me some insights? Thank you in advance!

Sincerely,