Home
Data Process
Genome
Transcriptome
Protein
Integration
Model
Train > supervised
Train > unsupervised
Train > semi-supervised
Use
Data Analyse
Help
``` ```
Train your unsupervised model
Home
Model
Train
1. Select strategy and upload files
Upload train/validation/testing datasets
Upload a dataset to conduct train/validation/testing split
Use stratified K-Fold cross validation method
Upload training set (Note: The uploaded dataset should not contain label or index columns)
Example
Upload validation set (Note: The uploaded dataset should not contain label or index columns)
Upload testing set (Note: The uploaded dataset should not contain label or index columns)
Upload a dataset (Note: The uploaded dataset should not contain label or index columns)
Example
Input a ratio of training:validation:testing (NOTE: The separator is a colon ':')
Upload training set (Note: The uploaded dataset should not contain label or index columns)
Example
Input K value (NOTE: If you want to use 3-Fold cross validation method, then K value is 3.)
Upload testing set (Note: The uploaded dataset should not contain label or index columns)
2. Choose model
VAE > Variational Autoencoder VAE can generate new samples by learning the probability distribution of the data
DeepCluster > Combining k-means and neural networks to cluster data
3. Upload training hyperparameters
(1) Epoch
(2) Learning Rate
(3) EarlyStopping Patience
(4) Batch Size
(5) Random Seed
(6) Loss Function
MSE
MAE
Smooth L1
Focal Loss
Contrastive Loss
Spectral Loss
Wasserstein Loss
Perceptual Loss
Cosine Loss
KL Divergence
Regularization Loss
BCE
Huber Loss
InfoNCE
Basic DeepCluster Loss
Combining Multiple Clustering Losses
Center Loss
Contrastive Loss
Spectral Loss
Entropy Loss
Compactness Loss
Separation Loss
(7) Optimizer
Adam
SGD
AdamW
Your Email
Submit