Pytorch implementation for t-SNE with cuda to accelerate
pytorch
implementation of algorithm described in Visualizing Data using t-SNE. This code support cuda accelerating.
Just download the repository, and the unzip mnist2500_X.zip or put feature file and labels file with code
1. run without cuda support
python tsne_torch.py --xfile mnist2500_X.txt --yfile mnist2500_labels.txt --cuda 0
2.run with cuda support
python tsne_torch.py --xfile mnist2500_X.txt --yfile mnist2500_labels.txt --cuda 1
Note: The input data should be normalized to the range [0.0, 1.0], otherwise you may get the 'nan' result.
This is our result compare to result of python implementation.
This code highly inspired by