Daniel Charua

Not sure what the question is, but I worked on this project a few months ago, you can see my code adaptation in this [repo](https://github.com/dcharua/T-Sne)

Hi I have the same issue, ran it on the FRGC with 3 channels, but got > /home/lifelogging/torch/install/bin/luajit: bad argument #2 to '?' (out of range at /home/lifelogging/torch/pkg/torch/generic/Tensor.c:913) stack traceback:...

The problem is with the data, it needs to be in the correct format a 32float so the header of the h5 should look like this > HDF5 "data4torch.h5" {...

Thank you so much for your answer, it worked perfectly I now have other problem :( I resized the images to 32 x 32 and used the FRGC structure as...

I got it, the problem was the datatype, it needs to be a 32 float, I added the cast to your code `data = np.array(p.map(process_image, train_paths)).astype(np.float32)` `labels = np.array(p.map(get_labels, train_paths)).astype(np.float32)`