We'll take a look at what t-sne does with the codewords produced by vggnet on the xtcav images.
- Grabbed 4000 codeword2
- about 2000 lasing, 2000 no-lasing
- grabbed the t-sne python code from https://lvdmaaten.github.io/tsne/,
- first eliminated the dead neurons - there were 1023 dead neaurons (at least from those 4000 samples, should check all)
- run tsne with default parameters (perplexity=30.0)
We get this image:
Interesting to see how well separated they are, it is odd to see a couple yellow no-lasing samples show up in the blue lasing area. The patch of blue lasing samples in the no-lasing area - that are so far away, is odd.