This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
cryolo_picking_unlabeled [2019/03/16 11:58] twagner [Toxin] |
cryolo_picking_unlabeled [2019/03/16 17:55] twagner [TRPC4] |
||
---|---|---|---|
Line 53: | Line 53: | ||
Again, it still picks basically everything while avoiding contamination. | Again, it still picks basically everything while avoiding contamination. | ||
+ | |||
+ | ===== TRPC4 ===== | ||
+ | |||
+ | The last example that I've choosen is TRPC4. The original training set comprises 32 images with 3038 particles (~94 particles / image): | ||
+ | |||
+ | [{{: | ||
+ | |||
+ | Again, the same procedure as with toxin and ATP synthase. I removed 80% of particles randomly: | ||
+ | |||
+ | [{{: | ||
+ | |||
+ | I trained the model, and picked again. Here are the results for picking with the default threshold: | ||
+ | |||
+ | [{{: | ||
+ | |||
+ | It missed a lot, but picked far more that one would expect from the sparsely labled training data. The missing particles appearing when you reduce the threshold to 0.14: | ||
+ | |||
+ | [{{: | ||
+ | |||
+ | Particles picked, contamination skipped, job done :-) |