====== crYOLO reference example ======
Here we provide quick run through example for training and picking with crYOLO. The main purpose is to check if your setup is running as expected. I will not provide detailed explanations in this text. Please note that there is [[http://sphire.mpg.de/wiki/doku.php?id=pipeline:window:cryolo|a detailed tutorial]].


===== Reference setup =====
We run this example on a machine with the following specification:
  * Titan V
  * Intel Core i9 7920X @ 2.90 Ghz
  * SSD Harddrive
  * crYOLO 1.5.0


===== Download reference data and getting started =====

You can download the reference data (TcdA1) here: 

[[https://owncloud.gwdg.de/index.php/s/SjzATaIMZaANrnm|Link to reference data]]

Then unzip the data:
<code>
unzip toxin_reference.zip -d toxin_reference/
cd toxin_reference
</code>

The ''toxin_reference'' directory contains multiple folders / files:
  * train_image: Folder with 12 training images
  * train_annot: Folder with 12 box files for the training images
  * config_phosnet.json: Configuration file for crYOLO
  * reference_model.h5: Model that I've trained on my machine using the commands below.
  * reference_results: Picked particles using my machine and the reference model.

Before you start training / picking please activate your environment:
<code>
source activate cryolo
</code>

===== Training =====


The training is done with this command:
<code>
cryolo_train.py -c config_phosnet.json -w 5 -e 5 -g 0
</code>
crYOLO needs 5 minutes 50 seconds to converge (5 warmup + 10 "normal" epochs). The best validation loss was 0.03042. These numbers might be a little bit different on your case.

===== Prediction =====
<code>
cryolo_predict.py -c config_phosnet.json -w model.h5 -i unseen_examples/ -o my_results
</code>

It picked 1617 particles on 12 micrographs in 3 seconds. Including filtering the image and loading the model the command needed 38 seconds.

===== Visualize results =====
<code>
cryolo_boxmanager.py -i unseen_examples/ -b my_results/CBOX/
</code>