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_reference_example [2019/04/03 15:44] twagner [Training] |
cryolo_reference_example [2019/09/22 16:37] twagner [Training] |
||
---|---|---|---|
Line 1: | Line 1: | ||
====== crYOLO reference example ====== | ====== crYOLO reference example ====== | ||
- | Here we provide quick example for training and picking with crYOLO. The main purpose is to check if your setup is running as expected. | + | Here we provide quick run through |
- | ===== Reference | + | ===== Reference |
- | We run this example on machine with the following specification: | + | We run this example on a machine with the following specification: |
* Titan V | * Titan V | ||
* Intel Core i9 7920X @ 2.90 Ghz | * Intel Core i9 7920X @ 2.90 Ghz | ||
+ | * SSD Harddrive | ||
Line 22: | Line 23: | ||
The '' | The '' | ||
- | * train_image: | + | * train_image: |
- | * train_annot: | + | * train_annot: |
* config_phosnet.json: | * config_phosnet.json: | ||
* reference_model.h5: | * reference_model.h5: | ||
Line 35: | Line 36: | ||
===== Training ===== | ===== Training ===== | ||
- | First, you have to warm up the network With "-g 0" I'm selection GPU 0. It takes 2 minutes 30 seconds on our reference setup: | + | |
- | < | + | The training is done with this command: |
- | cryolo_train.py -c config_phosnet.json -w 5 -g 0 | + | |
- | </ | + | |
- | The actual | + | |
< | < | ||
- | cryolo_train.py -c config_phosnet.json -w 0 -e 10 -g 0 | + | cryolo_train.py -c config_phosnet.json -w 5 -e 5 -g 0 |
</ | </ | ||
- | It needed 6 minutes 45 seconds to converge (18 epochs). The best validation loss was 0.03316. These number | + | It needed 6 minutes 45 seconds to converge (18 epochs). The best validation loss was 0.03316. These numbers |
===== Prediction ===== | ===== Prediction ===== |