@@ -86,12 +86,12 @@ Here is a short overview of the stages:
...
@@ -86,12 +86,12 @@ Here is a short overview of the stages:
-```stage=0```: deletes experiment folder (if it exists) and runs all subsequent stages in a row
-```stage=0```: deletes experiment folder (if it exists) and runs all subsequent stages in a row
-```stage=1```:
-```stage=1```:
- prepares the data given an experiment folder (e.g., ```DATA/BEAGR```)
- prepares the data given an experiment folder (e.g., ```DATA/BEAGR/```)
- resulting files are stored in ```exp_*/data/```
- resulting files are stored in ```exp_*/data/```
-```stage=2```:
-```stage=2```:
- counts frequencies of used codebook entries per speaker
- counts frequencies of used codebook entries per speaker
- if VERBOSE is true this stage also generates log-files
- if VERBOSE is true this stage also generates log-files
-**if you need to extract features with a CPU, set ```device = torch.device('cpu')``` in the script ```local/codebook_freqs.py``` (default is ```device = torch.device('gpu')```)**
-**if you need to extract features with a CPU, set ```device = torch.device('cpu')``` in the script ```local/codebook_freqs.py``` (default is ```device = torch.device('cuda')```)**
- resulting files are stored in ```exp_*/logs/```, ```exp_*/numpy/``` and```exp_*/txt/```
- resulting files are stored in ```exp_*/logs/```, ```exp_*/numpy/``` and```exp_*/txt/```
-```stage=3```:
-```stage=3```:
- prepares and stores a similarty matrix in the folder ```exp_*/numpy/```
- prepares and stores a similarty matrix in the folder ```exp_*/numpy/```