Utils for agi-med team metric calculation
Project description
agi-med-metrics
Стандартизация компонент общей библиотеки отдела для расчета метрик качества моделей
Ответственный разработчик
@bakulin
Метрики
ML:
- false positive rate
- false negative rate
NLP:
- BLEU
- ROUGE1, ROUGE2, ROUGEL
- cosine similarity
CV:
- mean character error rate
Тесты
sudo docker-compose -f docker-compose.yaml up --build
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
agi_med_metrics-0.0.7.tar.gz
(2.4 kB
view details)
Built Distribution
File details
Details for the file agi_med_metrics-0.0.7.tar.gz
.
File metadata
- Download URL: agi_med_metrics-0.0.7.tar.gz
- Upload date:
- Size: 2.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.0.0 CPython/3.10.15
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 19252daa653f7e98a52add0d160b638bf1e840495b992aaacff4252f53565a0b |
|
MD5 | c4dccc35657c5aa0164329a075007a0b |
|
BLAKE2b-256 | f9ba41cdf239c0ec4455f1b5b848fe03129f1b0a680b08bab16e34b558e77fdf |
File details
Details for the file agi_med_metrics-0.0.7-py3-none-any.whl
.
File metadata
- Download URL: agi_med_metrics-0.0.7-py3-none-any.whl
- Upload date:
- Size: 3.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.0.0 CPython/3.10.15
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 2e39ad6ca7dbb3d8d83113b431a8998a9cb0fa71042951acb8be92e9ff53d70b |
|
MD5 | 09efe38aea3ea6fcf4a2b008feaba36c |
|
BLAKE2b-256 | 543bfc5f92d1262abf8df0b3eb6c58f00ee71354b68737a2441a780227523508 |