Skip to main content

NSFW pipeline that classifies prompt, using a character embedding model

Project description

NSFW pipeline that classifies prompt, using a character embedding model

Feature | Description |
— | — |
Name | en_prompt_nsfw_pipeline_char_embed |
Version | 0.2.0 |
spaCy | >=3.0.0,<4.0.0 |
Default Pipeline | tok2vec, textcat |
Components | tok2vec, textcat |
Vectors | 514157 keys, 20000 unique vectors (300 dimensions) |
Sources | n/a |
License | UNLICENSED |
Author | [Jiayu Liu]() |

### Label Scheme

<details>

<summary>View label scheme (4 labels for 1 components)</summary>

Component | Labels |
— | — |
`textcat` | safe, underage_safe, adult, cp |

</details>

### Accuracy

Type | Score |
— | — |
CATS_SCORE | 89.86 |
CATS_MICRO_P | 90.28 |
CATS_MICRO_R | 90.28 |
CATS_MICRO_F | 90.28 |
CATS_MACRO_P | 89.76 |
CATS_MACRO_R | 90.01 |
CATS_MACRO_F | 89.86 |
CATS_MACRO_AUC | 98.50 |
TOK2VEC_LOSS | 21683.51 |
TEXTCAT_LOSS | 868.89 |

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

en_prompt_nsfw_pipeline_char_embed-0.2.0.tar.gz (33.2 MB view hashes)

Uploaded Source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page