BERTopic_flickr_bw_rgb

This is a BERTopic model. BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets.

Usage

To use this model, please install BERTopic:

pip install -U bertopic

You can use the model as follows:

from bertopic import BERTopic
topic_model = BERTopic.load("b-verma/BERTopic_flickr_bw_rgb")

topic_model.get_topic_info()

Topic overview

  • Number of topics: 24
  • Number of training documents: 7216
Click here for an overview of all topics.
Topic ID Topic Keywords Topic Frequency Label
-1 photograph - colorized photograph - colorized - dog - white 52 Photography and Dogs
0 woman - photograph woman - people - women - photograph 1697 Women in Photography
1 boy - young - photograph young - photograph - child 917 Childhood Joy
2 dogs - photograph dogs - white photograph dogs - colorized photograph dogs - photograph 817 Dog Photography
3 bike - bicycle - riding - photograph - photograph person 555 Action Sports Photography
4 wave - water - surfer - photograph people - boat 494 Surfing and Waves
5 man - photograph man - white photograph man - colorized photograph man - black 367 Man in Photographs
6 girl - young girl - photograph young girl - photograph girl - young 306 Childhood Memories
7 dog - water - photograph dog - water colorized - water colorized photograph 293 Dog Running Through Water
8 skateboarder - skateboard - photograph skateboarder - white photograph skateboarder - colorized photograph skateboarder 221 Skateboarding Photography
9 rock - climbing - photograph man - mountain - man 217 Rock Climbing
10 soccer - snow - dog - snow black white - snow black 176 Snowy Soccer Scenes
11 running - dog running - dog - grass - running grass 172 Dog Running in Grass
12 dog - dog jumping - jumping - dog jumps - white dog 165 Dog Jumping
13 girls - photograph young girls - young girls - photograph girls - photograph young 118 Teenage Girls in Photographs
14 football - photograph football - football player - player - football players 97 Football Action Photography
15 snowboarder - photograph snowboarder - colorized photograph snowboarder - white photograph snowboarder - air 87 Snowboarding Aerial Photography
16 dog - mouth - toy - photograph dog - ball 83 Dog Photography
17 bird - flying - photograph white - water - white bird 75 Flying Birds
18 basketball - playing basketball - men - basketball player - player 70 Basketball Player
19 skier - photograph skier - white photograph skier - colorized photograph skier - skiing 68 Skiing and Photography
20 horse - horses - riding - bull - brown horse 60 Horse Riding and Jumping
21 frisbee - frisbee black white - frisbee black - catch - dog 56 Dog and Frisbee Photography
22 tennis - tennis player - photograph tennis player - photograph tennis - player 53 Tennis Player in Action

Training hyperparameters

  • calculate_probabilities: True
  • language: None
  • low_memory: False
  • min_topic_size: 10
  • n_gram_range: (1, 1)
  • nr_topics: None
  • seed_topic_list: None
  • top_n_words: 10
  • verbose: True
  • zeroshot_min_similarity: 0.7
  • zeroshot_topic_list: None

Framework versions

  • Numpy: 1.26.4
  • HDBSCAN: 0.8.40
  • UMAP: 0.5.7
  • Pandas: 2.2.3
  • Scikit-Learn: 1.6.1
  • Sentence-transformers: 3.4.1
  • Transformers: 4.49.0
  • Numba: 0.61.0
  • Plotly: 6.0.1
  • Python: 3.10.16
Downloads last month
3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train b-verma/BERTopic_flickr_bw_rgb