MaartenGr

fig = concept_model.visualize_concepts(concepts=[concept for concept, _ in search_results])

MaartenGr

fig = concept_model.visualize_concepts()

MaartenGr

>>> search_results = concept_model.find_concepts("beach")
>>> search_results
[(100, 0.277577825349102),
 (53, 0.27431058773894657),
 (95, 0.25973751319723837),
 (77, 0.2560122597417548),
 (97, 0.25361988261846297)]

MaartenGr

from concept import ConceptModel

# Train Concept using the pre-trained image embeddings
concept_model = ConceptModel()
concepts = concept_model.fit_transform(img_names, 
                                       image_embeddings=image_embeddings, 
                                       docs=selected_nouns)

MaartenGr

from concept import ConceptModel

concept_model = ConceptModel()
concepts = concept_model.fit_transform(img_names, docs=selected_nouns)

MaartenGr

import random
import nltk
nltk.download("wordnet")
from nltk.corpus import wordnet as wn

all_nouns = [word for synset in wn.all_synsets('n') for word in synset.lemma_names() 
             if "_" not in word]
selected_nouns = random.sample(all_nouns, 50_000)

MaartenGr

import pickle
from sentence_transformers import util

# Load pre-trained image embeddings
emb_filename = 'unsplash-25k-photos-embeddings.pkl'
if not os.path.exists(emb_filename):   #Download dataset if does not exist
    util.http_get('http://sbert.net/datasets/'+emb_filename, emb_filename)
    
with open(emb_filename, 'rb') as fIn:
    img_names, image_embeddings = pickle.load(fIn) 

MaartenGr

import os
import glob
import zipfile
from tqdm import tqdm
from sentence_transformers import util

# Download 25k images from Unsplash 
img_folder = 'photos/'
if not os.path.exists(img_folder) or len(os.listdir(img_folder)) == 0:
    os.makedirs(img_folder, exist_ok=True)

MaartenGr

from bertopic import BERTopic
from sklearn.feature_extraction.text import TfidfVectorizer

# Create TF-IDF sparse matrix
vectorizer = TfidfVectorizer(min_df=5)
embeddings = vectorizer.fit_transform(docs)

# Model
model = BERTopic(stop_words="english")
topics, probabilities = model.fit_transform(docs, embeddings)

MaartenGr

from bertopic import BERTopic
from sentence_transformers import SentenceTransformer

# Prepare embeddings
sentence_model = SentenceTransformer("distilbert-base-nli-mean-tokens")
embeddings = sentence_model.encode(docs, show_progress_bar=False)

# Create topic model
model = BERTopic()
topics, probabilities = model.fit_transform(docs, embeddings)