clip-embeddings
mj5-clip-l-14-oai-embeddingsclip-embeddingswolt-food-clip-ViT-B-32-embeddings
wolt-food-clip-ViT-B-32-embeddings
Qdrant's Food Discovery demo relies on the dataset of food images from the Wolt
app. Each point in the collection represents a dish with a single image. The image is represented as a vector of 512
float numbers.
Generation process
The embeddings generated with clip-ViT-B-32 model have been generated using the following code snippet:
from PIL import Image
from sentence_transformers import SentenceTransformer
image_path =… See the full description on the dataset page: https://huggingface.co/datasets/Qdrant/wolt-food-clip-ViT-B-32-embeddings.ImageCaptions-7M-Embeddingsturkish_clip_dataset_with_text_embeddingsThis dataset cleaned and dowloaded version of following dataset: https://huggingface.co/datasets/visheratin/laion-coco-nllb
The main purpose was to extract Turkish captions and download images.
You can use this dataset to fine-tune or create a clip model.
Since there English and Turkish captions you can also use those to create language model?
imagenet-1k-224-clip-embeddings
ImageNet-1k-224 CLIP Embeddings
Pre-computed CLIP image embeddings for every image in
mlnomad/imagenet-1k-224.
Columns
Column
Type
Description
original_index
int
Row index in the source dataset for cross-referencing
label
int (0–999)
ImageNet class index
embedding
List[float]
L2-normalised CLIP image embedding (768D)
Stats
Source: mlnomad/imagenet-1k-224 (train split)
Total images: 1281167
Embedding dim: 768
CLIP model:… See the full description on the dataset page: https://huggingface.co/datasets/mlnomad/imagenet-1k-224-clip-embeddings.