deepghs/clip_onnx
By deepghs · ↓ 0 · ♥ 2 · Updated 2025-01-28
What's in this repo
This page lists the files in deepghs/clip_onnx, including image_encode.onnx, text_encode.onnx and more.
- 8 ONNX models (.onnx files)
- 23 files, including 12 .json, 8 .onnx, 1 .md, 1 .parquet
- Last updated 2025-01-28
ONNX files
| File | Size | Download |
|---|---|---|
| openai/clip-vit-base-patch16/image_encode.onnx | — | Download |
| openai/clip-vit-base-patch16/text_encode.onnx | — | Download |
| openai/clip-vit-base-patch32/image_encode.onnx | — | Download |
| openai/clip-vit-base-patch32/text_encode.onnx | — | Download |
| openai/clip-vit-large-patch14-336/image_encode.onnx | — | Download |
| openai/clip-vit-large-patch14-336/text_encode.onnx | — | Download |
| openai/clip-vit-large-patch14/image_encode.onnx | — | Download |
| openai/clip-vit-large-patch14/text_encode.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
ONNX exported version of CLIP models.
Models
4 models exported in total.
| Name | Image (Params/FLOPS) | Image Size | Image Width (Enc/Emb) | Text (Params/FLOPS) | Text Width (Enc/Emb) | Created At |
|---|---|---|---|---|---|---|
| openai/clip-vit-large-patch14-336 | 302.9M / 174.7G | 336 | 1024 / 768 | 85.1M / 1.2G | 768 / 768 | 2022-04-22 |
| openai/clip-vit-large-patch14 | 302.9M / 77.8G | 224 | 1024 / 768 | 85.1M / 1.2G | 768 / 768 | 2022-03-03 |
| openai/clip-vit-base-patch16 | 85.6M / 16.9G | 224 | 768 / 512 | 37.8M / 529.2M | 512 / 512 | 2022-03-03 |
| openai/clip-vit-base-patch32 | 87.4M / 4.4G | 224 | 768 / 512 | 37.8M / 529.2M | 512 / 512 | 2022-03-03 |
Model info
zero-shot-classification
dghs-realutils
dghs-realutils
onnx
transformers
clip
image
zero-shot-classification
en
base_model:openai/clip-vit-base-patch16
base_model:quantized:openai/clip-vit-base-patch16
region:us
↓ 0
♥ 2
Created: 2025-01-28
Updated: 2025-01-28
View on Hugging FaceFiles (23)
.gitattributes
README.md
models.parquet
openai/clip-vit-base-patch16/image_encode.onnx
ONNX
openai/clip-vit-base-patch16/meta.json
openai/clip-vit-base-patch16/preprocessor.json
openai/clip-vit-base-patch16/text_encode.onnx
ONNX
openai/clip-vit-base-patch16/tokenizer.json
openai/clip-vit-base-patch32/image_encode.onnx
ONNX
openai/clip-vit-base-patch32/meta.json
openai/clip-vit-base-patch32/preprocessor.json
openai/clip-vit-base-patch32/text_encode.onnx
ONNX
openai/clip-vit-base-patch32/tokenizer.json
openai/clip-vit-large-patch14-336/image_encode.onnx
ONNX
openai/clip-vit-large-patch14-336/meta.json
openai/clip-vit-large-patch14-336/preprocessor.json
openai/clip-vit-large-patch14-336/text_encode.onnx
ONNX
openai/clip-vit-large-patch14-336/tokenizer.json
openai/clip-vit-large-patch14/image_encode.onnx
ONNX
openai/clip-vit-large-patch14/meta.json
openai/clip-vit-large-patch14/preprocessor.json
openai/clip-vit-large-patch14/text_encode.onnx
ONNX
openai/clip-vit-large-patch14/tokenizer.json