CLIP model implementation with example (#1950)

* CLIP model implementation with example

* CLIP Implementation fixes, batch images

* CLIP model remove images from git

* CLIP model remove unnecessary use of batch_indices
This commit is contained in:
Tigran Zhampeissov
2024-03-28 17:44:12 +05:00
committed by GitHub
parent b3484e7a5e
commit b0340d72ec
6 changed files with 942 additions and 0 deletions

View File

@ -0,0 +1,46 @@
Contrastive Language-Image Pre-Training
Contrastive Language-Image Pre-Training (CLIP) is an architecture trained on
pairs of images with related texts.
https://github.com/openai/CLIP
https://github.com/huggingface/transformers/tree/f6fa0f0bf0796ac66f201f23bdb8585de1609add/src/transformers/models/clip
## Running on an example on cpu
```
$ cargo run --example clip --release -- --images "candle-examples/examples/stable-diffusion/assets/stable-diffusion-xl.jpg","candle-examples/examples/yolo-v8/assets/bike.jpg" --cpu --sequences "a cycling race","a photo of two cats","a robot holding a candle"
Results for image: candle-examples/examples/stable-diffusion/assets/stable-diffusion-xl.jpg
INFO clip: Probability: 0.0000% Text: a cycling race
INFO clip: Probability: 0.0000% Text: a photo of two cats
INFO clip: Probability: 100.0000% Text: a robot holding a candle
Results for image: candle-examples/examples/yolo-v8/assets/bike.jpg
INFO clip: Probability: 99.9999% Text: a cycling race
INFO clip: Probability: 0.0001% Text: a photo of two cats
INFO clip: Probability: 0.0000% Text: a robot holding a candle
```
## Running on an example with metal feature (mac)
```
$ cargo run --features metal --example clip --release -- --images "candle-examples/examples/stable-diffusion/assets/stable-diffusion-xl.jpg","candle-examples/examples/yolo-v8/assets/bike.jpg" --cpu --sequences "a cycling race","a photo of two cats","a robot holding a candle"
Results for image: candle-examples/examples/stable-diffusion/assets/stable-diffusion-xl.jpg
INFO clip: Probability: 0.0000% Text: a cycling race
INFO clip: Probability: 0.0000% Text: a photo of two cats
INFO clip: Probability: 100.0000% Text: a robot holding a candle
Results for image: candle-examples/examples/yolo-v8/assets/bike.jpg
INFO clip: Probability: 99.9999% Text: a cycling race
INFO clip: Probability: 0.0001% Text: a photo of two cats
INFO clip: Probability: 0.0000% Text: a robot holding a candle
```