33 lines
1017 B
Markdown
Executable File
33 lines
1017 B
Markdown
Executable File
---
|
|
description: Documentation for text encoding models in Ultralytics YOLOE, supporting both OpenAI CLIP and Apple MobileCLIP implementations for vision-language tasks.
|
|
keywords: YOLOE, text encoding, CLIP, MobileCLIP, TextModel, vision-language models, embeddings, Ultralytics, deep learning
|
|
---
|
|
|
|
# Reference for `ultralytics/nn/text_model.py`
|
|
|
|
!!! success "Improvements"
|
|
|
|
This page is sourced from [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/nn/text_model.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/nn/text_model.py). Have an improvement or example to add? Open a [Pull Request](https://docs.ultralytics.com/help/contributing/) — thank you! 🙏
|
|
|
|
<br>
|
|
|
|
## ::: ultralytics.nn.text_model.TextModel
|
|
|
|
<br><br><hr><br>
|
|
|
|
## ::: ultralytics.nn.text_model.CLIP
|
|
|
|
<br><br><hr><br>
|
|
|
|
## ::: ultralytics.nn.text_model.MobileCLIP
|
|
|
|
<br><br><hr><br>
|
|
|
|
## ::: ultralytics.nn.text_model.MobileCLIPTS
|
|
|
|
<br><br><hr><br>
|
|
|
|
## ::: ultralytics.nn.text_model.build_text_model
|
|
|
|
<br><br>
|