Add model card for MobileViT #40033
Open
Add model card for MobileViT #40033
+90
−50
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@stevhliu Please take a look at your convenience and do let me know if there is any further changes required. |
stevhliu
reviewed
Aug 8, 2025
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
stevhliu
approved these changes
Aug 11, 2025
|
|
||
| This model was contributed by [matthijs](https://huggingface.co/Matthijs). The TensorFlow version of the model was contributed by [sayakpaul](https://huggingface.co/sayakpaul). The original code and weights can be found [here](https://github.com/apple/ml-cvnets). | ||
| from transformers import pipeline |
There was a problem hiding this comment.
You can just run it on a single image rather than a dataset
import torch
from transformers import pipeline
pipeline = pipeline(
task="image-classification",
model="apple/mobilevit-small",
torch_dtype=torch.float16,
device=0
)
pipeline("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg")|
|
||
| ```python | ||
|
|
||
| import torch |
There was a problem hiding this comment.
import torch
import requests
from PIL import Image
from transformers import AutoModelForImageClassification, AutoImageProcessor
image_processor = AutoImageProcessor.from_pretrained(
"apple/mobilevit-small",
use_fast=True,
)
model = AutoModelForImageClassification.from_pretrained(
"apple/mobilevit-small",
)
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"
image = Image.open(requests.get(url, stream=True).raw)
inputs = image_processor(image, return_tensors="pt").to("cuda")
with torch.no_grad():
logits = model(**inputs).logits
predicted_class_id = logits.argmax(dim=-1).item()
class_labels = model.config.id2label
predicted_class_label = class_labels[predicted_class_id]
print(f"The predicted class label is: {predicted_class_label}")| <PipelineTag pipeline="image-classification"/> | ||
| - Does **not** operate on sequential data, it's purely designed for image tasks. | ||
| - Feature maps are used directly instead of token embeddings. | ||
| - Use [`MobileViTImageProcessor`](https://huggingface.co/docs/transformers/main/en/model_doc/mobilevit#transformers.MobileViTImageProcessor) to preprocess images. |
There was a problem hiding this comment.
Suggested change
| - Use [`MobileViTImageProcessor`](https://huggingface.co/docs/transformers/main/en/model_doc/mobilevit#transformers.MobileViTImageProcessor) to preprocess images. | |
| - Use [`MobileViTImageProcessor`] to preprocess images. |
Comment on lines
+114
to
+116
| - The **classification models** are pretrained on [**ImageNet-1k**](https://huggingface.co/datasets/imagenet-1k) (ILSVRC 2012). | ||
| - The **segmentation models** use a [**DeepLabV3**](https://huggingface.co/papers/1706.05587) head and are pretrained on [**PASCAL VOC**](http://host.robots.ox.ac.uk/pascal/VOC/). | ||
| - TensorFlow versions are compatible with **TensorFlow Lite**, making them ideal for edge/mobile deployment. |
There was a problem hiding this comment.
Suggested change
| - The **classification models** are pretrained on [**ImageNet-1k**](https://huggingface.co/datasets/imagenet-1k) (ILSVRC 2012). | |
| - The **segmentation models** use a [**DeepLabV3**](https://huggingface.co/papers/1706.05587) head and are pretrained on [**PASCAL VOC**](http://host.robots.ox.ac.uk/pascal/VOC/). | |
| - TensorFlow versions are compatible with **TensorFlow Lite**, making them ideal for edge/mobile deployment. | |
| - The classification models are pretrained on [ImageNet-1k](https://huggingface.co/datasets/imagenet-1k). | |
| - The segmentation models use a [DeepLabV3](https://huggingface.co/papers/1706.05587) head and are pretrained on [PASCAL VOC](http://host.robots.ox.ac.uk/pascal/VOC/). | |
| - TensorFlow versions are compatible with TensorFlow Lite, making them ideal for edge/mobile deployment. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do?
This PR adds a detailed and beginner-friendly model card for MobileViT to the Hugging Face Transformers documentation. The previous model card was minimal and lacked clear explanations about the model architecture. This model retains several elements from the earlier version, as they remain applicable and effective for users.
The new version includes:
Fixes # (issue)
Before submitting
Pull Request section?
to it if that's the case.
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.