riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-31 02:02:21 +06:00
Code Issues Actions 23 Packages Projects Releases Wiki Activity

Model card for mobilenet v1 and v2 (#37948)

Browse Source 
* doc: #36979

* doc: update hfoptions

* add model checkpoints links

* add model checkpoints links

* update example output

* update style #36979

* add pipeline tags

* improve comments

* Apply suggestions from code review

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* apply suggested changes

* Apply suggestions from code review

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
This commit is contained in:
Yuanzhou Cai 2025-05-29 00:20:19 +08:00 committed by GitHub
parent 9a8510572b
commit 942c60956f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 127 additions and 59 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

90
docs/source/en/model_doc/mobilenet_v1.md
View File

@ -14,54 +14,92 @@ rendered properly in your Markdown viewer.
-->
# MobileNet V1
<div class="flex flex-wrap space-x-1">
<img alt="PyTorch" src="https://img.shields.io/badge/PyTorch-DE3412?style=flat&logo=pytorch&logoColor=white">
<div style="float: right;">
<div class="flex flex-wrap space-x-1">
<img alt="PyTorch" src="https://img.shields.io/badge/PyTorch-EE4C2C?style=flat&logo=pytorch&logoColor=white">
</div>
</div>
## Overview
# MobileNet V1
The MobileNet model was proposed in [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://arxiv.org/abs/1704.04861) by Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam.
[MobileNet V1](https://huggingface.co/papers/1704.04861) is a family of efficient convolutional neural networks optimized for on-device or embedded vision tasks. It achieves this efficiency by using depth-wise separable convolutions instead of standard convolutions. The architecture allows for easy trade-offs between latency and accuracy using two main hyperparameters, a width multiplier (alpha) and an image resolution multiplier.
The abstract from the paper is the following:
You can all the original MobileNet checkpoints under the [Google](https://huggingface.co/google?search_models=mobilenet) organization.
*We present a class of efficient models called MobileNets for mobile and embedded vision applications. MobileNets are based on a streamlined architecture that uses depth-wise separable convolutions to build light weight deep neural networks. We introduce two simple global hyper-parameters that efficiently trade off between latency and accuracy. These hyper-parameters allow the model builder to choose the right sized model for their application based on the constraints of the problem. We present extensive experiments on resource and accuracy tradeoffs and show strong performance compared to other popular models on ImageNet classification. We then demonstrate the effectiveness of MobileNets across a wide range of applications and use cases including object detection, finegrain classification, face attributes and large scale geo-localization.*
> [!TIP]
> Click on the MobileNet V1 models in the right sidebar for more examples of how to apply MobileNet to different vision tasks.
This model was contributed by [matthijs](https://huggingface.co/Matthijs). The original code and weights can be found [here](https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet_v1.md).
The example below demonstrates how to classify an image with [`Pipeline`] or the [`AutoModel`] class.
## Usage tips
- The checkpoints are named **mobilenet\_v1\_*depth*\_*size***, for example **mobilenet\_v1\_1.0\_224**, where **1.0** is the depth multiplier (sometimes also referred to as "alpha" or the width multiplier) and **224** is the resolution of the input images the model was trained on.
<hfoptions id="usage">
<hfoption id="Pipeline">
- Even though the checkpoint is trained on images of specific size, the model will work on images of any size. The smallest supported image size is 32x32.
```python
import torch
from transformers import pipeline
- One can use [`MobileNetV1ImageProcessor`] to prepare images for the model.
pipeline = pipeline(
task="image-classification",
model="google/mobilenet_v1_1.0_224",
torch_dtype=torch.float16,
device=0
)
pipeline(images="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg")
```
- The available image classification checkpoints are pre-trained on [ImageNet-1k](https://huggingface.co/datasets/imagenet-1k) (also referred to as ILSVRC 2012, a collection of 1.3 million images and 1,000 classes). However, the model predicts 1001 classes: the 1000 classes from ImageNet plus an extra “background” class (index 0).
</hfoption>
<hfoption id="AutoModel">
- The original TensorFlow checkpoints use different padding rules than PyTorch, requiring the model to determine the padding amount at inference time, since this depends on the input image size. To use native PyTorch padding behavior, create a [`MobileNetV1Config`] with `tf_padding = False`.
```python
import torch
import requests
from PIL import Image
from transformers import AutoModelForImageClassification, AutoImageProcessor
Unsupported features:
image_processor = AutoImageProcessor.from_pretrained(
"google/mobilenet_v1_1.0_224",
)
model = AutoModelForImageClassification.from_pretrained(
"google/mobilenet_v1_1.0_224",
)
- The [`MobileNetV1Model`] outputs a globally pooled version of the last hidden state. In the original model it is possible to use a 7x7 average pooling layer with stride 2 instead of global pooling. For larger inputs, this gives a pooled output that is larger than 1x1 pixel. The HuggingFace implementation does not support this.
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")
- It is currently not possible to specify an `output_stride`. For smaller output strides, the original model invokes dilated convolution to prevent the spatial resolution from being reduced further. The output stride of the HuggingFace model is always 32.
with torch.no_grad():
logits = model(**inputs).logits
predicted_class_id = logits.argmax(dim=-1).item()
- The original TensorFlow checkpoints include quantized models. We do not support these models as they include additional "FakeQuantization" operations to unquantize the weights.
class_labels = model.config.id2label
predicted_class_label = class_labels[predicted_class_id]
print(f"The predicted class label is: {predicted_class_label}")
```
- It's common to extract the output from the pointwise layers at indices 5, 11, 12, 13 for downstream purposes. Using `output_hidden_states=True` returns the output from all intermediate layers. There is currently no way to limit this to specific layers.
</hfoption>
</hfoptions>
## Resources
<!-- Quantization - Not applicable -->
<!-- Attention Visualization - Not applicable for this model type -->
A list of official Hugging Face and community (indicated by 🌎) resources to help you get started with MobileNetV1.
<PipelineTag pipeline="image-classification"/>
## Notes
- [`MobileNetV1ForImageClassification`] is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/pytorch/image-classification) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/image_classification.ipynb).
- See also: [Image classification task guide](../tasks/image_classification)
- Checkpoint names follow the pattern `mobilenet_v1_{depth_multiplier}_{resolution}`, like `mobilenet_v1_1.0_224`. `1.0` is the depth multiplier and `224` is the image resolution.
- While trained on images of a specific sizes, the model architecture works with images of different sizes (minimum 32x32). The [`MobileNetV1ImageProcessor`] handles the necessary preprocessing.
- MobileNet is pretrained on [ImageNet-1k](https://huggingface.co/datasets/imagenet-1k), a dataset with 1000 classes. However, the model actually predicts 1001 classes. The additional class is an extra "background" class (index 0).
- The original TensorFlow checkpoints determines the padding amount at inference because it depends on the input image size. To use the native PyTorch padding behavior, set `tf_padding=False` in [`MobileNetV1Config`].
```python
from transformers import MobileNetV1Config
If you're interested in submitting a resource to be included here, please feel free to open a Pull Request and we'll review it! The resource should ideally demonstrate something new instead of duplicating an existing resource.
config = MobileNetV1Config.from_pretrained("google/mobilenet_v1_1.0_224", tf_padding=True)
```
- The Transformers implementation does not support the following features.
- Uses global average pooling instead of the optional 7x7 average pooling with stride 2. For larger inputs, this gives a pooled output that is larger than a 1x1 pixel.
- Does not support other `output_stride` values (fixed at 32). For smaller `output_strides`, the original implementation uses dilated convolution to prevent spatial resolution from being reduced further. (which would require dilated convolutions).
- `output_hidden_states=True` returns *all* intermediate hidden states. It is not possible to extract the output from specific layers for other downstream purposes.
- Does not include the quantized models from the original checkpoints because they include "FakeQuantization" operations to unquantize the weights.
## MobileNetV1Config

96
docs/source/en/model_doc/mobilenet_v2.md
View File

@ -14,61 +14,91 @@ rendered properly in your Markdown viewer.
-->
# MobileNet V2
<div class="flex flex-wrap space-x-1">
<img alt="PyTorch" src="https://img.shields.io/badge/PyTorch-DE3412?style=flat&logo=pytorch&logoColor=white">
<div style="float: right;">
<div class="flex flex-wrap space-x-1">
<img alt="PyTorch" src="https://img.shields.io/badge/PyTorch-EE4C2C?style=flat&logo=pytorch&logoColor=white">
</div>
</div>
## Overview
# MobileNet V2
The MobileNet model was proposed in [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://arxiv.org/abs/1801.04381) by Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen.
[MobileNet V2](https://huggingface.co/papers/1801.04381) improves performance on mobile devices with a more efficient architecture. It uses inverted residual blocks and linear bottlenecks to start with a smaller representation of the data, expands it for processing, and shrinks it again to reduce the number of computations. The model also removes non-linearities to maintain accuracy despite its simplified design. Like [MobileNet V1](./mobilenet_v1), it uses depthwise separable convolutions for efficiency.
The abstract from the paper is the following:
You can all the original MobileNet checkpoints under the [Google](https://huggingface.co/google?search_models=mobilenet) organization.
*In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes. We also describe efficient ways of applying these mobile models to object detection in a novel framework we call SSDLite. Additionally, we demonstrate how to build mobile semantic segmentation models through a reduced form of DeepLabv3 which we call Mobile DeepLabv3.*
> [!TIP]
> Click on the MobileNet V2 models in the right sidebar for more examples of how to apply MobileNet to different vision tasks.
*The MobileNetV2 architecture is based on an inverted residual structure where the input and output of the residual block are thin bottleneck layers opposite to traditional residual models which use expanded representations in the input an MobileNetV2 uses lightweight depthwise convolutions to filter features in the intermediate expansion layer. Additionally, we find that it is important to remove non-linearities in the narrow layers in order to maintain representational power. We demonstrate that this improves performance and provide an intuition that led to this design. Finally, our approach allows decoupling of the input/output domains from the expressiveness of the transformation, which provides a convenient framework for further analysis. We measure our performance on Imagenet classification, COCO object detection, VOC image segmentation. We evaluate the trade-offs between accuracy, and number of operations measured by multiply-adds (MAdd), as well as the number of parameters.*
This model was contributed by [matthijs](https://huggingface.co/Matthijs). The original code and weights can be found [here for the main model](https://github.com/tensorflow/models/tree/master/research/slim/nets/mobilenet) and [here for DeepLabV3+](https://github.com/tensorflow/models/tree/master/research/deeplab).
The examples below demonstrate how to classify an image with [`Pipeline`] or the [`AutoModel`] class.
## Usage tips
- The checkpoints are named **mobilenet\_v2\_*depth*\_*size***, for example **mobilenet\_v2\_1.0\_224**, where **1.0** is the depth multiplier (sometimes also referred to as "alpha" or the width multiplier) and **224** is the resolution of the input images the model was trained on.
<hfoptions id="usage-img-class">
<hfoption id="Pipeline">
- Even though the checkpoint is trained on images of specific size, the model will work on images of any size. The smallest supported image size is 32x32.
```python
import torch
from transformers import pipeline
- One can use [`MobileNetV2ImageProcessor`] to prepare images for the model.
pipeline = pipeline(
task="image-classification",
model="google/mobilenet_v2_1.4_224",
torch_dtype=torch.float16,
device=0
)
pipeline(images="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg")
```
- The available image classification checkpoints are pre-trained on [ImageNet-1k](https://huggingface.co/datasets/imagenet-1k) (also referred to as ILSVRC 2012, a collection of 1.3 million images and 1,000 classes). However, the model predicts 1001 classes: the 1000 classes from ImageNet plus an extra “background” class (index 0).
</hfoption>
<hfoption id="AutoModel">
- The segmentation model uses a [DeepLabV3+](https://arxiv.org/abs/1802.02611) head. The available semantic segmentation checkpoints are pre-trained on [PASCAL VOC](http://host.robots.ox.ac.uk/pascal/VOC/).
```python
import torch
import requests
from PIL import Image
from transformers import AutoModelForImageClassification, AutoImageProcessor
- The original TensorFlow checkpoints use different padding rules than PyTorch, requiring the model to determine the padding amount at inference time, since this depends on the input image size. To use native PyTorch padding behavior, create a [`MobileNetV2Config`] with `tf_padding = False`.
image_processor = AutoImageProcessor.from_pretrained(
"google/mobilenet_v2_1.4_224",
)
model = AutoModelForImageClassification.from_pretrained(
"google/mobilenet_v2_1.4_224",
)
Unsupported features:
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")
- The [`MobileNetV2Model`] outputs a globally pooled version of the last hidden state. In the original model it is possible to use an average pooling layer with a fixed 7x7 window and stride 1 instead of global pooling. For inputs that are larger than the recommended image size, this gives a pooled output that is larger than 1x1. The Hugging Face implementation does not support this.
with torch.no_grad():
logits = model(**inputs).logits
predicted_class_id = logits.argmax(dim=-1).item()
- The original TensorFlow checkpoints include quantized models. We do not support these models as they include additional "FakeQuantization" operations to unquantize the weights.
class_labels = model.config.id2label
predicted_class_label = class_labels[predicted_class_id]
print(f"The predicted class label is: {predicted_class_label}")
```
- It's common to extract the output from the expansion layers at indices 10 and 13, as well as the output from the final 1x1 convolution layer, for downstream purposes. Using `output_hidden_states=True` returns the output from all intermediate layers. There is currently no way to limit this to specific layers.
</hfoption>
</hfoptions>
- The DeepLabV3+ segmentation head does not use the final convolution layer from the backbone, but this layer gets computed anyway. There is currently no way to tell [`MobileNetV2Model`] up to which layer it should run.
## Resources
## Notes
A list of official Hugging Face and community (indicated by 🌎) resources to help you get started with MobileNetV2.
- Classification checkpoint names follow the pattern `mobilenet_v2_{depth_multiplier}_{resolution}`, like `mobilenet_v2_1.4_224`. `1.4` is the depth multiplier and `224` is the image resolution. Segmentation checkpoint names follow the pattern `deeplabv3_mobilenet_v2_{depth_multiplier}_{resolution}`.
- While trained on images of a specific sizes, the model architecture works with images of different sizes (minimum 32x32). The [`MobileNetV2ImageProcessor`] handles the necessary preprocessing.
- MobileNet is pretrained on [ImageNet-1k](https://huggingface.co/datasets/imagenet-1k), a dataset with 1000 classes. However, the model actually predicts 1001 classes. The additional class is an extra "background" class (index 0).
- The segmentation models use a [DeepLabV3+](https://huggingface.co/papers/1802.02611) head which is often pretrained on datasets like [PASCAL VOC](https://huggingface.co/datasets/merve/pascal-voc).
- The original TensorFlow checkpoints determines the padding amount at inference because it depends on the input image size. To use the native PyTorch padding behavior, set `tf_padding=False` in [`MobileNetV2Config`].
```python
from transformers import MobileNetV2Config
<PipelineTag pipeline="image-classification"/>
- [`MobileNetV2ForImageClassification`] is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/pytorch/image-classification) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/image_classification.ipynb).
- See also: [Image classification task guide](../tasks/image_classification)
**Semantic segmentation**
- [Semantic segmentation task guide](../tasks/semantic_segmentation)
If you're interested in submitting a resource to be included here, please feel free to open a Pull Request and we'll review it! The resource should ideally demonstrate something new instead of duplicating an existing resource.
config = MobileNetV2Config.from_pretrained("google/mobilenet_v2_1.4_224", tf_padding=True)
```
- The Transformers implementation does not support the following features.
- Uses global average pooling instead of the optional 7x7 average pooling with stride 2. For larger inputs, this gives a pooled output that is larger than a 1x1 pixel.
- `output_hidden_states=True` returns *all* intermediate hidden states. It is not possible to extract the output from specific layers for other downstream purposes.
- Does not include the quantized models from the original checkpoints because they include "FakeQuantization" operations to unquantize the weights.
- For segmentation models, the final convolution layer of the backbone is computed even though the DeepLabV3+ head doesn't use it.
## MobileNetV2Config