This model was released on 2017-04-17 and added to Hugging Face Transformers on 2022-11-21.

</div>

</div>

MobileNet V1

MobileNet V1 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.

You can all the original MobileNet checkpoints under the Google organization.

[!TIP] Click on the MobileNet V1 models in the right sidebar for more examples of how to apply MobileNet to different vision tasks.

The example below demonstrates how to classify an image with [Pipeline] or the [AutoModel] class.

python

from transformers import pipeline


pipeline = pipeline(
    task="image-classification",
    model="google/mobilenet_v1_1.0_224",
    device=0
)
pipeline("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg")

</hfoption> <hfoption id="AutoModel">

python

import requests
import torch
from PIL import Image

from transformers import AutoImageProcessor, AutoModelForImageClassification


image_processor = AutoImageProcessor.from_pretrained(
    "google/mobilenet_v1_1.0_224",
)
model = AutoModelForImageClassification.from_pretrained(
    "google/mobilenet_v1_1.0_224",
    device_map="auto",
)

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(model.device)

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}")

</hfoption> </hfoptions>

Notes

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, 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

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

[[autodoc]] MobileNetV1Config

MobileNetV1ImageProcessor

[[autodoc]] MobileNetV1ImageProcessor - preprocess

MobileNetV1ImageProcessorPil

[[autodoc]] MobileNetV1ImageProcessorPil - preprocess

MobileNetV1Model

[[autodoc]] MobileNetV1Model - forward

MobileNetV1ForImageClassification

[[autodoc]] MobileNetV1ForImageClassification - forward