mobilenetv2_quant.rst 787 B

123456789101112131415161718192021222324
  1. Quantized MobileNet V2
  2. ======================
  3. .. currentmodule:: torchvision.models.quantization
  4. The Quantized MobileNet V2 model is based on the `MobileNetV2: Inverted Residuals and Linear
  5. Bottlenecks <https://arxiv.org/abs/1801.04381>`__ paper.
  6. Model builders
  7. --------------
  8. The following model builders can be used to instantiate a quantized MobileNetV2
  9. model, with or without pre-trained weights. All the model builders internally
  10. rely on the ``torchvision.models.quantization.mobilenetv2.QuantizableMobileNetV2``
  11. base class. Please refer to the `source code
  12. <https://github.com/pytorch/vision/blob/main/torchvision/models/quantization/mobilenetv2.py>`_
  13. for more details about this class.
  14. .. autosummary::
  15. :toctree: generated/
  16. :template: function.rst
  17. mobilenet_v2