My Blog

Author: Awais Farooq

  • LayoutMap API

    —

    by

    Awais Farooq
    in

    LayoutMap class A dict-like object that maps string to TensorLayout instances. LayoutMap uses a string as key and a TensorLayout as value. There is a behavior difference between a normal Python dict and this class. The string key will be treated as a regex when retrieving the value. See the docstring of get for more details. See below for a usage example. You…

  • Mixed precision policy API

    —

    by

    Awais Farooq
    in

    DTypePolicy class A dtype policy for a Keras layer. A dtype policy determines a layer’s computation and variable dtypes. Each layer has a policy. Policies can be passed to the dtype argument of layer constructors, or a global policy can be set with keras.config.set_dtype_policy. Arguments Typically you only need to interact with dtype policies when using mixed precision, which…

  • InceptionResNetV2

    —

    by

    Awais Farooq
    in

    InceptionResNetV2 function Instantiates the Inception-ResNet v2 architecture. Reference This function returns a Keras image classification model, optionally loaded with weights pre-trained on ImageNet. For image classification use cases, see this page for detailed examples. For transfer learning use cases, make sure to read the guide to transfer learning & fine-tuning. Note: each Keras Application expects a specific kind…

  • InceptionV3

    —

    by

    Awais Farooq
    in

    InceptionV3 function Instantiates the Inception v3 architecture. Reference This function returns a Keras image classification model, optionally loaded with weights pre-trained on ImageNet. For image classification use cases, see this page for detailed examples. For transfer learning use cases, make sure to read the guide to transfer learning & fine-tuning. Note: each Keras Application expects a specific kind…

  • NasNetLarge and NasNetMobile

    —

    by

    Awais Farooq
    in

    NASNetLarge function Instantiates a NASNet model in ImageNet mode. Reference Optionally loads weights pre-trained on ImageNet. Note that the data format convention used by the model is the one specified in your Keras config at ~/.keras/keras.json. Note: each Keras Application expects a specific kind of input preprocessing. For NASNet, call keras.applications.nasnet.preprocess_input on your inputs before passing them to the…

  • DenseNet

    —

    by

    Awais Farooq
    in

    DenseNet121 function Instantiates the Densenet121 architecture. Reference Optionally loads weights pre-trained on ImageNet. Note that the data format convention used by the model is the one specified in your Keras config at ~/.keras/keras.json. Note: each Keras Application expects a specific kind of input preprocessing. For DenseNet, call keras.applications.densenet.preprocess_input on your inputs before passing them to the model. Arguments Returns…

  • MobileNet, MobileNetV2, and MobileNetV3

    —

    by

    Awais Farooq
    in

    MobileNet function Instantiates the MobileNet architecture. Reference This function returns a Keras image classification model, optionally loaded with weights pre-trained on ImageNet. For image classification use cases, see this page for detailed examples. For transfer learning use cases, make sure to read the guide to transfer learning & fine-tuning. Note: each Keras Application expects a specific kind of…

  • ResNet and ResNetV2

    —

    by

    Awais Farooq
    in

    ResNet50 function Instantiates the ResNet50 architecture. Reference For image classification use cases, see this page for detailed examples. For transfer learning use cases, make sure to read the guide to transfer learning & fine-tuning. Note: each Keras Application expects a specific kind of input preprocessing. For ResNet, call keras.applications.resnet.preprocess_input on your inputs before passing them to the model. resnet.preprocess_input will convert the…

  • VGG16 and VGG19

    —

    by

    Awais Farooq
    in

    VGG16 function Instantiates the VGG16 model. Reference For image classification use cases, see this page for detailed examples. For transfer learning use cases, make sure to read the guide to transfer learning & fine-tuning. The default input size for this model is 224×224. Note: each Keras Application expects a specific kind of input preprocessing. For VGG16, call keras.applications.vgg16.preprocess_input on your…

  • ConvNeXt Tiny, Small, Base, Large, XLarge

    —

    by

    Awais Farooq
    in

    ConvNeXtTiny function Instantiates the ConvNeXtTiny architecture. References For image classification use cases, see this page for detailed examples. For transfer learning use cases, make sure to read the guide to transfer learning & fine-tuning. The base, large, and xlarge models were first pre-trained on the ImageNet-21k dataset and then fine-tuned on the ImageNet-1k dataset. The pre-trained parameters of the models were assembled…