VGG#
eqxvision.models.VGG
#
A simple port of torchvision.models.vgg
__init__(self, cfg: List[Union[str, int]] = None, num_classes: int = 1000, batch_norm: bool = True, dropout: float = 0.5, *, key: Optional[jax.random.PRNGKey] = None)
#
Arguments:
cfg
: A list specifying the block configuration.num_classes
: Number of classes in the classification task. Also controls the final output shape(num_classes,)
. Defaults to1000
.batch_norm
: IfTrue
, thenBatchNorm
is enabled in the architecture.dropout
: The probability parameter forequinox.nn.Dropout
.key
: Ajax.random.PRNGKey
used to provide randomness for parameter initialisation. (Keyword only argument.)
__call__(self, x: Array, *, key: jax.random.PRNGKey) -> Array
#
Arguments:
x
: The input. Should be a JAX array with3
channels.key
: Required parameter. Utilised by few layers such asDropout
orDropPath
.
eqxvision.models.vgg11(torch_weights: str = None, **kwargs: Any) -> VGG
#
VGG 11-layer model (configuration "A") from Very Deep Convolutional Networks For Large-Scale Image Recognition. The required minimum input size of the model is 32x32.
Arguments:
torch_weights
: APath
orURL
for thePyTorch
weights. Defaults toNone
eqxvision.models.vgg11_bn(torch_weights: str = None, **kwargs: Any) -> VGG
#
VGG 11-layer model (configuration "A") with batch normalization Very Deep Convolutional Networks For Large-Scale Image Recognition. The required minimum input size of the model is 32x32.
Arguments:
torch_weights
: APath
orURL
for thePyTorch
weights. Defaults toNone
eqxvision.models.vgg13(torch_weights: str = None, **kwargs: Any) -> VGG
#
VGG 13-layer model (configuration "B") Very Deep Convolutional Networks For Large-Scale Image Recognition. The required minimum input size of the model is 32x32.
Arguments:
torch_weights
: APath
orURL
for thePyTorch
weights. Defaults toNone
eqxvision.models.vgg13_bn(torch_weights: str = None, **kwargs: Any) -> VGG
#
VGG 13-layer model (configuration "B") with batch normalization Very Deep Convolutional Networks For Large-Scale Image Recognition. The required minimum input size of the model is 32x32.
Arguments:
torch_weights
: APath
orURL
for thePyTorch
weights. Defaults toNone
eqxvision.models.vgg16(torch_weights: str = None, **kwargs: Any) -> VGG
#
VGG 16-layer model (configuration "D") Very Deep Convolutional Networks For Large-Scale Image Recognition. The required minimum input size of the model is 32x32.
Arguments:
torch_weights
: APath
orURL
for thePyTorch
weights. Defaults toNone
eqxvision.models.vgg16_bn(torch_weights: str = None, **kwargs: Any) -> VGG
#
VGG 16-layer model (configuration "D") with batch normalization Very Deep Convolutional Networks For Large-Scale Image Recognition. The required minimum input size of the model is 32x32.
Arguments:
torch_weights
: APath
orURL
for thePyTorch
weights. Defaults toNone
eqxvision.models.vgg19(torch_weights: str = None, **kwargs: Any) -> VGG
#
VGG 19-layer model (configuration "E") Very Deep Convolutional Networks For Large-Scale Image Recognition. The required minimum input size of the model is 32x32.
Arguments:
torch_weights
: APath
orURL
for thePyTorch
weights. Defaults toNone
eqxvision.models.vgg19_bn(torch_weights: str = None, **kwargs: Any) -> VGG
#
VGG 19-layer model (configuration 'E') with batch normalization Very Deep Convolutional Networks For Large-Scale Image Recognition. The required minimum input size of the model is 32x32.
Arguments:
torch_weights
: APath
orURL
for thePyTorch
weights. Defaults toNone