ConvNeXt#
eqxvision.models.ConvNeXt
#
A simple port of torchvision.models.convnext
.
__init__(self, block_setting: Sequence[_CNBlockConfig], stochastic_depth_prob: float = 0.0, layer_scale: float = 1e-06, num_classes: int = 1000, block: Optional[eqx.Module] = None, norm_layer: Optional[eqx.Module] = None, *, key: jax.random.PRNGKey = None)
#
block_setting
: Configuration of the computational blocksstochastic_depth_prob
: Probability of dropping a sample along channelslayer_scale
: Scale applied to the output of computational stemnum_classes
: Number of classes in the classification task. Also controls the final output shape(num_classes,)
block
: The block type used within the networknorm_layer
: Normalisation applied to the intermediate outputskey
: 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 inputJAX
array.key
: Required parameter. Utilised by few layers such asDropout
orDropPath
.
eqxvision.models.convnext_tiny(*, torch_weights: str = None, **kwargs: Any) -> ConvNeXt
#
ConvNeXt Tiny model architecture from the
"A ConvNet for the 2020s" <https://arxiv.org/abs/2201.03545>
_ paper.
Arguments:
torch_weights
: APath
orURL
for thePyTorch
weights. Defaults toNone
eqxvision.models.convnext_small(*, torch_weights: str = None, **kwargs: Any) -> ConvNeXt
#
ConvNeXt Small model architecture from the A ConvNet for the 2020s paper.
Arguments:
torch_weights
: APath
orURL
for thePyTorch
weights. Defaults toNone
eqxvision.models.convnext_base(*, torch_weights: str = None, **kwargs: Any) -> ConvNeXt
#
ConvNeXt Base model architecture from the A ConvNet for the 2020s paper.
Arguments:
torch_weights
: APath
orURL
for thePyTorch
weights. Defaults toNone
eqxvision.models.convnext_large(*, torch_weights: str = None, **kwargs: Any) -> ConvNeXt
#
ConvNeXt Large model architecture from the A ConvNet for the 2020s paper.
Arguments:
torch_weights
: APath
orURL
for thePyTorch
weights. Defaults toNone