ResNeXt(cardinality, width; block_config, nclasses = 1000)

Create a ResNeXt model (reference).

Arguments

• cardinality: the number of groups to use for the convolution
• width: the number of feature maps in each group in the bottleneck
• block_config: a list of the number of residual blocks at each stage
• nclasses: the number of output classes

ResNeXt(config::Integer = 50; cardinality = 32, width = 4, pretrain = false, nclasses = 1000)

Create a ResNeXt model with specified configuration. Currently supported values for config are (50, 101). (reference). Set pretrain = true to load the model with pre-trained weights for ImageNet.

See also Metalhead.resnext.