egc.module.loss package

Submodules

egc.module.loss.contrastive_loss module

Contrastive Loss Adapted from https://github.com/Yunfan-Li/Contrastive-Clustering

egc.module.loss.contrastive_loss.mask_correlated_samples(batch_size)

class egc.module.loss.contrastive_loss.InstanceLoss(batch_size, temperature)

Bases: Module

Instance Contrastive Loss

forward(z_i, z_j)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

training: bool

class egc.module.loss.contrastive_loss.ClusterLoss(class_num, temperature)

Bases: Module

Cluster Contrastive Loss

forward(c_i, c_j)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

training: bool

Module contents

Loss