pyanomaly.networks.meta package

Subpackages

• pyanomaly.networks.meta.base package
  • Submodules
  • pyanomaly.networks.meta.base.commonness module
  • pyanomaly.networks.meta.base.convolution_lstm module
  • pyanomaly.networks.meta.base.prednet module
  • Module contents
• pyanomaly.networks.meta.pcn_parts package
  • Submodules
  • pyanomaly.networks.meta.pcn_parts.convolution_lstm module
  • pyanomaly.networks.meta.pcn_parts.erm module
  • pyanomaly.networks.meta.pcn_parts.pcm module
  • pyanomaly.networks.meta.pcn_parts.prednet module
  • Module contents

Submodules

pyanomaly.networks.meta.amc_networks module

@author: Yuhao Cheng @contact: yuhao.cheng[at]outlook.com

class pyanomaly.networks.meta.amc_networks.AMCDiscriminiator(cfg, c_in=5, filters=64)

Bases: torch.nn.modules.module.Module

forward(x)

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.

class pyanomaly.networks.meta.amc_networks.AMCGenerator(cfg, c_in=3, opticalflow_channel_num=2, image_channel_num=3, dropout_prob=0, bilinear=True)

Bases: torch.nn.modules.module.Module

forward(x)

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.

pyanomaly.networks.meta.anopcn_networks module

@author: Yuhao Cheng @contact: yuhao.cheng[at]outlook.com

class pyanomaly.networks.meta.anopcn_networks.AnoPcn(cfg)

Bases: torch.nn.modules.module.Module

forward(x, target)

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.

pyanomaly.networks.meta.anopred_networks module

@author: Yuhao Cheng @contact: yuhao.cheng[at]outlook.com

class pyanomaly.networks.meta.anopred_networks.AnoPredGeneratorUnet(cfg, bilinear=False)

Bases: torch.nn.modules.module.Module

forward(x)

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.

pyanomaly.networks.meta.memae_networks module

@author: Yuhao Cheng @contact: yuhao.cheng[at]outlook.com

class pyanomaly.networks.meta.memae_networks.AutoEncoderCov3DMem(chnum_in, mem_dim, shrink_thres=0.0025)

Bases: torch.nn.modules.module.Module

forward(x)

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.

pyanomaly.networks.meta.ocae_networks module

@author: Yuhao Cheng @contact: yuhao.cheng[at]outlook.com

class pyanomaly.networks.meta.ocae_networks.CAE(c_in)

Bases: torch.nn.modules.module.Module

forward(x)

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.

pyanomaly.networks.meta.stae_networks module

@author: Yuhao Cheng @contact: yuhao.cheng[at]outlook.com

class pyanomaly.networks.meta.stae_networks.STAutoEncoderCov3D(cfg)

Bases: torch.nn.modules.module.Module

forward(x)

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.

Module contents

@author: Yuhao Cheng @contact: yuhao.cheng[at]outlook.com