CCDeep.ResNet package

Submodules

CCDeep.ResNet.residual_block module

class CCDeep.ResNet.residual_block.BasicBlock(*args, **kwargs)

基类：Layer

call(inputs, training=None)

This is where the layer's logic lives.

Note here that call() method in tf.keras is little bit different from keras API. In keras API, you can pass support masking for layers as additional arguments. Whereas tf.keras has compute_mask() method to support masking.

参数

• inputs -- Input tensor, or list/tuple of input tensors.

• **kwargs -- Additional keyword arguments. Currently unused.

返回

A tensor or list/tuple of tensors.

class CCDeep.ResNet.residual_block.BottleNeck(*args, **kwargs)

基类：Layer

call(inputs, training=None)

This is where the layer's logic lives.

Note here that call() method in tf.keras is little bit different from keras API. In keras API, you can pass support masking for layers as additional arguments. Whereas tf.keras has compute_mask() method to support masking.

参数

• inputs -- Input tensor, or list/tuple of input tensors.

• **kwargs -- Additional keyword arguments. Currently unused.

返回

A tensor or list/tuple of tensors.

CCDeep.ResNet.residual_block.make_basic_block_layer(filter_num, blocks, stride=1)

CCDeep.ResNet.residual_block.make_bottleneck_layer(filter_num, blocks, stride=1)

CCDeep.ResNet.resnet module

class CCDeep.ResNet.resnet.ResNetTypeI(*args, **kwargs)

基类：Model

ResNet type I

call(inputs, training=None)

Calls the model on new inputs.

In this case call just reapplies all ops in the graph to the new inputs (e.g. build a new computational graph from the provided inputs).

参数

• inputs -- A tensor or list of tensors.

• training -- Boolean or boolean scalar tensor, indicating whether to run the Network in training mode or inference mode.

• mask -- A mask or list of masks. A mask can be either a tensor or None (no mask).

返回

A tensor if there is a single output, or a list of tensors if there are more than one outputs.

class CCDeep.ResNet.resnet.ResNetTypeII(*args, **kwargs)

基类：Model

ResNet type II

call(inputs, training=None)

Calls the model on new inputs.

In this case call just reapplies all ops in the graph to the new inputs (e.g. build a new computational graph from the provided inputs).

参数

• inputs -- A tensor or list of tensors.

• training -- Boolean or boolean scalar tensor, indicating whether to run the Network in training mode or inference mode.

• mask -- A mask or list of masks. A mask can be either a tensor or None (no mask).

返回

A tensor if there is a single output, or a list of tensors if there are more than one outputs.

CCDeep.ResNet.resnet.resnet_101()

return resnet101

CCDeep.ResNet.resnet.resnet_152()

return resnet152

CCDeep.ResNet.resnet.resnet_18()

return resnet18

CCDeep.ResNet.resnet.resnet_34()

return resnet34

CCDeep.ResNet.resnet.resnet_50()

return resnet50

Module contents