bitorch.models.resnet.BottleneckV1¶
- class bitorch.models.resnet.BottleneckV1(in_channels: int, out_channels: int, stride: int)[source]¶
Bottleneck V1 from “Deep Residual Learning for Image Recognition” paper. This is used for ResNet V1 for 50, 101, 152 layers.
Methods
builds body and downsampling layers
forwards the input tensor x through the building block.
Attributes