Args: x (Tensor): Has shape (B, C, H, W). In most case, C is 3. Returns: tuple: Contains merged results and i

Args: x (Tensor): Has shape (B, H*W, C_in). input_size (tuple[int]): The spatial shape of x, arrange as (H, W).

Load checkpoint from a file or URI. Args: model (Module): Module to load checkpoint. filename (str): Accept local filepath, URL,

Constructs a ResNet-101 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet progress (bool): If True,

Constructs a ResNet-101 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet progress (bool): If True,

Constructs a ResNet-152 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet progress (bool): If True,

Constructs a ResNet-18 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet progress (bool): If True,

Constructs a ResNet-34 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet progress (bool): If True,

Constructs a ResNet-50 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet progress (bool): If True,

Constructs a ResNet-50 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet progress (bool): If True,

Constructs a ResNeXt-101 32x4d model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet progress (bool): I

Constructs a ResNeXt-101 32x8d model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet progress (bool): I

Constructs a ResNeXt-50 32x4d model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet progress (bool): If

Save checkpoint to file. The checkpoint will have 3 fields: ``meta``, ``state_dict`` and ``optimizer``. By default ``meta`` will contain vers

Convert the model into training mode while keep layers freezed.