Remove the fc layer parameter from state_dict.

evaluate the attribute recognition precision

3x3 convolution with padding

Args: sys_device_ids: a tuple; which GPUs to use e.g. sys_device_ids = (), only use cpu sys_device_ids = (3,),

Multiplied by a factor at the beging of specified epochs. Different params groups specify thier own base learning rates. Args: pa

Input: gt_result, pt_result, N*L, with 0/1 Output: result a dictionary, including label-based and instance-based evaluation

create a dataset split file, which consists of index of the train/val/test splits

create a dataset split file, which consists of index of the train/val/test splits

create a dataset split file, which consists of index of the train/val/test splits

create a dataset split file, which consists of index of the train/val/test splits

extract feature for images

create a dataset description file, which consists of images, labels

create a dataset description file, which consists of images, labels

create a dataset description file, which consists of images, labels

create a dataset description file, which consists of images, labels

load state_dict of module & optimizer from file Args: modules_optims: A two-element list which contains module and optimizer

maybe_modules, an object or a list of objects.

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

save state_dict of modules/optimizers to file Args: modules_optims: a two-element list which contains a module and a optimizer

transform a 1-length pytorch Variable or Tensor to scalar

Args: img: a 3-dimensional torch tensor with shape [R,G,B]*H*W Returns: img: a 3-dimensional padded tensor wi

Args: index (int): Index Returns: tuple: (image, target) where target is the index of the target class

copy parameter from src_state_dict to model Arguments: model: A torch.nn.Module object src_state_dict: a dict containing para

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

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

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

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