o ϯiY @shddlmZddlmZddlmZddlmZ dZdediZ dd e d e d ed ej fddZ dS))AnyN)create_r2plus1d)load_state_dict_from_urlz>https://dl.fbaipublicfiles.com/pytorchvideo/model_zoo/kinetics r2plus1d_r50z/R2PLUS1D_16x4_R50.pythFT pretrainedprogresskwargsreturncKsBtdddi|}|rtd}t||dd}|d}|||S) a R(2+1)D model architecture from [1] with pretrained weights based on 16x4 setting on the Kinetics dataset. Model with pretrained weights has top1 accuracy of 76.01. (trained on 8*8 GPUs) [1] "A closer look at spatiotemporal convolutions for action recognition" Du Tran, Heng Wang, Lorenzo Torresani, Jamie Ray, Yann LeCun, Manohar Paluri. CVPR 2018. https://arxiv.org/abs/1711.11248 Args: pretrained (bool): If True, returns a model pre-trained on the Kinetics dataset progress (bool): If True, displays a progress bar of the download to stderr kwargs: use these to modify any of the other model settings. All the options are defined in pytorchvideo/models/resnet.py NOTE: to use the pretrained model, do not modify the model configuration via the kwargs. Only modify settings via kwargs to initialize a new model without pretrained weights. dropout_rateg?rcpu)r map_location model_stateN)rcheckpoint_pathsrload_state_dict)rrrmodelpath checkpoint state_dictrrT/home/ubuntu/.local/lib/python3.10/site-packages/pytorchvideo/models/hub/r2plus1d.pyrs )FT) typingrtorch.nnnnpytorchvideo.models.r2plus1dr torch.hubrroot_dirrboolModulerrrrrs$