o ϯi @shddlmZddlmZddlmZddlmZ dZdediZ dd e d e d ed ej fddZ dS))AnyN) create_csn)load_state_dict_from_urlz>https://dl.fbaipublicfiles.com/pytorchvideo/model_zoo/kineticscsn_r101z/CSN_32x2_R101.pythFT pretrainedprogresskwargsreturncKsHtd dtjdd|}|r"td}t||dd}|d}|||S) a Channel-Separated Convolutional Networks (CSN) R101 model architecture [1] with pretrained weights based on 32x2 setting on the Kinetics dataset. Model with pretrained weights has top1 accuracy of 77.0 (trained on 16x8 GPUs). [1] "Video classification with channel-separated convolutional networks" Du Tran, Heng Wang, Lorenzo Torresani, Matt Feiszli. ICCV 2019. https://arxiv.org/abs/1904.02811 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. e)r ) model_depth stem_poolhead_pool_kernel_sizercpu)r map_location model_stateN)rnn MaxPool3dcheckpoint_pathsrload_state_dict)rrrmodelpath checkpoint state_dictrrO/home/ubuntu/.local/lib/python3.10/site-packages/pytorchvideo/models/hub/csn.pyrs )FT) typingrtorch.nnrpytorchvideo.models.csnr torch.hubrroot_dirrboolModulerrrrrs$