o ϯi:3@s&ddlmZmZddlZddlmZddlmZddlm Z m Z m Z ddl m Z ddddejejd d d dd d d dddde dejdd ddddedededededededeedeededeed eed!eed"eed#ed$eed%eed&ed'ed(ed)eed*eed+ed,ed-ejf2d.d/ZdS)0)CallableTupleN)create_res_basic_head)Netcreate_bottleneck_blockcreate_res_stage)create_res_basic_stem2i@)r r )r)r r r r r r )r r r r )r rrr)r r r T) input_channel model_depthmodel_num_class dropout_ratenorm activation stem_dim_outstem_conv_kernel_sizestem_conv_stride stem_poolstem_pool_kernel_sizestem_pool_stridestage_conv_a_kernel_sizestage_conv_b_kernel_sizestage_conv_b_width_per_groupstage_spatial_stridestage_temporal_stride bottleneckbottleneck_ratio head_poolhead_pool_kernel_sizehead_output_sizehead_activationhead_output_with_global_averagerrrrrrrrrrrrrrrr r!r"r#r$r%r&r'r(returnc$CsLtjddddd}||vsJ|d|||}g}t||||dd|D| | | d d| D||d }|||}|d }tt|D]?}||}||} ||||||f}!t| ||||| d d d| D| |!dd| D||d ||d}"||"|}|d}qMt ||||||||d}#||#t t |dS)uj Build Channel-Separated Convolutional Networks (CSN): Video classification with channel-separated convolutional networks. Du Tran, Heng Wang, Lorenzo Torresani, Matt Feiszli. ICCV 2019. CSN follows the ResNet style architecture including three parts: Stem, Stages and Head. The three parts are assembled in the following order: :: Input ↓ Stem ↓ Stage 1 ↓ . . . ↓ Stage N ↓ Head CSN uses depthwise convolution. To further reduce the computational cost, it uses low resolution (112x112), short clips (4 frames), different striding and kernel size, etc. Args: input_channel (int): number of channels for the input video clip. model_depth (int): the depth of the resnet. Options include: 50, 101, 152. model_num_class (int): the number of classes for the video dataset. dropout_rate (float): dropout rate. norm (callable): a callable that constructs normalization layer. activation (callable): a callable that constructs activation layer. stem_dim_out (int): output channel size to stem. stem_conv_kernel_size (tuple): convolutional kernel size(s) of stem. stem_conv_stride (tuple): convolutional stride size(s) of stem. stem_pool (callable): a callable that constructs resnet head pooling layer. stem_pool_kernel_size (tuple): pooling kernel size(s). stem_pool_stride (tuple): pooling stride size(s). stage_conv_a_kernel_size (tuple): convolutional kernel size(s) for conv_a. stage_conv_b_kernel_size (tuple): convolutional kernel size(s) for conv_b. stage_conv_b_width_per_group(int): the width of each group for conv_b. Set it to 1 for depthwise convolution. stage_spatial_stride (tuple): the spatial stride for each stage. stage_temporal_stride (tuple): the temporal stride for each stage. bottleneck (callable): a callable that constructs bottleneck block layer. Examples include: create_bottleneck_block. bottleneck_ratio (int): the ratio between inner and outer dimensions for the bottleneck block. head_pool (callable): a callable that constructs resnet head pooling layer. head_pool_kernel_size (tuple): the pooling kernel size. head_output_size (tuple): the size of output tensor for head. head_activation (callable): a callable that constructs activation layer. head_output_with_global_average (bool): if True, perform global averaging on the head output. Returns: (nn.Module): the csn model. zPYTORCHVIDEO.model.create_csn)r rr )r rr )r $r )r ez is not in cSg|]}|dqSr.0sizer2r2K/home/ubuntu/.local/lib/python3.10/site-packages/pytorchvideo/models/csn.py zcreate_csn..cSr0r1r2r3r2r2r6r7r8) in_channels out_channelsconv_kernel_size conv_stride conv_paddingpoolpool_kernel_size pool_stride pool_paddingrrrrcSr0r1r2r3r2r2r6r7r8cSr0r1r2r3r2r2r6r7r8)depthdim_in dim_innerdim_outr"conv_a_kernel_size conv_a_strideconv_a_paddingconv_b_kernel_size conv_b_strideconv_b_paddingconv_b_num_groupsconv_b_dilationrrr) in_features out_featuresr> output_sizer?rroutput_with_global_average)blocks) torch_C_log_api_usage_oncekeysrappendrangelenrrrnn ModuleList)$rrrrrrrrrrrrrrrr r!r"r#r$r%r&r'r(_MODEL_STAGE_DEPTH stage_depthsrRstem stage_dim_in stage_dim_outidxstage_dim_innerrBstage_conv_b_stridestageheadr2r2r6 create_csn s| g         rf)typingrrrStorch.nnrZpytorchvideo.models.headrpytorchvideo.models.resnetrrrpytorchvideo.models.stemr BatchNorm3dReLU AvgPool3dintfloatboolModulerfr2r2r2r6s       !