Method _construct_network

slowfast/models/ptv_model_builder.py:245–411

Builds a SlowFast model. Args: cfg (CfgNode): model building configs, details are in the comments of the config file.

(self, cfg)

        self._construct_network(cfg)

    def _construct_network(self, cfg):
        """
        Builds a SlowFast model.

        Args:
            cfg (CfgNode): model building configs, details are in the
                comments of the config file.
        """
        _MODEL_STAGE_DEPTH = {50: (3, 4, 6, 3), 101: (3, 4, 23, 3)}

        # Params from configs.
        norm_module = get_norm(cfg)
        pool_size = _POOL1[cfg.MODEL.ARCH]
        num_groups = cfg.RESNET.NUM_GROUPS
        width_per_group = cfg.RESNET.WIDTH_PER_GROUP
        spatial_dilations = cfg.RESNET.SPATIAL_DILATIONS
        spatial_strides = cfg.RESNET.SPATIAL_STRIDES
        temp_kernel = _TEMPORAL_KERNEL_BASIS[cfg.MODEL.ARCH]
        num_block_temp_kernel = cfg.RESNET.NUM_BLOCK_TEMP_KERNEL
        stage_depth = _MODEL_STAGE_DEPTH[cfg.RESNET.DEPTH]

        stage_conv_a_kernel_sizes = [[], []]
        for pathway in range(2):
            for stage in range(4):
                stage_conv_a_kernel_sizes[pathway].append(
                    ((temp_kernel[stage + 1][pathway][0], 1, 1),)
                    * num_block_temp_kernel[stage][pathway]
                    + ((1, 1, 1),)
                    * (
                        stage_depth[stage]
                        - num_block_temp_kernel[stage][pathway]
                    )
                )

        # Head from config
        # Number of stages = 4
        stage_dim_in = cfg.RESNET.WIDTH_PER_GROUP * 2 ** (4 + 1)
        head_in_features = stage_dim_in
        for reduction_ratio in cfg.SLOWFAST.BETA_INV:
            head_in_features = (
                head_in_features + stage_dim_in // reduction_ratio
            )

        if cfg.DETECTION.ENABLE:
            # self.detection_head = create_res_roi_pooling_head(
            #     in_features=head_in_features,
            #     out_features=cfg.MODEL.NUM_CLASSES,
            #     pool=None,
            #     output_size=(1, 1, 1),
            #     dropout_rate=cfg.MODEL.DROPOUT_RATE,
            #     activation=None,
            #     output_with_global_average=False,
            #     pool_spatial=nn.MaxPool2d,
            #     resolution=[cfg.DETECTION.ROI_XFORM_RESOLUTION] * 2,
            #     spatial_scale=1.0 / float(cfg.DETECTION.SPATIAL_SCALE_FACTOR),
            #     sampling_ratio=0,
            #     roi=ROIAlign,
            # )