sage.architecture.network.mscnn1d_catt_resnet2d_cbam

Filename : mscnn1d_catt_resnet2d_cbam.py Description : Short description of the file

Created on 2026-03-19 23:50:10

__author__ = Narenraju Nagarajan __copyright__ = Copyright 2026, ProjectName __license__ = MIT Licence __version__ = 0.0.1 __maintainer__ = Narenraju Nagarajan __affiliation__ = N/A __email__ = N/A __status__ = [‘inProgress’, ‘Archived’, ‘inUsage’, ‘Debugging’]

GitHub Repository: NULL

Documentation: NULL

Classes

MSCNN1D_catt_2DResNetCBAM

Multi-scale CNN backend + ResNet CBAM frontend for GW detection.

Module Contents

class MSCNN1D_catt_2DResNetCBAM(frontend_filters=32, frontend_kernel=64, cross_attention_heads=4, backend_resnet_size=50, norm_type='instancenorm')

Bases: torch.nn.Module

Multi-scale CNN backend + ResNet CBAM frontend for GW detection.

Parameters:

• backend_filters – base filter size for ConvBlock backend

• backend_kernel – base kernel size for ConvBlock backend

• resnet_size – 18, 34, 50, 101, 152

• norm_type (str) – ‘batchnorm’, ‘layernorm’, ‘instancenorm’

• num_point_estimates – number of continuous parameters to predict

• frontend_filters (int)

• frontend_kernel (int)

• cross_attention_heads (int)

• backend_resnet_size (int)

Initialize internal Module state, shared by both nn.Module and ScriptModule.

num_detectors

norm

frontend

cross_attention

gate

proj_gate

reduce

backend

avg_pool_1d

flatten

get_ranking_statistic

point_estimate_layers

forward(x)

x: Tensor of shape (batch, 2, signal_length) returns: raw, pred_prob, point_estimates (list of tensors)