This specific variant (26w-4s) is designed to offer a superior balance between accuracy and computational cost. Res2Net: A New Multi-scale Backbone Architecture - arXiv
The Res2Net50-v1b-26w-4s-3cf99910.pth model has several advantages, including:
: This refers to a common modification of the ResNet "stem" where the initial convolution is replaced by three
from mmcls.models import build_classifier config = dict( type='ImageClassifier', backbone=dict( type='Res2Net', depth=50, base_width=26, scale=4, deep_stem=False, avg_down=False), neck=dict(type='GlobalAveragePooling'), head=dict(type='LinearClsHead', num_classes=1000)) model = build_classifier(config) model.load_state_dict(state_dict, strict=True)
This specific variant (26w-4s) is designed to offer a superior balance between accuracy and computational cost. Res2Net: A New Multi-scale Backbone Architecture - arXiv
The Res2Net50-v1b-26w-4s-3cf99910.pth model has several advantages, including:
: This refers to a common modification of the ResNet "stem" where the initial convolution is replaced by three
from mmcls.models import build_classifier config = dict( type='ImageClassifier', backbone=dict( type='Res2Net', depth=50, base_width=26, scale=4, deep_stem=False, avg_down=False), neck=dict(type='GlobalAveragePooling'), head=dict(type='LinearClsHead', num_classes=1000)) model = build_classifier(config) model.load_state_dict(state_dict, strict=True)
© 2026 — DLS Source
