Bottleneck Transformers for Visual Recognition

Experiments

Summary

Usage (example)

• Model

from model import Model

model = ResNet50(num_classes=1000, resolution=(224, 224))
x = torch.randn([2, 3, 224, 224])
print(model(x).size())

• Module

from model import MHSA

resolution = 14
mhsa = MHSA(planes, width=resolution, height=resolution)

Reference

• Paper link
• Author: Aravind Srinivas, Tsung-Yi Lin, Niki Parmar, Jonathon Shlens, Pieter Abbeel, Ashish Vaswani
• Organization: UC Berkeley, Google Research