【发布时间】:2020-11-10 02:46:43
【问题描述】:
我是 Pytorch (python) 的新手,我刚刚浏览了他们的官方教程,发现了这个简单的神经网络架构。一切都很清楚,但是那些数字,最后三个全连接层,它们来自哪里?
self.fc1 = nn.Linear(16 * 6 * 6, 120) # 6*6 from image dimension and 16 from last conv layer
self.fc2 = nn.Linear(120, 84) # but here, 120? 84? why? is this just random or there is some logic behind it?
self.fc3 = nn.Linear(84, 10)
【问题讨论】:
标签: python-3.x pytorch conv-neural-network