Data Science Stack Exchange is a question and answer site for Data science professionals, Machine Learning specialists, and those interested in learning more about the field. It only takes a minute to sign up.
Sign up to join this community
The paper by He et al. "Deep Residual Learning for Image Recognition" illustrates their residual network in Figure 3 as follows:
I am not a neural network expert, so could somebody please explain to me what the highlighted notation above "3x3 conv, 256, /2" means? The first part is clear (convolutional neural network with a 3x3 pixel window), but what is the "256" and the "/2"?
3x3 conv, 256, /2
stands for:
The latter is explained on page 3 where the authors state
(ii) if the feature map size is halved, the number of filters is doubled so as to preserve the time complexity per layer. We perform downsampling directly by convolutional layers that have a stride of 2.
This means ResNet does, except for the beginning and end of the network, not use pooling layers to reduce spatial dimensions but conv. layers.
Also, table 1 shows what is happening:
The part you have highlighted in your screenshot is the transition from conv3_x to the conv4_x layer of the 34-layer network. As you can see in the table the output size is reduced from 28x28 to 14x14 (that is what /2 does) while the filters are doubled from 128 to 256.
