Machine learning 全卷积神经网络的反卷积/上采样层规范
我正在努力了解该计划的实施情况。本文讨论了三种模型:fcn8、fcn16和FCN32。 . 以下是本文对fcn16的详细描述Machine learning 全卷积神经网络的反卷积/上采样层规范,machine-learning,computer-vision,tensorflow,deep-learning,Machine Learning,Computer Vision,Tensorflow,Deep Learning,我正在努力了解该计划的实施情况。本文讨论了三种模型:fcn8、fcn16和FCN32。 . 以下是本文对fcn16的详细描述 We first divide the output stride in half by predicting from a 16 pixel stride layer. We add a 1 × 1 convolution layer on top of pool4 to produce additional class predictions. We fuse th
We first divide the output stride in half by predicting
from a 16 pixel stride layer. We add a 1 × 1 convolution
layer on top of pool4 to produce additional class predictions.
We fuse this output with the predictions computed
on top of conv7 (convolutionalized fc7) at stride 32 by
adding a 2× upsampling layer and summing6 both predictions
(see Figure 3). We initialize the 2× upsampling to bilinear
interpolation, but allow the parameters to be learned
as described in Section 3.3. Finally, the stride 16 predictions
are upsampled back to the image.
对于来自pool4的跳过层和来自原始卷积层7的预测层,没有关于反卷积滤波器的内核大小的明确说明。此外,作者还提到在conv7上添加一个2*上采样层。这是否意味着一步=2?同样在这种情况下,反褶积层的内核大小应该是多少