The Conv1 layer has the following specifications:

  • Kernel size: 2003 (200 filters of size 33)
  • Stride: 50*1 (move the filters by 50 units horizontally and 1 unit vertically)
  • Padding: 1 (add a border of 1 pixel around the input)

The input to this layer is a tensor of size 110,00012, which means it has 1 channel, a height of 10,000 pixels, and a width of 12 pixels.

The activation function used in this layer is ReLU (Rectified Linear Unit), which applies the function max(0, x) to each element of the output.

Note: The output size of the Conv1 layer will depend on the stride and padding used, as well as the input size

Conv1 Kernel sizeStridePadding :20035011 Input size:11000012 Activation :Relu

原文地址: https://www.cveoy.top/t/topic/hLZv 著作权归作者所有。请勿转载和采集!

免费AI点我,无需注册和登录