Conv+ReLU Fusion

Problem

Apply a fused valid-mode convolution, bias add and ReLU to a 2D image.

out[i][j] = max(0, bias + sum of the k x k patch times the kernel). Return integer values.

case 1

in: [[[1,2,3],[4,5,6],[7,8,9]],[[1,1],[1,1]],0]

expected: [[12,16],[24,28]]

case 2

in: [[[1,2,3],[4,5,6],[7,8,9]],[[1,1],[1,1]],-10]

expected: [[2,6],[14,18]]

case 3

in: [[[1,2,3],[4,5,6],[7,8,9]],[[1,0],[0,-1]],0]

expected: [[0,0],[0,0]]

Starter codePython

def conv_relu(feature, kernel, bias):
    # Your code here
    pass

3 test cases · run your code against them in the editor