Mastering Computer Vision with TensorFlow 2.x

Right half-block

The code for the right block is as follows:

def create_right_half_blocks(leftfeatures, bottleneck, hglayer, num_channels):lf1, lf2, lf4, lf8 = leftfeaturesrf8 = bottom_layer(lf8, bottleneck, hglayer, num_channels)rf4 = connect_left_to_right(lf4, rf8, bottleneck, 'hg' + str(hglayer) + '_rf4', num_channels)rf2 = connect_left_to_right(lf2, rf4, bottleneck, 'hg' + str(hglayer) + '_rf2', num_channels)rf1 = connect_left_to_right(lf1, rf2, bottleneck, 'hg' + str(hglayer) + '_rf1', num_channels)return rf1

In the preceding code, lf8, lf4, lf2, and lf1 have left features. The corresponding right block's features – rf8, rf4, rf2, and rf1 – are generated by applying the left to right bottleneck block to each of the left features. The ...