The Network in Network (NiN) block can be implemented programmatically across deep learning frameworks as a sequential container of convolutional layers. It consists of an initial spatial convolution followed by two $1 \times 1$ convolutions that act as per-pixel fully connected layers. Each convolutional layer in the block is immediately followed by a ReLU activation function.

PyTorch Implementation:

def nin_block(out_channels, kernel_size, strides, padding):
    return nn.Sequential(
        nn.LazyConv2d(out_channels, kernel_size, strides, padding), nn.ReLU(),
        nn.LazyConv2d(out_channels, kernel_size=1), nn.ReLU(),
        nn.LazyConv2d(out_channels, kernel_size=1), nn.ReLU())

MXNet Implementation:

def nin_block(num_channels, kernel_size, strides, padding):
    blk = nn.Sequential()
    blk.add(nn.Conv2D(num_channels, kernel_size, strides, padding,
                      activation='relu'),
            nn.Conv2D(num_channels, kernel_size=1, activation='relu'),
            nn.Conv2D(num_channels, kernel_size=1, activation='relu'))
    return blk

JAX Implementation:

def nin_block(out_channels, kernel_size, strides, padding):
    return nn.Sequential([
        nn.Conv(out_channels, kernel_size, strides, padding),
        nn.relu,
        nn.Conv(out_channels, kernel_size=(1, 1)), nn.relu,
        nn.Conv(out_channels, kernel_size=(1, 1)), nn.relu])

TensorFlow Implementation:

def nin_block(out_channels, kernel_size, strides, padding):
    return tf.keras.models.Sequential([
    tf.keras.layers.Conv2D(out_channels, kernel_size, strides=strides,
                           padding=padding),
    tf.keras.layers.Activation('relu'),
    tf.keras.layers.Conv2D(out_channels, 1),
    tf.keras.layers.Activation('relu'),
    tf.keras.layers.Conv2D(out_channels, 1),
    tf.keras.layers.Activation('relu')])