The stem of the AnyNet model can be implemented as a sequential block containing a $3 \times 3$ convolution with a stride of $2$ and padding, followed by batch normalization and a ReLU activation function. This sequence halves the input resolution and generates the initial channels.

PyTorch Implementation:

class AnyNet(d2l.Classifier):
    def stem(self, num_channels):
        return nn.Sequential(
            nn.LazyConv2d(num_channels, kernel_size=3, stride=2, padding=1),
            nn.LazyBatchNorm2d(), nn.ReLU())

MXNet Implementation:

class AnyNet(d2l.Classifier):
    def stem(self, num_channels):
        net = nn.Sequential()
        net.add(nn.Conv2D(num_channels, kernel_size=3, padding=1, strides=2),
                nn.BatchNorm(), nn.Activation('relu'))
        return net

JAX Implementation:

class AnyNet(d2l.Classifier):
    arch: tuple
    stem_channels: int
    lr: float = 0.1
    num_classes: int = 10
    training: bool = True

    def setup(self):
        self.net = self.create_net()

    def stem(self, num_channels):
        return nn.Sequential([
            nn.Conv(num_channels, kernel_size=(3, 3), strides=(2, 2),
                    padding=(1, 1)),
            nn.BatchNorm(not self.training),
            nn.relu
        ])

TensorFlow Implementation:

class AnyNet(d2l.Classifier):
    def stem(self, num_channels):
        return tf.keras.models.Sequential([
            tf.keras.layers.Conv2D(num_channels, kernel_size=3, strides=2,
                                   padding='same'),
            tf.keras.layers.BatchNormalization(),
            tf.keras.layers.Activation('relu')])