An AnyNet stage is implemented by sequentially stacking a specified depth of ResNeXt blocks. The first block in the sequence uses a spatial stride of $2$ and a $1 \times 1$ convolution on the residual branch to halve the feature map resolution. The remaining blocks use a default stride of $1$, preserving the spatial dimensions.

PyTorch Implementation:

@d2l.add_to_class(AnyNet)
def stage(self, depth, num_channels, groups, bot_mul):
    blk = []
    for i in range(depth):
        if i == 0:
            blk.append(d2l.ResNeXtBlock(num_channels, groups, bot_mul,
                use_1x1conv=True, strides=2))
        else:
            blk.append(d2l.ResNeXtBlock(num_channels, groups, bot_mul))
    return nn.Sequential(*blk)

MXNet Implementation:

@d2l.add_to_class(AnyNet)
def stage(self, depth, num_channels, groups, bot_mul):
    net = nn.Sequential()
    for i in range(depth):
        if i == 0:
            net.add(d2l.ResNeXtBlock(
                num_channels, groups, bot_mul, use_1x1conv=True, strides=2))
        else:
            net.add(d2l.ResNeXtBlock(
                num_channels, num_channels, groups, bot_mul))
    return net

JAX Implementation:

@d2l.add_to_class(AnyNet)
def stage(self, depth, num_channels, groups, bot_mul):
    blk = []
    for i in range(depth):
        if i == 0:
            blk.append(d2l.ResNeXtBlock(num_channels, groups, bot_mul,
                use_1x1conv=True, strides=(2, 2), training=self.training))
        else:
            blk.append(d2l.ResNeXtBlock(num_channels, groups, bot_mul,
                                        training=self.training))
    return nn.Sequential(blk)

TensorFlow Implementation:

@d2l.add_to_class(AnyNet)
def stage(self, depth, num_channels, groups, bot_mul):
    net = tf.keras.models.Sequential()
    for i in range(depth):
        if i == 0:
            net.add(d2l.ResNeXtBlock(num_channels, groups, bot_mul,
                use_1x1conv=True, strides=2))
        else:
            net.add(d2l.ResNeXtBlock(num_channels, groups, bot_mul))
    return net