from torchinfo import summary

model = ConvNet()
batch_size = 16
summary(model, input_size=(batch_size, 1, 28, 28))

def summary(
    model: nn.Module,
    input_size: Optional[INPUT_SIZE_TYPE] = None,
    input_data: Optional[INPUT_DATA_TYPE] = None,
    batch_dim: Optional[int] = None,
    cache_forward_pass: Optional[bool] = None,
    col_names: Optional[Iterable[str]] = None,
    col_width: int = 25,
    depth: int = 3,
    device: Optional[torch.device] = None,
    dtypes: Optional[List[torch.dtype]] = None,
    mode: str | None = None,
    row_settings: Optional[Iterable[str]] = None,
    verbose: int = 1,
    **kwargs: Any,
) -> ModelStatistics:
"""
Summarize the given PyTorch model. Summarized information includes:
    1) Layer names,
    2) input/output shapes,
    3) kernel shape,
    4) # of parameters,
    5) # of operations (Mult-Adds),
    6) whether layer is trainable

NOTE: If neither input_data or input_size are provided, no forward pass through the
network is performed, and the provided model information is limited to layer names.

Args:
    model (nn.Module):
            PyTorch model to summarize. The model should be fully in either train()
            or eval() mode. If layers are not all in the same mode, running summary
            may have side effects on batchnorm or dropout statistics. If you
            encounter an issue with this, please open a GitHub issue.

    input_size (Sequence of Sizes):
            Shape of input data as a List/Tuple/torch.Size
            (dtypes must match model input, default is FloatTensors).
            You should include batch size in the tuple.
            Default: None

    input_data (Sequence of Tensors):
            Arguments for the model's forward pass (dtypes inferred).
            If the forward() function takes several parameters, pass in a list of
            args or a dict of kwargs (if your forward() function takes in a dict
            as its only argument, wrap it in a list).
            Default: None

    batch_dim (int):
            Batch_dimension of input data. If batch_dim is None, assume
            input_data / input_size contains the batch dimension, which is used
            in all calculations. Else, expand all tensors to contain the batch_dim.
            Specifying batch_dim can be an runtime optimization, since if batch_dim
            is specified, torchinfo uses a batch size of 1 for the forward pass.
            Default: None

    cache_forward_pass (bool):
            If True, cache the run of the forward() function using the model
            class name as the key. If the forward pass is an expensive operation,
            this can make it easier to modify the formatting of your model
            summary, e.g. changing the depth or enabled column types, especially
            in Jupyter Notebooks.
            WARNING: Modifying the model architecture or input data/input size when
            this feature is enabled does not invalidate the cache or re-run the
            forward pass, and can cause incorrect summaries as a result.
            Default: False

    col_names (Iterable[str]):
            Specify which columns to show in the output. Currently supported: (
                "input_size",
                "output_size",
                "num_params",
                "params_percent",
                "kernel_size",
                "mult_adds",
                "trainable",
            )
            Default: ("output_size", "num_params")
            If input_data / input_size are not provided, only "num_params" is used.

    col_width (int):
            Width of each column.
            Default: 25

    depth (int):
            Depth of nested layers to display (e.g. Sequentials).
            Nested layers below this depth will not be displayed in the summary.
            Default: 3

    device (torch.Device):
            Uses this torch device for model and input_data.
            If not specified, uses the dtype of input_data if given, or the
            parameters of the model. Otherwise, uses the result of
            torch.cuda.is_available().
            Default: None

    dtypes (List[torch.dtype]):
            If you use input_size, torchinfo assumes your input uses FloatTensors.
            If your model use a different data type, specify that dtype.
            For multiple inputs, specify the size of both inputs, and
            also specify the types of each parameter here.
            Default: None

    mode (str)
            Either "train" or "eval", which determines whether we call
            model.train() or model.eval() before calling summary().
            Default: "eval".

    row_settings (Iterable[str]):
            Specify which features to show in a row. Currently supported: (
                "ascii_only",
                "depth",
                "var_names",
            )
            Default: ("depth",)

    verbose (int):
            0 (quiet): No output
            1 (default): Print model summary
            2 (verbose): Show weight and bias layers in full detail
            Default: 1
            If using a Juypter Notebook or Google Colab, the default is 0.

    **kwargs:
            Other arguments used in `model.forward` function. Passing *args is no
            longer supported.

Return:
    ModelStatistics object
            See torchinfo/model_statistics.py for more information.
"""

from torchinfo import summary

model_stats = summary(your_model, (1, 3, 28, 28), verbose=0)
summary_str = str(model_stats)
# summary_str contains the string representation of the summary!

class LSTMNet(nn.Module):
    def __init__(self, vocab_size=20, embed_dim=300, hidden_dim=512, num_layers=2):
        super().__init__()
        self.hidden_dim = hidden_dim
        self.embedding = nn.Embedding(vocab_size, embed_dim)
        self.encoder = nn.LSTM(embed_dim, hidden_dim, num_layers=num_layers, batch_first=True)
        self.decoder = nn.Linear(hidden_dim, vocab_size)

    def forward(self, x):
        embed = self.embedding(x)
        out, hidden = self.encoder(embed)
        out = self.decoder(out)
        out = out.view(-1, out.size(2))
        return out, hidden

summary(
    LSTMNet(),
    (1, 100),
    dtypes=[torch.long],
    verbose=2,
    col_width=16,
    col_names=["kernel_size", "output_size", "num_params", "mult_adds"],
    row_settings=["var_names"],
)

import torchvision

model = torchvision.models.resnet152()
summary(model, (1, 3, 224, 224), depth=3)

class MultipleInputNetDifferentDtypes(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1a = nn.Linear(300, 50)
        self.fc1b = nn.Linear(50, 10)

        self.fc2a = nn.Linear(300, 50)
        self.fc2b = nn.Linear(50, 10)

    def forward(self, x1, x2):
        x1 = F.relu(self.fc1a(x1))
        x1 = self.fc1b(x1)
        x2 = x2.type(torch.float)
        x2 = F.relu(self.fc2a(x2))
        x2 = self.fc2b(x2)
        x = torch.cat((x1, x2), 0)
        return F.log_softmax(x, dim=1)

summary(model, [(1, 300), (1, 300)], dtypes=[torch.float, torch.long])

input_data = torch.randn(1, 300)
other_input_data = torch.randn(1, 300).long()
model = MultipleInputNetDifferentDtypes()

summary(model, input_data=[input_data, other_input_data, ...])

class ContainerModule(nn.Module):

    def __init__(self):
        super().__init__()
        self._layers = nn.ModuleList()
        self._layers.append(nn.Linear(5, 5))
        self._layers.append(ContainerChildModule())
        self._layers.append(nn.Linear(5, 5))

    def forward(self, x):
        for layer in self._layers:
            x = layer(x)
        return x


class ContainerChildModule(nn.Module):

    def __init__(self):
        super().__init__()
        self._sequential = nn.Sequential(nn.Linear(5, 5), nn.Linear(5, 5))
        self._between = nn.Linear(5, 5)

    def forward(self, x):
        out = self._sequential(x)
        out = self._between(out)
        for l in self._sequential:
            out = l(out)

        out = self._sequential(x)
        for l in self._sequential:
            out = l(out)
        return out

summary(ContainerModule(), (1, 5))