class Model(torch.nn.Module):
    def __init__(self):
        super().__init__()
        self.convolution = torch.nn.Sequential(
            torch.nn.Conv2d(1, 32, 3),
            torch.nn.ReLU(inplace=True),  # Inplace may harm kernel fusion
            torch.nn.Conv2d(32, 128, 3, groups=32),  # Depthwise is slower in PyTorch
            torch.nn.ReLU(inplace=True),  # Same as before
            torch.nn.Conv2d(128, 250, 3),  # Wrong output size for TensorCores
        )

        self.classifier = torch.nn.Sequential(
            torch.nn.Linear(250, 64),  # Wrong input size for TensorCores
            torch.nn.ReLU(),  # Fine, no info about this layer
            torch.nn.Linear(64, 10),  # Wrong output size for TensorCores
        )

    def forward(self, inputs):
        convolved = torch.nn.AdaptiveAvgPool2d(1)(self.convolution(inputs)).flatten()
        return self.classifier(convolved)

# All you have to do
print(torchfunc.performance.tips(Model()))

# Inb4 MNIST, you can use any module with those functions
model = torch.nn.Linear(784, 10)
torchfunc.seed(0)
frozen = torchfunc.module.freeze(model, bias=False)

with torchfunc.Timer() as timer:
  frozen(torch.randn(32, 784)
  print(timer.checkpoint()) # Time since the beginning
  frozen(torch.randn(128, 784)
  print(timer.checkpoint()) # Since last checkpoint

print(f"Overall time {timer}; Model size: {torchfunc.sizeof(frozen)}")

# Still MNIST but any module can be put in it's place
model = torch.nn.Sequential(
    torch.nn.Linear(784, 100),
    torch.nn.ReLU(),
    torch.nn.Linear(100, 50),
    torch.nn.ReLU(),
    torch.nn.Linear(50, 10),
)
# Recorder which sums all inputs to layers
recorder = torchfunc.hooks.recorders.ForwardPre(reduction=lambda x, y: x+y)
# Record only for torch.nn.Linear
recorder.children(model, types=(torch.nn.Linear,))
# Train your network normally (or pass data through it)
...
# Activations of all neurons of first layer!
print(recorder[1]) # You can also post-process this data easily with apply