EpochMetric

class ignite.metrics.EpochMetric(compute_fn, output_transform=<function EpochMetric.<lambda>>, check_compute_fn=True, device=device(type='cpu'))

Class for metrics that should be computed on the entire output history of a model. Model’s output and targets are restricted to be of shape (batch_size, n_targets). Output datatype should be float32. Target datatype should be long for classification and float for regression.

Warning

Current implementation stores all input data (output and target) in as tensors before computing a metric. This can potentially lead to a memory error if the input data is larger than available RAM.

In distributed configuration, all stored data (output and target) is mutually collected across all processes using all gather collective operation. This can potentially lead to a memory error. Compute method executes compute_fn on zero rank process only and final result is broadcasted to all processes.

• update must receive output of the form (y_pred, y).

Parameters

• compute_fn (Callable[[Tensor, Tensor], float]) – a callable which receives two tensors as the predictions and targets and returns a scalar. Input tensors will be on specified device (see arg below).

• output_transform (Callable) – a callable that is used to transform the Engine’s process_function’s output into the form expected by the metric. This can be useful if, for example, you have a multi-output model and you want to compute the metric with respect to one of the outputs.

• check_compute_fn (bool) – if True, compute_fn is run on the first batch of data to ensure there are no issues. If issues exist, user is warned that there might be an issue with the compute_fn. Default, True.

• device (Union[str, device]) – optional device specification for internal storage.

Example

For more information on how metric works with Engine, visit Attach Engine API.

from collections import OrderedDict

import torch
from torch import nn, optim

from ignite.engine import *
from ignite.handlers import *
from ignite.metrics import *
from ignite.utils import *
from ignite.contrib.metrics.regression import *
from ignite.contrib.metrics import *

# create default evaluator for doctests

def eval_step(engine, batch):
    return batch

default_evaluator = Engine(eval_step)

# create default optimizer for doctests

param_tensor = torch.zeros([1], requires_grad=True)
default_optimizer = torch.optim.SGD([param_tensor], lr=0.1)

# create default trainer for doctests
# as handlers could be attached to the trainer,
# each test must define his own trainer using `.. testsetup:`

def get_default_trainer():

    def train_step(engine, batch):
        return batch

    return Engine(train_step)

# create default model for doctests

default_model = nn.Sequential(OrderedDict([
    ('base', nn.Linear(4, 2)),
    ('fc', nn.Linear(2, 1))
]))

manual_seed(666)

def mse_fn(y_preds, y_targets):
    return torch.mean(((y_preds - y_targets.type_as(y_preds)) ** 2)).item()

metric = EpochMetric(mse_fn)
metric.attach(default_evaluator, "mse")
y_true = torch.tensor([0, 1, 2, 3, 4, 5])
y_pred = y_true * 0.75
state = default_evaluator.run([[y_pred, y_true]])
print(state.metrics["mse"])

0.5729...

Warning

EpochMetricWarning: User is warned that there are issues with compute_fn on a batch of data processed. To disable the warning, set check_compute_fn=False.

Methods

compute	Computes the metric based on it's accumulated state.
reset	Resets the metric to it's initial state.
update	Updates the metric's state using the passed batch output.

compute()

Computes the metric based on it’s accumulated state.

By default, this is called at the end of each epoch.

Returns

the actual quantity of interest. However, if a Mapping is returned, it will be (shallow) flattened into engine.state.metrics when completed() is called.

Return type

Any

Raises

NotComputableError – raised when the metric cannot be computed.

reset()

Resets the metric to it’s initial state.

By default, this is called at the start of each epoch.

Return type

None

update(output)

Updates the metric’s state using the passed batch output.

By default, this is called once for each batch.

Parameters

output (Tuple[Tensor, Tensor]) – the is the output from the engine’s process function.

Return type

None