mindspore.nn.WithEvalCell
- class mindspore.nn.WithEvalCell(network, loss_fn, add_cast_fp32=False)[source]
Cell that returns loss, output and label for evaluation.
This Cell accepts a network and loss function as arguments and computes loss for model. It returns loss, output and label to calculate the metrics.
- Parameters
- Inputs:
data (Tensor) - Tensor of shape \((N, \ldots)\).
label (Tensor) - Tensor of shape \((N, \ldots)\).
- Outputs:
Tuple, containing a scalar loss Tensor, a network output Tensor of shape \((N, \ldots)\) and a label Tensor of shape \((N, \ldots)\).
- Raises
TypeError – If add_cast_fp32 is not a bool.
- Supported Platforms:
Ascend
GPU
CPU
Examples
>>> # For a defined network Net without loss function >>> net = Net() >>> loss_fn = nn.SoftmaxCrossEntropyWithLogits() >>> eval_net = nn.WithEvalCell(net, loss_fn)