# Interpretation of Predictions
------------------------------------------------------------------------
source
### Interpretation
``` python
def Interpretation(
learn:Learner, dl:DataLoader, # `DataLoader` to run inference over
losses:TensorBase, # Losses calculated from `dl`
act:NoneType=None, # Activation function for prediction
):
```
*Interpretation base class, can be inherited for task specific
Interpretation classes*
[`Interpretation`](https://docs.fast.ai/interpret.html#interpretation)
is a helper base class for exploring predictions from trained models. It
can be inherited for task specific interpretation classes, such as
[`ClassificationInterpretation`](https://docs.fast.ai/interpret.html#classificationinterpretation).
[`Interpretation`](https://docs.fast.ai/interpret.html#interpretation)
is memory efficient and should be able to process any sized dataset,
provided the hardware could train the same model.
> **Note**
>
> [`Interpretation`](https://docs.fast.ai/interpret.html#interpretation)
> is memory efficient due to generating inputs, predictions, targets,
> decoded outputs, and losses for each item on the fly, using batch
> processing where possible.
------------------------------------------------------------------------
source
### Interpretation.from_learner
``` python
def from_learner(
learn, # Model used to create interpretation
ds_idx:int=1, # Index of `learn.dls` when `dl` is None
dl:DataLoader=None, # `Dataloader` used to make predictions
act:NoneType=None, # Override default or set prediction activation function
):
```
*Construct interpretation object from a learner*
------------------------------------------------------------------------
source
### Interpretation.top_losses
``` python
def top_losses(
k:int | None=None, # Return `k` losses, defaults to all
largest:bool=True, # Sort losses by largest or smallest
items:bool=False, # Whether to return input items
):
```
*`k` largest(/smallest) losses and indexes, defaulting to all losses.*
With the default of `k=None`, `top_losses` will return the entire
dataset’s losses. `top_losses` can optionally include the input items
for each loss, which is usually a file path or Pandas `DataFrame`.
------------------------------------------------------------------------
source
### Interpretation.plot_top_losses
``` python
def plot_top_losses(
k:int | collections.abc.MutableSequence, # Number of losses to plot
largest:bool=True, # Sort losses by largest or smallest
**kwargs
):
```
*Show `k` largest(/smallest) preds and losses. Implementation based on
type dispatch*
To plot the first 9 top losses:
``` python
interp = Interpretation.from_learner(learn)
interp.plot_top_losses(9)
```
Then to plot the 7th through 16th top losses:
``` python
interp.plot_top_losses(range(7,16))
```
------------------------------------------------------------------------
source
### Interpretation.show_results
``` python
def show_results(
idxs:list, # Indices of predictions and targets
**kwargs
):
```
*Show predictions and targets of `idxs`*
Like
[`Learner.show_results`](https://docs.fast.ai/learner.html#learner.show_results),
except can pass desired index or indicies for item(s) to show results
from.
------------------------------------------------------------------------
source
### ClassificationInterpretation
``` python
def ClassificationInterpretation(
learn:Learner, dl:DataLoader, # `DataLoader` to run inference over
losses:TensorBase, # Losses calculated from `dl`
act:NoneType=None, # Activation function for prediction
):
```
*Interpretation methods for classification models.*
------------------------------------------------------------------------
source
### ClassificationInterpretation.confusion_matrix
``` python
def confusion_matrix():
```
*Confusion matrix as an `np.ndarray`.*
------------------------------------------------------------------------
source
### ClassificationInterpretation.plot_confusion_matrix
``` python
def plot_confusion_matrix(
normalize:bool=False, # Whether to normalize occurrences
title:str='Confusion matrix', # Title of plot
cmap:str='Blues', # Colormap from matplotlib
norm_dec:int=2, # Decimal places for normalized occurrences
plot_txt:bool=True, # Display occurrence in matrix
**kwargs
):
```
*Plot the confusion matrix, with `title` and using `cmap`.*
------------------------------------------------------------------------
source
### ClassificationInterpretation.most_confused
``` python
def most_confused(
min_val:int=1
):
```
*Sorted descending largest non-diagonal entries of confusion matrix
(actual, predicted, \# occurrences*
------------------------------------------------------------------------
source
### SegmentationInterpretation
``` python
def SegmentationInterpretation(
learn:Learner, dl:DataLoader, # `DataLoader` to run inference over
losses:TensorBase, # Losses calculated from `dl`
act:NoneType=None, # Activation function for prediction
):
```
*Interpretation methods for segmentation models