vissl.meters package¶
vissl.meters.accuracy_list_meter¶
-
class
vissl.meters.accuracy_list_meter.
AccuracyListMeter
(num_meters: int, topk_values: List[int], meter_names: List[str])[source]¶ Bases:
classy_vision.meters.classy_meter.ClassyMeter
Meter to calculate top-k accuracy for single label image classification task.
Supports Single target and multiple output. A list of accuracy meters is constructed and each output has a meter associated.
- Parameters
num_meters – number of meters and hence we have same number of outputs
topk_values – list of int k values. Example: [1, 5]
meter_names – list of str indicating the name of meter. Usually corresponds to the output layer name.
-
classmethod
from_config
(meters_config: vissl.utils.hydra_config.AttrDict)[source]¶ Get the AccuracyListMeter instance from the user defined config
-
property
name
¶ Name of the meter
-
property
value
¶ Value of the meter globally synced. For each output, all the top-k values are returned. If there are several meters attached to the same layer name, a list of top-k values will be returned for that layer name meter.
-
update
(model_output: Union[torch.Tensor, List[torch.Tensor]], target: torch.Tensor)[source]¶ Updates the value of the meter for the given model output list and targets.
- Parameters
model_output – list of tensors of shape (B, C) where each value is either logit or class probability.
target – tensor of shape (B).
NOTE: For binary classification, C=2.
vissl.meters.mean_ap_meter¶
-
class
vissl.meters.mean_ap_meter.
MeanAPMeter
(meters_config: vissl.utils.hydra_config.AttrDict)[source]¶ Bases:
classy_vision.meters.classy_meter.ClassyMeter
Meter to calculate mean AP metric for multi-label image classification task.
- Parameters
meters_config (AttrDict) – config containing the meter settings
meters_config should specify the num_classes
-
classmethod
from_config
(meters_config: vissl.utils.hydra_config.AttrDict)[source]¶ Get the AccuracyListMeter instance from the user defined config
-
property
name
¶ Name of the meter
-
property
value
¶ Value of the meter globally synced. mean AP and AP for each class is returned
-
gather_scores
(scores: torch.Tensor)[source]¶ Do a gather over all embeddings, so we can compute the loss. Final shape is like: (batch_size * num_gpus) x embedding_dim
-
gather_targets
(targets: torch.Tensor)[source]¶ Do a gather over all embeddings, so we can compute the loss. Final shape is like: (batch_size * num_gpus) x embedding_dim
vissl.meters.mean_ap_list_meter¶
-
class
vissl.meters.mean_ap_list_meter.
MeanAPListMeter
(meters_config: vissl.utils.hydra_config.AttrDict)[source]¶ Bases:
classy_vision.meters.classy_meter.ClassyMeter
Meter to calculate mean AP metric for multi-label image classification task on multiple output single target.
Supports Single target and multiple output. A list of mean AP meters is constructed and each output has a meter associated.
- Parameters
meters_config (AttrDict) – config containing the meter settings
meters_config should specify the num_meters and meter_names
-
classmethod
from_config
(meters_config: vissl.utils.hydra_config.AttrDict)[source]¶ Get the AccuracyListMeter instance from the user defined config
-
property
name
¶ Name of the meter
-
property
value
¶ Value of the meter globally synced. For each output, mean AP and AP for each class is returned.
-
update
(model_output: Union[torch.Tensor, List[torch.Tensor]], target: torch.Tensor)[source]¶ Updates the value of the meter for the given model output list and targets.
- Parameters
model_output – list of tensors of shape (B, C) where each value is either logit or class probability.
target – tensor of shape (B).
NOTE: For binary classification, C=2.