Type SparseTopKCategoricalAccuracy
Namespace tensorflow.keras.metrics
Parent MeanMetricWrapper
Interfaces ISparseTopKCategoricalAccuracy
Computes how often integer targets are in the top `K` predictions. Usage:
Usage with tf.keras API:
Show Example
m = tf.keras.metrics.SparseTopKCategoricalAccuracy() m.update_state([2, 1], [[0.1, 0.9, 0.8], [0.05, 0.95, 0]]) print('Final result: ', m.result().numpy()) # Final result: 1.0
Properties
- activity_regularizer
- activity_regularizer_dyn
- built
- count
- dtype
- dtype_dyn
- dynamic
- dynamic_dyn
- inbound_nodes
- inbound_nodes_dyn
- input
- input_dyn
- input_mask
- input_mask_dyn
- input_shape
- input_shape_dyn
- input_spec
- input_spec_dyn
- losses
- losses_dyn
- metrics
- metrics_dyn
- name
- name_dyn
- name_scope
- name_scope_dyn
- non_trainable_variables
- non_trainable_variables_dyn
- non_trainable_weights
- non_trainable_weights_dyn
- outbound_nodes
- outbound_nodes_dyn
- output
- output_dyn
- output_mask
- output_mask_dyn
- output_shape
- output_shape_dyn
- PythonObject
- reduction
- stateful
- submodules
- submodules_dyn
- supports_masking
- total
- trainable
- trainable_dyn
- trainable_variables
- trainable_variables_dyn
- trainable_weights
- trainable_weights_dyn
- updates
- updates_dyn
- variables
- variables_dyn
- weights
- weights_dyn