How to use 'Recall' as metric in keras classifier?

Question

How can use use the 'Recall' and other metrics in keras classifier. The following code only works for accuracy but if I change the metric to recall it fails.

Versions

"""
[('numpy', '1.19.1'),
 ('pandas', '1.1.1'),
 ('sklearn', '0.23.2'),
 ('tensorflow', '2.3.0'),
 ('keras', '2.4.3')]

"""

MWE

import numpy as np
import pandas as pd
import sklearn
import tensorflow as tf
import keras
from keras.models import Sequential
from keras.layers.core import Dense

SEED = 100


np.random.seed(100)
X = np.random.random((20, 3))
y = np.random.randint(0,2,size=20)

print(x.shape, y.shape) # (20, 3) (20,)

n_inputs = X.shape[1]

model = Sequential([
    Dense(n_inputs, input_shape=(n_inputs, ), activation='relu'),
    Dense(32, activation='relu'),
    Dense(2, activation='softmax')
])


METRIC = 'Recall' # Recall fails
# METRIC = 'accuracy' # accuracy works


model.compile('adam',loss='binary_crossentropy',metrics=[METRIC])
model.fit(X, y,validation_split=0.2,epochs=1)

Error

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-17-b372311b0ed4> in <module>
     38             epochs=10,
     39             shuffle=True,
---> 40             verbose=5)

~/opt/miniconda3/envs/tf2/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py in _method_wrapper(self, *args, **kwargs)
    106   def _method_wrapper(self, *args, **kwargs):
    107     if not self._in_multi_worker_mode():  # pylint: disable=protected-access
--> 108       return method(self, *args, **kwargs)
    109 
    110     # Running inside `run_distribute_coordinator` already.

~/opt/miniconda3/envs/tf2/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)
   1096                 batch_size=batch_size):
   1097               callbacks.on_train_batch_begin(step)
-> 1098               tmp_logs = train_function(iterator)
   1099               if data_handler.should_sync:
   1100                 context.async_wait()

~/opt/miniconda3/envs/tf2/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py in __call__(self, *args, **kwds)
    778       else:
    779         compiler = "nonXla"
--> 780         result = self._call(*args, **kwds)
    781 
    782       new_tracing_count = self._get_tracing_count()

~/opt/miniconda3/envs/tf2/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
    821       # This is the first call of __call__, so we have to initialize.
    822       initializers = []
--> 823       self._initialize(args, kwds, add_initializers_to=initializers)
    824     finally:
    825       # At this point we know that the initialization is complete (or less

~/opt/miniconda3/envs/tf2/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py in _initialize(self, args, kwds, add_initializers_to)
    695     self._concrete_stateful_fn = (
    696         self._stateful_fn._get_concrete_function_internal_garbage_collected(  # pylint: disable=protected-access
--> 697             *args, **kwds))
    698 
    699     def invalid_creator_scope(*unused_args, **unused_kwds):

~/opt/miniconda3/envs/tf2/lib/python3.7/site-packages/tensorflow/python/eager/function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
   2853       args, kwargs = None, None
   2854     with self._lock:
-> 2855       graph_function, _, _ = self._maybe_define_function(args, kwargs)
   2856     return graph_function
   2857 

~/opt/miniconda3/envs/tf2/lib/python3.7/site-packages/tensorflow/python/eager/function.py in _maybe_define_function(self, args, kwargs)
   3211 
   3212       self._function_cache.missed.add(call_context_key)
-> 3213       graph_function = self._create_graph_function(args, kwargs)
   3214       self._function_cache.primary[cache_key] = graph_function
   3215       return graph_function, args, kwargs

~/opt/miniconda3/envs/tf2/lib/python3.7/site-packages/tensorflow/python/eager/function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
   3073             arg_names=arg_names,
   3074             override_flat_arg_shapes=override_flat_arg_shapes,
-> 3075             capture_by_value=self._capture_by_value),
   3076         self._function_attributes,
   3077         function_spec=self.function_spec,

~/opt/miniconda3/envs/tf2/lib/python3.7/site-packages/tensorflow/python/framework/func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes)
    984         _, original_func = tf_decorator.unwrap(python_func)
    985 
--> 986       func_outputs = python_func(*func_args, **func_kwargs)
    987 
    988       # invariant: `func_outputs` contains only Tensors, CompositeTensors,

~/opt/miniconda3/envs/tf2/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py in wrapped_fn(*args, **kwds)
    598         # __wrapped__ allows AutoGraph to swap in a converted function. We give
    599         # the function a weak reference to itself to avoid a reference cycle.
--> 600         return weak_wrapped_fn().__wrapped__(*args, **kwds)
    601     weak_wrapped_fn = weakref.ref(wrapped_fn)
    602 

~/opt/miniconda3/envs/tf2/lib/python3.7/site-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
    971           except Exception as e:  # pylint:disable=broad-except
    972             if hasattr(e, "ag_error_metadata"):
--> 973               raise e.ag_error_metadata.to_exception(e)
    974             else:
    975               raise

ValueError: in user code:

    /Users/poudel/opt/miniconda3/envs/tf2/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py:806 train_function  *
        return step_function(self, iterator)
    /Users/poudel/opt/miniconda3/envs/tf2/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py:796 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    /Users/poudel/opt/miniconda3/envs/tf2/lib/python3.7/site-packages/tensorflow/python/distribute/distribute_lib.py:1211 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    /Users/poudel/opt/miniconda3/envs/tf2/lib/python3.7/site-packages/tensorflow/python/distribute/distribute_lib.py:2585 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    /Users/poudel/opt/miniconda3/envs/tf2/lib/python3.7/site-packages/tensorflow/python/distribute/distribute_lib.py:2945 _call_for_each_replica
        return fn(*args, **kwargs)
    /Users/poudel/opt/miniconda3/envs/tf2/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py:789 run_step  **
        outputs = model.train_step(data)
    /Users/poudel/opt/miniconda3/envs/tf2/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py:759 train_step
        self.compiled_metrics.update_state(y, y_pred, sample_weight)
    /Users/poudel/opt/miniconda3/envs/tf2/lib/python3.7/site-packages/tensorflow/python/keras/engine/compile_utils.py:409 update_state
        metric_obj.update_state(y_t, y_p, sample_weight=mask)
    /Users/poudel/opt/miniconda3/envs/tf2/lib/python3.7/site-packages/tensorflow/python/keras/utils/metrics_utils.py:90 decorated
        update_op = update_state_fn(*args, **kwargs)
    /Users/poudel/opt/miniconda3/envs/tf2/lib/python3.7/site-packages/tensorflow/python/keras/metrics.py:176 update_state_fn
        return ag_update_state(*args, **kwargs)
    /Users/poudel/opt/miniconda3/envs/tf2/lib/python3.7/site-packages/tensorflow/python/keras/metrics.py:1410 update_state  **
        sample_weight=sample_weight)
    /Users/poudel/opt/miniconda3/envs/tf2/lib/python3.7/site-packages/tensorflow/python/keras/utils/metrics_utils.py:353 update_confusion_matrix_variables
        y_pred.shape.assert_is_compatible_with(y_true.shape)
    /Users/poudel/opt/miniconda3/envs/tf2/lib/python3.7/site-packages/tensorflow/python/framework/tensor_shape.py:1134 assert_is_compatible_with
        raise ValueError("Shapes %s and %s are incompatible" % (self, other))

    ValueError: Shapes (None, 2) and (None, 1) are incompatible

Answer 1

Change the final layer output 2 to 1.

import numpy as np
import pandas as pd
import sklearn
import tensorflow as tf
import keras
from keras.models import Sequential
from keras.layers.core import Dense

SEED = 100


np.random.seed(100)
X = np.random.random((20, 3))
y = np.random.randint(0,2,size=20)

print(X.shape, y.shape) # (20, 3) (20,)

n_inputs = X.shape[1]

model = Sequential([
    Dense(n_inputs, input_shape=(n_inputs, ), activation='relu'),
    Dense(32, activation='relu'),
    Dense(1, activation='relu')
])


METRIC = 'Recall' # Recall fails
# METRIC = 'accuracy' # accuracy works


model.compile('adam',loss='binary_crossentropy',metrics=[METRIC])
model.fit(X, y,validation_split=0.2,epochs=1)