TypeError: Expected float32, but got auto of type 'str'. Tensorflow error , tell me how to-CodePudding

I got TypeError: Expected float32, but got auto of type 'str'. error while fitting the sequential model. I checked my inputs both are numpy.ndarray.

type(xtrain),type(ytrain)
(numpy.ndarray, numpy.ndarray)

model = tf.keras.Sequential()

model.add(tf.keras.layers.Flatten(input_shape = (28,28)))
model.add(tf.keras.layers.Dense(32,activation='relu'))
model.add(tf.keras.layers.Dense(32,activation='relu'))
model.add(tf.keras.layers.Dense(10,activation=tf.keras.activations.softmax))

model.compile(loss = tf.keras.losses.SparseCategoricalCrossentropy,optimizer = 
    tf.keras.optimizers.Adam(learning_rate=.0001),metrics = ['accuracy'])

model.fit(x =xtrain,y = ytrain,epochs=100)

Epoch 1/100

TypeError Traceback (most recent call last) in () ----> 1 model.fit(x =xtrain,y = ytrain,epochs=100)

1 frames /usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py in autograph_handler(*args, **kwargs) 1127 except Exception as e: # pylint:disable=broad-except 1128 if hasattr(e, "ag_error_metadata"): -> 1129 raise e.ag_error_metadata.to_exception(e) 1130 else: 1131 raise

TypeError: in user code:

File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 878, in train_function  *
    return step_function(self, iterator)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 867, in step_function  **
    outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 860, in run_step  **
    outputs = model.train_step(data)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 810, in train_step
    y, y_pred, sample_weight, regularization_losses=self.losses)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/compile_utils.py", line 201, in __call__
    loss_value = loss_obj(y_t, y_p, sample_weight=sw)
File "/usr/local/lib/python3.7/dist-packages/keras/losses.py", line 141, in __call__
    losses = call_fn(y_true, y_pred)
File "/usr/local/lib/python3.7/dist-packages/keras/losses.py", line 245, in call  **
    return ag_fn(y_true, y_pred, **self._fn_kwargs)
File "/usr/local/lib/python3.7/dist-packages/keras/losses.py", line 752, in __init__  **
    from_logits=from_logits)
File "/usr/local/lib/python3.7/dist-packages/keras/losses.py", line 227, in __init__
    super().__init__(reduction=reduction, name=name)
File "/usr/local/lib/python3.7/dist-packages/keras/losses.py", line 88, in __init__
    losses_utils.ReductionV2.validate(reduction)
File "/usr/local/lib/python3.7/dist-packages/keras/utils/losses_utils.py", line 82, in validate
    if key not in cls.all():

TypeError: Expected float32, but got auto of type 'str'.

CodePudding user response：

The error may be in this part of the code:

model.compile(loss = tf.keras.losses.SparseCategoricalCrossentropy,optimizer = tf.keras.optimizers.Adam(learning_rate=.0001),metrics = ['accuracy'])

Try changing the loss parameter from tf.keras.losses.SparseCategoricalCrossentropy to tf.keras.losses.SparseCategoricalCrossentropy().

For some clarity, the difference between the two is that with tf.keras.losses.SparseCategoricalCrossentropy you are not passing and instance of the class, with tf.keras.losses.SparseCategoricalCrossentropy() you are.

CodePudding user response：

IIUC, your xtrain or ytrain is not float you need to convert them: (use copy=False for converting as in-place and without copy array and don't use more memory and convert them):

xtrain = xtrain.astype('float32', copy=False)
ytrain = ytrain.astype('float32', copy=False)