TypeError: fit() got an unexpected keyword argument 'metrics'-CodePudding

model = tf.keras.Sequential()
model.add(tf.keras.layers.Conv1D(64, kernel_size=64, padding="same", activation='relu', input_shape=(x_train.shape[1], 1)))
model.add(tf.keras.layers.Conv1D(64, kernel_size=64, padding="same", activation='relu'))
model.add(tf.keras.layers.Dropout(0.6))
model.add(tf.keras.layers.MaxPooling1D(pool_size=2))
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(20, activation='relu'))
model.add(tf.keras.layers.Dense(10))
opt = tf.keras.optimizers.SGD(lr=0.01)
model.compile(loss='binary_crossentropy', optimizer=opt, metrics=['acc'])
print(model.summary())
model.fit(x_train, y_train, epochs=epochs,validation_data=(x_test,y_test), 
          batch_size=batch_size, metrics=['acc'], verbose=1)

Having this error:

TypeError: fit() got an unexpected keyword argument 'metrics'

I am using a dataframe which was originally in csv format. The shape of the dataframe after splitting it into 80:20 ratio using:

x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

is (206138, 198) (51535, 198) (206138,) (51535,)

CodePudding user response：

since metrics is a parameter to model.compile, not model.fit as mentioned by @Rahul, the quick fix was to remove the metrics from model.compile

CodePudding user response：

as it is with the error code The fit method of the keras sequential does not support the metric factor.

Please refer to the Tensorflow document

compile(
optimizer='rmsprop',
loss=None,
metrics=None,
loss_weights=None,
weighted_metrics=None,
run_eagerly=None,
steps_per_execution=None,
jit_compile=None,
**kwargs

)

and fit

fit(
x=None,
y=None,
batch_size=None,
epochs=1,
verbose='auto',
callbacks=None,
validation_split=0.0,
validation_data=None,
shuffle=True,
class_weight=None,
sample_weight=None,
initial_epoch=0,
steps_per_epoch=None,
validation_steps=None,
validation_batch_size=None,
validation_freq=1,
max_queue_size=10,
workers=1,
use_multiprocessing=False

)