ValueError: `y` argument is not supported when using `keras.utils.Sequence` as input-CodePudding

I am new to image processing and machine learning in python. I have been trying to execute a model in google colab using inceptionv3 but i am stuck at fitting the model.

    # fit the model
    # Run the cell. It will take some time to execute
    validation_data=test_set
    epochs=10
    steps_per_epoch=len(training_set)
    validation_steps=len(test_set)
    r = model.fit(
    training_set,
    validation_data,
    epochs,
    steps_per_epoch,
    validation_steps
    )

the whole code is in my git repository. https://github.com/Aditya757/MyRepository.git

this is my dataset image link below

      https://i.stack.imgur.com/jWaJ8.png

CodePudding user response：

You need to write

model.fit(
    training_set,
    validation_data=validation_data,
    epochs=epochs,
    steps_per_epoch=steps_per_epoch,
    validation_steps=validation_steps
)

If you pass validation_data without the keyword, it will bind to 'y'

EDIT: also, this was already answered. First result on google HERE...

CodePudding user response：

You have to pass feature vector/matrix X and ground truth y first. The .fit() method assumes validation_data to be your target/ground truth. Better you specify argument and pass its value.

model.fit(X_train, y_train, validation_data= (X_val, y_val), validation_steps=10, epochs=20, steps_per_epoch=len(X_train), callbacks=[checkpoint,early])