Donate. I desperately need donations to survive due to my health

Get paid by answering surveys Click here

Click here to donate

Remote/Work from Home jobs

Shape issue with model.fit()

on

I have an unexplicable issue when reaching the model.fit line in my code.

def train(self,sample):
    spec = np.asarray(sample.spec)
    labels = np.asarray(sample.labels)

    self.model.fit(spec, labels, epochs=5, validation_split=0.05, shuffle=True, verbose=1)

So i have a huge list of "sample" object wich contains an array (spec) of shape (193,) containing many representative features of the sound, and a list (labels) containing the labels describing the sample.

Here is how the input of my network is defined :

ins = keras.layers.Input(shape=(193,))

So i get this "Error. Couldn't load Error when checking input: expected input_1 to have shape (193,) but got array with shape (1,)" when reaching the model.fit line.

Here is a view of spec array with debugger right before the error :

debugger screenshot

Comments

Post a Comment