Error of placeholder tensor in _evaluate function about keract

[jordangierschendorf]

Hi again,

I solved my problem by changing my initial model definition to:

vgg_model = applications.VGG16(weights=None, include_top=False, input_shape=(224, 224, 3))
model = keras.models.Sequential()
model.add(InputLayer(input_shape=(224, 224, 3)))
for layer in vgg_model.layers: model.add(layer)
model.add(Flatten(input_shape=model.output_shape[1:]))
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.75))
model.add(Dense(1, activation='sigmoid', name='Output_Classification'))

Then I loaded my initial weights and set it to my new "flat" vgg model, now it works !