X = base_model.output X = Flatten()(X) X = Dense(2048, activation='relu')(X) X = Dropout(0.2)(X) X

Question

X = base_model.output X = Flatten()(X) X = Dense(2048, activation='relu')(X) X = Dropout(0.2)(X) X

= Dense(1024, activation='relu')(X)
X = Dropout(0.2)(X)
X = Dense(512, activation='relu')(X)
X = Dropout(0.2)(X)
X = Dense(256, activation='relu')(X)
X = Dropout(0.2)(X)
X = Dense(128, activation='relu')(X)
X = Dropout(0.2)(X)
X = Dense(64, activation='relu')(X)
predictions = Dense(outputs_number, activation="relu")(X)

может так быть? или у слоев нужно другую активацию поставить?