EfficientNetの導入の際に次元のエラーが起きます

前提・実現したいこと

EfficientNetの導入を行っている際に、エラーが発生しました。

発生している問題・エラーメッセージ


  File "C:users...\Efficientnet\Efficientnet.py", line 147, in <module>
    X_train, Y_train, batch_size=8, epochs=2, validation_split=0.32

  File "C:\Users...\Efficientnet\Efficientnet.py", line 116, in train
    verbose=self.verbose

  File "C:\Users...\keras\engine\training.py", line 1154, in fit
    batch_size=batch_size)

  File "C:\Users...\keras\engine\training.py", line 621, in _standardize_user_data
    exception_prefix='target')

  File "C:\Users...\keras\engine\training_utils.py", line 145, in standardize_input_data
    str(data_shape))

ValueError: Error when checking target: expected probs to have shape (1000,) but got array with shape (1,)

該当のソースコード

Python
1#モデルとのフィッ
2class Trainer():
3
4    def __init__(self, model, loss, optimizer):
5        self._target = model
6        self._target.compile(
7            loss=loss, optimizer=optimizer, metrics=["mae"]
8            )
9        self.verbose = 1
10
11    def train(self, X_train, Y_train, batch_size, epochs, validation_split):
12
13        self._target.fit(
14            X_train, Y_train,
15            batch_size=batch_size, epochs=epochs,
16            validation_split=validation_split,
17#            callbacks = [TensorBoard(set_dir_name='CNN_LeNet_0.237W_369')],
18            
19            verbose=self.verbose
20        )
21
22#モデルの作成
23input_layer = Input(shape=(244, 244, 3))  # 最初の層
24
25
26
27
28efficient_net = EfficientNetB0(
29    weights='imagenet',  # imagenetでもよい 
30    include_top=False,  # 全結合層は自分で作成するので要らない
31    input_tensor = input_layer,  # 入力
32    pooling='max')
33
34for layer in efficient_net.layers:  # 転移学習はしない
35    layer.trainable = True
36
37
38model = EfficientNetB0((224, 224, 3))
39
40model.summary()
41
42
43#訓練の設定
44trainer = Trainer(model, loss="mean_squared_error", optimizer="adam")
45trainer.train(
46    X_train, Y_train, batch_size=8, epochs=2, validation_split=0.32
47    )
48
49
50＿＿＿以下、評価＿＿＿