首页 文章

ValueError:检查目标时出错:期望的dense_2有4个维度,但得到的数组有形状(64,50)(Keras)

提问于
浏览
0

使用Keras训练预训练模型的方式如下:

baseModel = keras.applications.resnet50.ResNet50(include_top=False, weights='imagenet')
t = baseModel.output
t = MaxPooling2D()(t)
t = Dense(1000, activation='relu', kernel_regularizer=regularizers.l2(0.01))(t)
predictions = Dense(NUMCLASSES, activation='softmax')(t)
model = Model(inputs=baseModel.input, outputs=predictions)

for layer in baseModel.layers:
    layer.trainable = False

model.compile(loss=losses.categorical_crossentropy, optimizer=keras.optimizers.Adam())

# loading the data
files = np.array(list(train_gt.keys()))
np.random.shuffle(files)
pics = [resize(io.imread(join(trainImgDir, f)), INPUTSHAPE, mode='reflect') for f in files]
pics = np.array(pics)
classes = np.array([train_gt[f] for f in files])
classes = to_categorical(classes, NUMCLASSES)

train = pics[: int(pics.shape[0] * ((SPLITDATA - 1) / SPLITDATA))]
classesTr = classes[: int(classes.shape[0] * ((SPLITDATA - 1) / SPLITDATA))]

# training
fIn = open("Error", 'w')

batchSize = 64
for ep in range(1000):
    # train data
    trLosses = np.array([], dtype='Float64')
    for s in range(train.shape[0] // batchSize + (train.shape[0] % batchSize != 0)):
        batch = train[s * batchSize : (s + 1) * batchSize]
        batchClasses = classesTr[s * batchSize : (s + 1) * batchSize]
        trLosses = np.append(trLosses, model.train_on_batch(batch, batchClasses))

我有一个错误:

File "/home/mark/miniconda3/lib/python3.6/site-packages/keras/engine/training.py", line 1636, in train_on_batch
check_batch_axis=True)
File "/home/mark/miniconda3/lib/python3.6/site-packages/keras/engine/training.py", line 1315, in _standardize_user_data
    exception_prefix='target')
  File "/home/mark/miniconda3/lib/python3.6/site-packages/keras/engine/training.py", line 127, in _standardize_input_data
    str(array.shape))
ValueError: Error when checking target: expected dense_2 to have 4 dimensions, but got array with shape (64, 50)

我尝试了其他损失,但这没有帮助 . batchClasses有shape(batchSize,NUMCLASSES)=(64,50),我希望在Dense的输出中有这个形状 .

1 回答

  • 0

    MaxPooling2D() 不会删除宽度和高度尺寸,因此 t = MaxPooling2D()(t) 的输出将是形状 (batch_size, w, h, 2048) 的张量 . 这就是为什么以下 Dense 层为您提供4D张量的原因 .

    此外,由于您未使用默认参数 pool_size=(2, 2)MaxPooling2D() 提供任何参数,因此 wh 可能都大于1 .

    所以你基本上有两个选择,取决于你认为哪个更适合你的问题:

    • MaxPooling2D() 之后添加 Flatten() :我不确定这是否是你想要的,因为如果 wh 很大,展平它将导致一个非常大的向量 .

    • 删除 t = MaxPooling2D()(t) 并使用以下任一方法:

    • ResNet50(..., pooling='max') (推荐),或

    • t = GlobalMaxPooling2D()(t)

相关问题