我是 tensorflow keras 和數據集的新手。誰能幫我理解為什么下面的代碼不起作用？import tensorflow as tfimport tensorflow.keras as kerasimport numpy as npfrom tensorflow.python.data.ops import dataset_opsfrom tensorflow.python.data.ops import iterator_opsfrom tensorflow.python.keras.utils import multi_gpu_modelfrom tensorflow.python.keras import backend as Kdata = np.random.random((1000,32))labels = np.random.random((1000,10))dataset = tf.data.Dataset.from_tensor_slices((data,labels))print( dataset)print( dataset.output_types)print( dataset.output_shapes)dataset.batch(10)dataset.repeat(100)inputs = keras.Input(shape=(32,)) # Returns a placeholder tensor# A layer instance is callable on a tensor, and returns a tensor.x = keras.layers.Dense(64, activation='relu')(inputs)x = keras.layers.Dense(64, activation='relu')(x)predictions = keras.layers.Dense(10, activation='softmax')(x)# Instantiate the model given inputs and outputs.model = keras.Model(inputs=inputs, outputs=predictions)# The compile step specifies the training configuration.model.compile(optimizer=tf.train.RMSPropOptimizer(0.001), loss='categorical_crossentropy', metrics=['accuracy'])# Trains for 5 epochsmodel.fit(dataset, epochs=5, steps_per_epoch=100)
2 回答
幕布斯7119047
TA貢獻1794條經驗 獲得超8個贊
關于您為什么收到錯誤的原始問題：
Error when checking input: expected input_1 to have 2 dimensions, but got array with shape (32,)
您的代碼中斷的原因是因為您沒有將.batch()back應用于dataset變量，如下所示：
dataset = dataset.batch(10)
您只需調用dataset.batch().
這會中斷，因為沒有batch()輸出張量不會批量處理，即您得到的是 shape(32,)而不是(1,32).
添加回答
舉報
0/150
提交
取消