import tensorflow as tffrom random import*from numpy import arrayinput_randoms = []for i in range(10000): input_randoms.append([randint(0,100),randint(0,100)])output_randoms = []for pair in input_randoms: output_randoms.append(sum(pair))model = tf.keras.models.Sequential([ tf.keras.layers.Flatten(input_shape=(2,)), tf.keras.layers.Dense(128, activation='relu'), tf.keras.layers.Dropout(0.2), tf.keras.layers.Dense(202, activation='softmax')])model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])model.fit(array(input_randoms), output_randoms, epochs=5)model.evaluate([[50,32],[16,18]], [82,34], verbose=2)输出为：
WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/resource_variable_ops.py:1630: calling BaseResourceVariable.__init__ (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version.Instructions for updating:If using Keras pass *_constraint arguments to layers.Train on 10000 samplesEpoch 1/510000/10000 [==============================] - 1s 107us/sample - loss: 7.1288 - acc: 0.0090Epoch 2/510000/10000 [==============================] - 1s 69us/sample - loss: 4.9724 - acc: 0.0120Epoch 3/510000/10000 [==============================] - 1s 67us/sample - loss: 4.8243 - acc: 0.0132Epoch 4/510000/10000 [==============================] - 1s 68us/sample - loss: 4.7343 - acc: 0.0113Epoch 5/510000/10000 [==============================] - 1s 69us/sample - loss: 4.6702 - acc: 0.0139---------------------------------------------------------------------------ValueError Traceback (most recent call last)<ipython-input-1-4b4fc1f78d7e> in <module>() 26 model.fit(array(input_randoms), output_randoms, epochs=5) 27 ---> 28 model.evaluate([[50,32],[16,18]], [82,34], verbose=2) 29 3 frames/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/training_utils.py in standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix) 570 ': expected ' + names[i] + ' to have shape ' + 571 str(shape) + ' but got array with shape ' +--> 572 str(data_shape)) 573 return data 574 ValueError: Error when checking input: expected flatten_input to have shape (2,) but got array with shape (1,)我正在尝试完成这个AI。
据我所知，model.evaluate([[50,32],[16,18]], [82,34], verbose=2) 我应该输入两个样本输入及其正确的答案。我期望的输出如上所示，在错误之前的输出部分。
回答：
我认为你少了一对括号，一旦我加上括号，输入应该就是正确的了。我也是初学者，不太懂…
model.evaluate([[50,32],[16,18]], [82,34], verbose=2)改为
model.evaluate([[[50,32],[16,18]]], [82,34], verbose=2)
