ValueError：将符号张量馈送到模型时，我们期望张量具有静态批处理大小

Question

我是新手，当我遇到此错误时Keras，我正尝试使用构建text-classification CNN模型Python 3.6：Traceback (most recent call last):  File "model.py", line 94, in <module>    model.fit([x1, x2], y_label, batch_size=batch_size, epochs=epochs, verbose=1, callbacks=[checkpoint], validation_split=0.2)  # starts training  File "/../../anaconda3/lib/python3.6/site-packages/keras/engine/training.py", line 955, in fit    batch_size=batch_size)  File "/../../anaconda3/lib/python3.6/site-packages/keras/engine/training.py", line 754, in _standardize_user_data    exception_prefix='input')  File "/../../anaconda3/lib/python3.6/site-packages/keras/engine/training_utils.py", line 90, in standardize_input_data    data = [standardize_single_array(x) for x in data]  File "/../../anaconda3/lib/python3.6/site-packages/keras/engine/training_utils.py", line 90, in <listcomp>    data = [standardize_single_array(x) for x in data]  File "/../../anaconda3/lib/python3.6/site-packages/keras/engine/training_utils.py", line 23, in standardize_single_array    'Got tensor with shape: %s' % str(shape))ValueError: When feeding symbolic tensors to a model, we expect thetensors to have a static batch size. Got tensor with shape: (None, 50, 100)我的模型代码在这里：print("\nCreating Model...")x1 = Input(shape=(seq_len1, 100), name='x1')x2 = Input(shape=(seq_len2, 100), name='x2')x1_r = Reshape((seq_len1, embedding_dim, 1))(x1)x2_r = Reshape((seq_len2, embedding_dim, 1))(x2)conv_0 = Conv2D(num_filters, kernel_size=(filter_sizes[0], 1), padding='valid', kernel_initializer='normal', activation='relu').# Conv layers with different filter sizes.    maxpool = MaxPool2D(pool_size=(2, 1), strides=(1,1), padding='valid')output1 = conv_0(x1_r)output1 = maxpool(output1)output1 = conv_1(output1)output1 = maxpool(output1)output1 = conv_2(output1)output1 = maxpool(output1).# Same for output2.我model.fit在行中遇到此错误。这里seq_len1 = 50和seq_len2 =120。请帮助我解决此问题。