ValueError：无法为张量 u'InputData/X:0' 提供形状 (2, 4) 的值

Question

我收到一个错误，ValueError：无法为 Tensor u'InputData/X:0' 提供形状 (2, 4) 的值，其形状为 '(?, 2, 4, 104)'。我写了代码，# coding: utf-8import tensorflow as tfimport tflearnfrom tflearn.layers.core import input_data,dropout,fully_connectedfrom tflearn.layers.conv import conv_2d, max_pool_2dfrom tflearn.layers.normalization import local_response_normalizationfrom tflearn.layers.estimator import regressionimport pandas as pdimport numpy as npfrom sklearn import metricstf.reset_default_graph()net = input_data(shape=[2, 4, 104])net = conv_2d(net, 4, 16, activation='relu')net = max_pool_2d(net, 1)net = tflearn.activations.relu(net)net = dropout(net, 0.5)net = tflearn.fully_connected(net, 10, activation='softmax')net = tflearn.regression(net, optimizer='adam', learning_rate=0.5, loss='categorical_crossentropy')model = tflearn.DNN(net)trainDataSet = [[0.25,0.25,1,1],[0,0,1,1],[0.25,0.25,1,1]]trainLabel = [[0,1],[0,1],[1,0]]model.fit(trainDataSet, trainLabel, n_epoch=100, batch_size=32, validation_set=0.1, show_metric=True)追溯说Traceback (most recent call last):  File "cnn.py", line 16, in <module>    model.fit(trainDataSet, trainLabel, n_epoch=100, batch_size=32, validation_set=0.1, show_metric=True)  File "/Users/xxx/anaconda/xxx/lib/python2.7/site-packages/tflearn/models/dnn.py", line 216, in fit    callbacks=callbacks)  File "/Users/xxx/anaconda/xxx/lib/python2.7/site-packages/tflearn/helpers/trainer.py", line 339, in fit    show_metric)  File "/Users/xxx/anaconda/xxx/lib/python2.7/site-packages/tflearn/helpers/trainer.py", line 818, in _train    feed_batch)  File "/Users/xxx/anaconda/xxx/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 929, in run    run_metadata_ptr)  File "/Users/xxx/anaconda/xxx/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1128, in _run    str(subfeed_t.get_shape())))ValueError: Cannot feed value of shape (2, 4) for Tensor u'InputData/X:0', which has shape '(?, 2, 4, 104)'但发生了同样的错误。我的代码有什么问题？我应该如何解决这个问题？