我正在构建一个字符级卷积神经网络。我有一组样本作为训练数据，每个样本的维度为3640。我认为我对如何在tensorflow中调整/重塑维度几乎一无所知，因为我不断遇到无法解决的错误：

Traceback (most recent call last):  File "/Users/osopova/Documents/00_KSU_Masters/00_2016_Fall/00_Research/cnn_da/step_4_cnn_4.py", line 87, in my_conv_model    prediction, loss = learn.models.logistic_regression(pool, y)  File "/Users/osopova/Applications/anaconda/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/models.py", line 146, in logistic_regression    'weights', [x.get_shape()[1], y.get_shape()[-1]], dtype=dtype)  File "/Users/osopova/Applications/anaconda/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 873, in get_variable    custom_getter=custom_getter)  File "/Users/osopova/Applications/anaconda/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 700, in get_variable    custom_getter=custom_getter)  File "/Users/osopova/Applications/anaconda/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 217, in get_variable    validate_shape=validate_shape)  File "/Users/osopova/Applications/anaconda/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 202, in _true_getter    caching_device=caching_device, validate_shape=validate_shape)  File "/Users/osopova/Applications/anaconda/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 515, in _get_single_variable    "but instead was %s." % (name, shape))ValueError: Shape of a new variable (logistic_regression/weights) must be fully defined, but instead was (?, 1).Traceback (most recent call last):  File "/Users/osopova/Documents/00_KSU_Masters/00_2016_Fall/00_Research/cnn_da/step_4_cnn_4.py", line 175, in <module>Traceback (most recent call last):  File "/Users/osopova/Documents/00_KSU_Masters/00_2016_Fall/00_Research/cnn_da/step_4_cnn_4.py", line 87, in my_conv_model    prediction, loss = learn.models.logistic_regression(pool, y)  File "/Users/osopova/Applications/anaconda/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/models.py", line 146, in logistic_regression    'weights', [x.get_shape()[1], y.get_shape()[-1]], dtype=dtype)  File "/Users/osopova/Applications/anaconda/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 873, in get_variable    custom_getter=custom_getter)  File "/Users/osopova/Applications/anaconda/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 700, in get_variable    custom_getter=custom_getter)  File "/Users/osopova/Applications/anaconda/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 217, in get_variable    validate_shape=validate_shape)  File "/Users/osopova/Applications/anaconda/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 202, in _true_getter    caching_device=caching_device, validate_shape=validate_shape)  File "/Users/osopova/Applications/anaconda/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 515, in _get_single_variable    "but instead was %s." % (name, shape))ValueError: Shape of a new variable (logistic_regression/weights) must be fully defined, but instead was (?, 1).

以下是代码：

卷积模型开始：

def my_conv_model(x, y):# 形成形状为batch_size x 1 x N_FEATURES x 1的4d张量x = tf.reshape(x, [-1, 1, N_FEATURES, 1])# 这将提供1 x WINDOW_SIZE的滑动窗口卷积features = tf.contrib.layers.convolution2d(inputs=x,                                           num_outputs=N_FILTERS,                                           kernel_size=[1, WINDOW_SIZE],                                           padding='VALID')# 添加RELU以实现非线性features = tf.nn.relu(features)# 对卷积+Relu的输出进行最大池化pool = tf.nn.max_pool(features, ksize=[1, 1, 2, 1],                         strides=[1, 1, 2, 1], padding='SAME')print("(1) pool_shape", pool.get_shape()) print("(1) y_shape", y.get_shape()) pool_shape = tf.shape(pool)pool = tf.reshape(pool, [pool_shape[0], pool_shape[2]*pool_shape[3]])y = tf.expand_dims(y, 1)print("(2) pool_shape", pool.get_shape()) print("(2) y_shape", y.get_shape()) try:    exc_info = sys.exc_info()    print("(3) pool_shape", pool.get_shape())    print("(3) y_shape", y.get_shape())

这里出现错误：

    prediction, loss = learn.models.logistic_regression(pool, y)    return prediction, lossexcept Exception:    #print(traceback.format_exc())    passfinally:    # 显示原始异常    traceback.print_exception(*exc_info)    del exc_info#return prediction, loss

形状如下：

(1) pool_shape (?, 1, 1819, 10)(1) y_shape (?,)(2) pool_shape (?, ?)(2) y_shape (?, 1)(3) pool_shape (?, ?)(3) y_shape (?, 1)

主函数如下：

def main(unused_argv):    # 训练和测试数据编码为one-hot    data_folder = './data'    sandyData = np.loadtxt(data_folder+'/sandyData.csv', delimiter=',')    sandyLabels = np.loadtxt(data_folder+'/sandyLabels.csv', delimiter=',')    x_train, x_test, y_train, y_test = \        train_test_split(sandyData, sandyLabels, test_size=0.2, random_state=7)    x_train = np.array(x_train, dtype=np.float32)    x_test = np.array(x_test, dtype=np.float32)    y_train = np.array(y_train, dtype=np.float32)    y_test = np.array(y_test, dtype=np.float32)    # 构建模型    classifier = learn.Estimator(model_fn=my_conv_model)    # 训练和预测    classifier.fit(x_train, y_train, steps=100)    y_predicted = [p['class'] for p in classifier.predict(x_test, as_iterable=True)]    score = metrics.accuracy_score(y_test, y_predicted)    print('Accuracy: {0:f}'.format(score))if __name__ == '__main__':    tf.app.run() `

回答：

看起来问题出在传递给logistic_regression()的pool参数没有已知的列数。linear_regression()需要知道其x参数的列数，以便创建大小合适的权重矩阵。

这个问题源自以下行：

pool_shape = tf.shape(pool)pool = tf.reshape(pool, [pool_shape[0], pool_shape[2]*pool_shape[3]])

尽管pool_shape[2]*pool_shape[3]具有常量值，但TensorFlow的客户端常量折叠当前不处理此表达式，因此它推断出pool张量的静态形状为(?, ?)（如您的日志输出所示）。一个解决方法是进行以下更改：

pool_shape = pool.get_shape()pool = tf.reshape(pool, [-1, (pool_shape[2] * pool_shape[3]).value])

使用pool.get_shape()而不是tf.shape(pool)可以为TensorFlow提供更多关于pool的（部分定义的）形状的信息，作为tf.TensorShape对象而不是tf.Tensor对象。在此更改之后，pool_shape[2]和pool_shape[3]都具有已知值，因此pool的列数将是已知的。