TensorFlow sparse_softmax_cross_entropy秩误差

Question

我正试图在TensorFlow上用LSTM构建一个RNN。输入和输出都是5000×2矩阵，其中列表示特征。然后，这些矩阵被输入到batchX和batchY占位符，这些占位符支持反向传播。代码的主要定义在底部。我得到了以下错误：

等级错配:标签的等级(接收到2)应该等于逻辑的-1(接收到2)。

我检查了logits_series和labels_series，它们似乎都包含[batch_size, num_features]形状的张量的反向传播量。

我感到困惑的是:既然逻辑是标签的预测，它们不应该有相同的维度吗？

'''
RNN definitions

input_dimensions = [batch_size, truncated_backprop_length, num_features_input] 
output_dimensions = [batch_size, truncated_backprop_length, num_features_output]
state_dimensions = [batch_size, state_size]
'''
batchX_placeholder = tf.placeholder(tf.float32, (batch_size, truncated_backprop_length, num_features_input))
batchY_placeholder = tf.placeholder(tf.int32, (batch_size, truncated_backprop_length, num_features_output))
init_state = tf.placeholder(tf.float32, (batch_size, state_size))
inputs_series = tf.unstack(batchX_placeholder, axis=1)
labels_series = tf.unstack(batchY_placeholder, axis=1)

w = tf.Variable(np.random.rand(num_features_input+state_size,state_size), dtype = tf.float32)
b = tf.Variable(np.zeros((batch_size, state_size)), dtype = tf.float32)
w2 = tf.Variable(np.random.rand(state_size, num_features_output), dtype = tf.float32)
b2 = tf.Variable(np.zeros((batch_size, num_features_output)), dtype=tf.float32)

#calculate state and output variables

state_series = []
output_series = []
current_state = init_state
#iterate over each truncated_backprop_length
for current_input in inputs_series:
    current_input = tf.reshape(current_input,[batch_size, num_features_input])
    input_and_state_concatenated = tf.concat([current_input,current_state], 1)
    next_state = tf.tanh(tf.matmul(input_and_state_concatenated, w) + b)
    state_series.append(next_state)
    current_state = next_state
    output = tf.matmul(current_state, w2)+b2
    output_series.append(output)

#calculate expected output for each state    
logits_series = [tf.matmul(state, w2) + b2 for state in state_series] 
#print(logits_series)
predictions_series = [tf.nn.softmax(logits) for logits in logits_series]
'''
batchY_placeholder = np.zeros((batch_size,truncated_backprop_length))
for i in range(batch_size):
    for j in range(truncated_backprop_length):
        batchY_placeholder[i,j] = batchY1_placeholder[j, i, 0]+batchY1_placeholder[j, i, 1]
'''
print("logits_series", logits_series)
print("labels_series", labels_series)
#calculate losses given each actual and calculated output
losses = [tf.nn.sparse_softmax_cross_entropy_with_logits(logits = logits, labels = labels) for logits, labels in zip(logits_series,labels_series)]
total_loss = tf.reduce_mean(losses)

Answer 1

多亏了陈茂熙，我发现了这个问题。那是因为

tf.nn.sparse_softmax_cross_entropy_with_logits

要求标签比逻辑少一个维度。具体来说，标签参数接受形状[batch_size] and the dtype int32 or int64的值。

我通过枚举我拥有的一个热编码标签来解决这个问题，减少了维度。

然而，它也有可能使用

tf.nn.softmax_cross_entropy_with_logits

，它没有降维要求，因为它使用带有[batch_size, num_classes] and dtype float32 or float64.形状的标签值。