InvalidArgumentError (see above for traceback): logits and labels must
be same size: logits_size=[10,9] labels_size=[7040,9] [[Node:
SoftmaxCrossEntropyWithLogits =
SoftmaxCrossEntropyWithLogits[T=DT_FLOAT,
_device="/job:localhost/replica:0/task:0/gpu:0"](Reshape, Reshape_1)]]
我的输入大小为
batch_size
*
n_steps
*
n_input
批次大小
n_步数
*
n_classes
=>通过双向RNN,它将通过10*700*9
我应该如何更改此代码以修复错误?
batch\u size是指如下数据的数量:
数据1:ABCABCAADD。。。
...
数据10:ABCCCCABDBBAA。。。
n_步长表示每个数据的长度(数据用“O”填充以固定每个数据的长度):704
和
学习的输出应该是这样的:
...
数据输出10:ZXYYRZYZZ。。。
输出的每个字母表都受到输入字母表的环境和顺序的影响。
learning_rate = 0.001
training_iters = 100000
batch_size = 10
display_step = 10
# Network Parameters
n_input = 100
n_steps = 704 # timesteps
n_hidden = 50 # hidden layer num of features
n_classes = 9
x = tf.placeholder("float", [None, n_steps, n_input])
y = tf.placeholder("float", [None, n_steps, n_classes])
weights = {
'out': tf.Variable(tf.random_normal([2*n_hidden, n_classes]))
}
biases = {
'out': tf.Variable(tf.random_normal([n_classes]))
}
def BiRNN(x, weights, biases):
x = tf.unstack(tf.transpose(x, perm=[1, 0, 2]))
# Forward direction cell
lstm_fw_cell = rnn.BasicLSTMCell(n_hidden, forget_bias=1.0)
# Backward direction cell
lstm_bw_cell = rnn.BasicLSTMCell(n_hidden, forget_bias=1.0)
# Get lstm cell output
try:
outputs, _, _ = rnn.static_bidirectional_rnn(lstm_fw_cell, lstm_bw_cell, x,
dtype=tf.float32)
except Exception: # Old TensorFlow version only returns outputs not states
outputs = rnn.static_bidirectional_rnn(lstm_fw_cell, lstm_bw_cell, x,
dtype=tf.float32)
# Linear activation, using rnn inner loop last output
return tf.matmul(outputs[-1], weights['out']) + biases['out']
pred = BiRNN(x, weights, biases)
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# Evaluate model
correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# Initializing the variables
init = tf.global_variables_initializer()
# Launch the graph
with tf.Session() as sess:
sess.run(init)
step = 1
while step * batch_size < training_iters:
batch_x, batch_y = next_batch(batch_size, r_big_d, y_r_big_d)
#batch_x = batch_x.reshape((batch_size, n_steps, n_input))
# Run optimization op (backprop)
sess.run(optimizer, feed_dict={x: batch_x, y: batch_y})
if step % display_step == 0:
# Calculate batch accuracy
acc = sess.run(accuracy, feed_dict={x: batch_x, y: batch_y})
# Calculate batch loss
loss = sess.run(cost, feed_dict={x: batch_x, y: batch_y})
print("Iter " + str(step*batch_size) + ", Minibatch Loss= " + \
"{:.6f}".format(loss) + ", Training Accuracy= " + \
"{:.5f}".format(acc))
step += 1
print("Optimization Finished!")
test_x, test_y = next_batch(batch_size, v_big_d, y_v_big_d)
print("Testing Accuracy:", \
sess.run(accuracy, feed_dict={x: test_x, y: test_y}))
