TensorFlow：不兼容的形狀：[100155]對[128155]組合CNN和LSTM當

Question

問題

我發現了試圖以層疊轉化率時不兼容的形狀誤差 - > LSTM - >用於完全連接層音頻迴歸任務。我無法弄清楚爲什麼我得到了我得到的錯誤 - 圖形沒有問題然後拋出錯誤 - 任何人都可以幫忙嗎？

代碼

lstm_num_hidden = 128 
lstm_number_layers = 3 
x = tf.placeholder(tf.float32, [None, 1024]) 
y = tf.placeholder(tf.float32, [None, 155]) 
keep_probability = tf.placeholder(tf.float32) 

def conv2d(x, weights): 
    return tf.nn.conv2d(x, weights, strides=[1, 1, 1, 1], padding='SAME') 

x_spectrogram = tf.reshape(x, [-1, 32, 32, 1]) 

conv1_weights = tf.Variable(tf.truncated_normal([5, 5, 1, 32], stddev=0.1)) 
conv1_bias = tf.Variable(tf.constant(0.1, shape=[32])) 
conv1_hidden = tf.nn.relu(conv2d(x_spectrogram, conv1_weights) + conv1_bias) 
conv1_pooling = tf.nn.max_pool(conv1_hidden, ksize=[1, 2, 2, 1],strides=[1, 2, 2, 1], padding='SAME') 

conv2_weights = tf.Variable(tf.truncated_normal([5, 5, 32, 64], stddev=0.1)) 
conv2_bias = tf.Variable(tf.constant(0.1, shape=[64])) 
conv2_hidden = tf.nn.relu(conv2d(conv1_pooling, conv2_weights) + conv2_bias) 
conv2_pooling = tf.nn.max_pool(conv2_hidden, ksize=[1, 2, 2, 1],strides=[1, 2, 2, 1], padding='SAME') 
conv2_output = tf.reshape(conv2_pooling, [-1, 64, 64]) 

# changes to [8, BatchSize, 8, 64] 
tr_x = tf.transpose(conv2_output, [1, 0, 2]) 
re_x = tf.reshape(tr_x, [-1, 64]) 
sp_x = tf.split(0, 64, re_x) 

lstm_cell = rnn_cell.LSTMCell(lstm_num_hidden, forget_bias=1.0, state_is_tuple=True) 
lstm_cell = rnn_cell.MultiRNNCell([lstm_cell] * lstm_number_layers, state_is_tuple=True) 
init_state = lstm_cell.zero_state(128, tf.float32) 
lstm_output, _ = rnn.rnn(cell=lstm_cell, inputs=sp_x, dtype=tf.float32, initial_state=init_state) 
lstm_weights = tf.Variable(tf.truncated_normal([lstm_num_hidden, 155], stddev=0.1)) 
lstm_bias = tf.Variable(tf.truncated_normal([155], stddev=0.1)) 
out = tf.add(tf.matmul(lstm_output[-1], lstm_weights), lstm_bias) 

fully_connected1_weights = tf.Variable(tf.truncated_normal([155, 1024], stddev=0.1)) 
fully_connected1_biases = tf.Variable(tf.truncated_normal([1024], stddev=0.1)) 
fully_connected1 = tf.nn.relu(tf.matmul(out, fully_connected1_weights) + fully_connected1_biases) 
fully_connected1_dropout = tf.nn.dropout(fully_connected1, keep_probability) 

fully_connected2_weights = tf.Variable(tf.truncated_normal([1024, 155], stddev=0.1)) 
fully_connected2_biases = tf.Variable(tf.truncated_normal([155], stddev=0.1)) 
prediction = tf.matmul(fully_connected1_dropout, fully_connected2_weights) + fully_connected2_biases 

def error(labels, prediction): 
    return tf.sqrt(tf.reduce_mean(tf.square(tf.sub(labels, prediction)))) 

rmse = error(y, prediction) 
optimise = tf.train.AdamOptimizer(1e-4).minimize(rmse) 

# Get training and testing batch. 
train_batch_x = np.load("train_x.npy") 
train_batch_y = np.load("train_y.npy") 
test_batch_x = np.load("test_x.npy") 
test_batch_y = np.load("test_y.npy") 

sess = tf.Session() 
sess.run(tf.global_variables_initializer()) 

for i in range(100): 

    for batch in trange(99, desc="Training"): 
     start = batch * 100 
     end = batch * 100 + 100 
     sess.run(optimise, { x: train_batch_x[start:end], 
          y: train_batch_y[start:end], 
          keep_probability: 0.5 }) 

    rmse_error = sess.run(rmse, { x: test_batch_x, 
            y: test_batch_y, 
            keep_probability: 1.0 }) 
    print "Root Mean Squared Error:" + str(rmse_error) 

錯誤

W tensorflow/core/framework/op_kernel.cc:975] Invalid argument: Incompatible shapes: [100,155] vs. [128,155] 
    [[Node: gradients/Sub_grad/BroadcastGradientArgs = BroadcastGradientArgs[T=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](gradients/Sub_grad/Shape, gradients/Sub_grad/Shape_1)]] 
W tensorflow/core/framework/op_kernel.cc:975] Invalid argument: Incompatible shapes: [100,155] vs. [128,155] 
    [[Node: gradients/Sub_grad/BroadcastGradientArgs = BroadcastGradientArgs[T=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](gradients/Sub_grad/Shape, gradients/Sub_grad/Shape_1)]] 

Traceback (most recent call last): 
    File "conv_rnn_experiment.py", line 81, in <module> 
    keep_probability: 0.5 }) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 766, in run 
    run_metadata_ptr) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 964, in _run 
    feed_dict_string, options, run_metadata) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1014, in _do_run 
    target_list, options, run_metadata) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1034, in _do_call 
    raise type(e)(node_def, op, message) 
tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [100,155] vs. [128,155] 
    [[Node: gradients/Sub_grad/BroadcastGradientArgs = BroadcastGradientArgs[T=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](gradients/Sub_grad/Shape, gradients/Sub_grad/Shape_1)]] 

Caused by op u'gradients/Sub_grad/BroadcastGradientArgs', defined at: 
    File "conv_rnn_experiment.py", line 63, in <module> 
    optimise = tf.train.AdamOptimizer(1e-4).minimize(rmse) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/optimizer.py", line 269, in minimize 
    grad_loss=grad_loss) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/optimizer.py", line 335, in compute_gradients 
    colocate_gradients_with_ops=colocate_gradients_with_ops) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gradients_impl.py", line 482, in gradients 
    in_grads = grad_fn(op, *out_grads) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/math_grad.py", line 594, in _SubGrad 
    rx, ry = gen_array_ops._broadcast_gradient_args(sx, sy) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 390, in _broadcast_gradient_args 
    name=name) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 759, in apply_op 
    op_def=op_def) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2240, in create_op 
    original_op=self._default_original_op, op_def=op_def) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1128, in __init__ 
    self._traceback = _extract_stack() 

    ...which was originally created as op u'Sub', defined at: 
    File "conv_rnn_experiment.py", line 62, in <module> 
    rmse = error(y, prediction) 
    File "conv_rnn_experiment.py", line 60, in error 
    return tf.sqrt(tf.reduce_mean(tf.square(tf.sub(labels, prediction)))) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_math_ops.py", line 2758, in sub 
    result = _op_def_lib.apply_op("Sub", x=x, y=y, name=name) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 759, in apply_op 
    op_def=op_def) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2240, in create_op 
    original_op=self._default_original_op, op_def=op_def) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1128, in __init__ 
    self._traceback = _extract_stack() 

    InvalidArgumentError (see above for traceback): Incompatible shapes: [100,155] vs. [128,155] 
    [[Node: gradients/Sub_grad/BroadcastGradientArgs = BroadcastGradientArgs[T=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](gradients/Sub_grad/Shape, gradients/Sub_grad/Shape_1)]] 

Answer 1

如果打印夫婦的事情，當你做之前你sess.run()你會發現，它打破在lstm_output。去關，你就可以開始縮小你的問題，這結束了該行：

init_state = lstm_cell.zero_state(128, tf.float32)

這個初始化是確定批量大小。由於您有155個單位，並聲明批量爲128，因此預計輸入爲128 x 155。但是，它看起來像你的批次是100，所以如果你改變這一行它應該工作。