瞭解ResourceExhaustedError：分配形狀張量時的OOM

Question

我試圖使用張量流實現跳過思考模型，並且當前版本被放置here。

目前我用我的機器上的一個GPU（共2個GPU）和GPU的信息是

2017-09-06 11:29:32.657299: I tensorflow/core/common_runtime/gpu/gpu_device.cc:940] Found device 0 with properties: 
name: GeForce GTX 1080 Ti 
major: 6 minor: 1 memoryClockRate (GHz) 1.683 
pciBusID 0000:02:00.0 
Total memory: 10.91GiB 
Free memory: 10.75GiB 

然而，我當我試圖把數據反饋給模型OOM。我嘗試調試如下：

我用下面的代碼片段我運行sess.run(tf.global_variables_initializer())

logger.info('Total: {} params'.format(
     np.sum([ 
      np.prod(v.get_shape().as_list()) 
      for v in tf.trainable_variables() 
     ]))) 

，並得到2017-09-06 11:29:51,333 INFO main main.py:127 - Total: 62968629 params之後，如果全部採用tf.float32約莫240Mb。的tf.global_variables輸出是

[<tf.Variable 'embedding/embedding_matrix:0' shape=(155229, 200) dtype=float32_ref>, 
<tf.Variable 'encoder/rnn/gru_cell/gates/kernel:0' shape=(400, 400) dtype=float32_ref>, 
<tf.Variable 'encoder/rnn/gru_cell/gates/bias:0' shape=(400,) dtype=float32_ref>, 
<tf.Variable 'encoder/rnn/gru_cell/candidate/kernel:0' shape=(400, 200) dtype=float32_ref>, 
<tf.Variable 'encoder/rnn/gru_cell/candidate/bias:0' shape=(200,) dtype=float32_ref>, 
<tf.Variable 'decoder/weights:0' shape=(200, 155229) dtype=float32_ref>, 
<tf.Variable 'decoder/biases:0' shape=(155229,) dtype=float32_ref>, 
<tf.Variable 'decoder/previous_decoder/rnn/gru_cell/gates/kernel:0' shape=(400, 400) dtype=float32_ref>, 
<tf.Variable 'decoder/previous_decoder/rnn/gru_cell/gates/bias:0' shape=(400,) dtype=float32_ref>, 
<tf.Variable 'decoder/previous_decoder/rnn/gru_cell/candidate/kernel:0' shape=(400, 200) dtype=float32_ref>, 
<tf.Variable 'decoder/previous_decoder/rnn/gru_cell/candidate/bias:0' shape=(200,) dtype=float32_ref>, 
<tf.Variable 'decoder/next_decoder/rnn/gru_cell/gates/kernel:0' shape=(400, 400) dtype=float32_ref>, 
<tf.Variable 'decoder/next_decoder/rnn/gru_cell/gates/bias:0' shape=(400,) dtype=float32_ref>, 
<tf.Variable 'decoder/next_decoder/rnn/gru_cell/candidate/kernel:0' shape=(400, 200) dtype=float32_ref>, 
<tf.Variable 'decoder/next_decoder/rnn/gru_cell/candidate/bias:0' shape=(200,) dtype=float32_ref>, 
<tf.Variable 'global_step:0' shape=() dtype=int32_ref>] 

在我的訓練句話，我有一個數據數組，其形狀爲(164652, 3, 30)，即sample_size x 3 x time_step的3在這裏是指前面的句子，當前句子和下一個句子。該訓練數據的大小約爲57Mb，存儲在loader中。然後，我用寫一個生成函數來獲得句子，看起來像

def iter_batches(self, batch_size=128, time_major=True, shuffle=True): 

    num_samples = len(self._sentences) 
    if shuffle: 
     samples = self._sentences[np.random.permutation(num_samples)] 
    else: 
     samples = self._sentences 

    batch_start = 0 
    while batch_start < num_samples: 
     batch = samples[batch_start:batch_start + batch_size] 

     lens = (batch != self._vocab[self._vocab.pad_token]).sum(axis=2) 
     y, x, z = batch[:, 0, :], batch[:, 1, :], batch[:, 2, :] 
     if time_major: 
      yield (y.T, lens[:, 0]), (x.T, lens[:, 1]), (z.T, lens[:, 2]) 
     else: 
      yield (y, lens[:, 0]), (x, lens[:, 1]), (z, lens[:, 2]) 
     batch_start += batch_size 

的訓練循環看起來像

for epoch in num_epochs: 
    batches = loader.iter_batches(batch_size=args.batch_size) 
    try: 
     (y, y_lens), (x, x_lens), (z, z_lens) = next(batches) 
     _, summaries, loss_val = sess.run(
     [train_op, train_summary_op, st.loss], 
     feed_dict={ 
      st.inputs: x, 
      st.sequence_length: x_lens, 
      st.previous_targets: y, 
      st.previous_target_lengths: y_lens, 
      st.next_targets: z, 
      st.next_target_lengths: z_lens 
     }) 
    except StopIteraton: 
     ... 

然後我得到了一個OOM。如果我將整個try正文（不提供數據）註釋掉，腳本運行得很好。

我不知道爲什麼我在這麼小的數據範圍內得到了OOM。使用nvidia-smi我總是得到

Wed Sep 6 12:03:37 2017 
+-----------------------------------------------------------------------------+ 
| NVIDIA-SMI 384.59     Driver Version: 384.59     | 
|-------------------------------+----------------------+----------------------+ 
| GPU Name  Persistence-M| Bus-Id  Disp.A | Volatile Uncorr. ECC | 
| Fan Temp Perf Pwr:Usage/Cap|   Memory-Usage | GPU-Util Compute M. | 
|===============================+======================+======================| 
| 0 GeForce GTX 108... Off | 00000000:02:00.0 Off |     N/A | 
| 0% 44C P2 60W/275W | 10623MiB/11172MiB |  0%  Default | 
+-------------------------------+----------------------+----------------------+ 
| 1 GeForce GTX 108... Off | 00000000:03:00.0 Off |     N/A | 
| 0% 43C P2 62W/275W | 10621MiB/11171MiB |  0%  Default | 
+-------------------------------+----------------------+----------------------+ 

+-----------------------------------------------------------------------------+ 
| Processes:              GPU Memory | 
| GPU  PID Type Process name        Usage  | 
|=============================================================================| 
| 0  32748 C python3          10613MiB | 
| 1  32748 C python3          10611MiB | 
+-----------------------------------------------------------------------------+ 

我無法看到我的腳本的實際 GPU使用，因爲總是tensorflow搶斷開頭的所有記憶。這裏的實際問題是我不知道如何調試。

我讀過一些關於StackOverflow上的OOM的文章。其中大部分發生在向模型提供大型測試集數據並通過小批量提供數據時可以避免該問題。但我不明白爲什麼在我的11Gb 1080Ti中看到這樣的小數據和參數組合糟糕，因爲它只是試圖分配一個大小爲[3840 x 155229]的矩陣。 （解碼器的輸出矩陣，3840 = 30(time_steps) x 128(batch_size)，155229是vocab_size）。

2017-09-06 12:14:45.787566: W tensorflow/core/common_runtime/bfc_allocator.cc:277] ********************************************************************************************xxxxxxxx 
2017-09-06 12:14:45.787597: W tensorflow/core/framework/op_kernel.cc:1158] Resource exhausted: OOM when allocating tensor with shape[3840,155229] 
2017-09-06 12:14:45.788735: W tensorflow/core/framework/op_kernel.cc:1158] Resource exhausted: OOM when allocating tensor with shape[3840,155229] 
    [[Node: decoder/previous_decoder/Add = Add[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/gpu:0"](decoder/previous_decoder/MatMul, decoder/biases/read)]] 
2017-09-06 12:14:45.790453: I tensorflow/core/common_runtime/gpu/pool_allocator.cc:247] PoolAllocator: After 2857 get requests, put_count=2078 evicted_count=1000 eviction_rate=0.481232 and unsatisfied allocation rate=0.657683 
2017-09-06 12:14:45.790482: I tensorflow/core/common_runtime/gpu/pool_allocator.cc:259] Raising pool_size_limit_ from 100 to 110 
Traceback (most recent call last): 
    File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1139, in _do_call 
    return fn(*args) 
    File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1121, in _run_fn 
    status, run_metadata) 
    File "/usr/lib/python3.6/contextlib.py", line 88, in __exit__ 
    next(self.gen) 
    File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status 
    pywrap_tensorflow.TF_GetCode(status)) 
tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocating tensor with shape[3840,155229] 
    [[Node: decoder/previous_decoder/Add = Add[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/gpu:0"](decoder/previous_decoder/MatMul, decoder/biases/read)]] 
    [[Node: GradientDescent/update/_146 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_2166_GradientDescent/update", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]()]] 

During handling of the above exception, another exception occurred: 

任何幫助將不勝感激。提前致謝。

Answer 1

讓我們從一個分裂的問題之一：

關於tensorflow分配所有存儲器中，可以使用下面的代碼片段，讓tensorflow每當需要的時候分配內存。這樣你就可以理解事情的進展。

gpu_options = tf.GPUOptions(allow_growth=True) 
session = tf.InteractiveSession(config=tf.ConfigProto(gpu_options=gpu_options)) 

關於大小第二件事， 由於沒有關於網絡大小的信息，我們不能估計什麼錯誤。但是，您可以選擇一步一步地調試所有網絡。例如，僅創建一個網絡圖層，獲取其輸出，創建會話和饋送值一次，並可視化您消耗的內存量。迭代此調試會話，直到看到內存不足的地方。

請注意，3840 x 155229輸出是真的，真的是一個大輸出。它意味着〜600M神經元，並且每一層只有〜2.22GB。如果您有任何相似的尺寸圖層，它們將會加起來以非常快的速度填充您的GPU內存。

此外，這是僅適用於前進方向，如果要使用該層進行訓練，通過優化加入反向傳播和層將這種尺寸由2。所以相乘，對於訓練你消耗〜5 GB只是爲輸出層。

我建議你修改你的網絡，並儘量減少批量大小/參數計數爲你解答適合模型到GPU