Tensorflow图是否可以在会话外运行

Question

Could someone please explain the following situation:

I've created a simple convolutional neural network using Tensorflow. I'm using a class and I've created my graph in the constructor. I then train the network using a train method I've written. I'm also using queues and the feed-in mechanism. This is an excerpt from the code:

 class Super_res:
'Create a CNN model which augments the resolution of an image'
# object initialization (python) - constructor
def __init__(self, input, output, batch_size, record_size, weights, biases):    # input (neurons), output (no. neurons), batch_size (batches to process before registering delta), record_size ()
    print("Initializing object")
    self.input = input
    self.output = output
    self.batch_size = batch_size
    self.record_size = record_size
    self.weights = weights
    self.biases = biases

    # initialize data batch readers. Parameters: [Path], record_size, batch_size
    self.data_batch = data_reader3.batch_generator([DATA_PATH_OPTICAL_TRAIN],self.record_size, self.batch_size) # train set
    self.data_batch_eval = data_reader3.batch_generator([DATA_PATH_EVAL],self.record_size, self.batch_size) # eval set

    # this returns a [batch_size, 2, n_input] tensor. The second dimension is comprised of the low-res image and the GT high-res image. Each of these images is comprised of n_input entries (flat vector)
    self.data1 = tf.placeholder_with_default(tf.transpose(self.data_batch, [1, 0, 2]), [2, batch_size, n_input]) # one for optical and another for GT image [batch_size, n_input] each

    self.keep_prob = tf.placeholder(tf.float32) #dropout (keep probability) - this placeholder can accept a Tensor of arbitrary shape

    # create network model
    self.pred = self.cnn_model(self.data1[0], self.weights,     self.biases)    # self.data1[0] is the low-res data 

 def train(self):
    #self.low_res = self.data1[0]
    #self.high_res = self.data1[1]

    # define loss and optimizer
    #self.cost = tf.reduce_mean(tf.pow(self.data1[1] - self.pred, 2))
    #self.optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(self.cost)

    # Initializing the variables
    init = tf.global_variables_initializer()

    # Initialize session
    with tf.Session() as sess:
        sess.run(init)
        coord = tf.train.Coordinator()
        threads = tf.train.start_queue_runners(coord=coord)
        step = 1
        print("Entering training")

        # Keep  training until reach max iterations
        while step * batch_size < training_iters:
            #_, c = sess.run([self.optimizer, self.cost])
            conv_result = sess.run(self.pred)
            print(conv_result)
            #data2 = self.data1[0]
            #print(data2)

            if step % display_step == 0:
                print("Step:", '%04d' % (step+1))
            #   "cost=", c)
            step = step + 1

        coord.request_stop()
        coord.join(threads)

When I run this code, I get the following error output:

 Entering training
 Traceback (most recent call last):
 File "C:\Users\divin\Miniconda3\envs\tensorflow_gpu\lib\site-packages  \tensorflow\python\client\session.py", line 1139, in _do_call
return fn(*args)
File "C:\Users\divin\Miniconda3\envs\tensorflow_gpu\lib\site-packages \tensorflow\python\client\session.py", line 1121, in _run_fn
status, run_metadata)
File "C:\Users\divin\Miniconda3\envs\tensorflow_gpu\lib\contextlib.py", line 66, in __exit__
next(self.gen)
File "C:\Users\divin\Miniconda3\envs\tensorflow_gpu\lib\site-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.OutOfRangeError:    RandomShuffleQueue '_2_shuffle_batch/random_shuffle_queue' is closed and has   insufficient elements (requested 512, current size 0)
     [[Node: shuffle_batch = QueueDequeueManyV2[component_types=  [DT_FLOAT], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"]  (shuffle_batch/random_shuffle_queue, shuffle_batch/n)]]
     [[Node: shuffle_batch/_25 = _Recv[client_terminated=false,   recv_device="/job:localhost/replica:0/task:0/gpu:0",   send_device="/job:localhost/replica:0/task:0/cpu:0",   send_device_incarnation=1, tensor_name="edge_5_shuffle_batch",    tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/gpu:0"]()]]

 During handling of the above exception, another exception occurred:

 Traceback (most recent call last):
 File "super_res_class.py", line 137, in <module>
 p.train()
 File "super_res_class.py", line 106, in train
 conv_result = sess.run(self.pred)
 File "C:\Users\divin\Miniconda3\envs\tensorflow_gpu\lib\site-packages  \tensorflow\python\client\session.py", line 789, in run
 run_metadata_ptr)
 File "C:\Users\divin\Miniconda3\envs\tensorflow_gpu\lib\site-packages \tensorflow\python\client\session.py", line 997, in _run
 feed_dict_string, options, run_metadata)
 File "C:\Users\divin\Miniconda3\envs\tensorflow_gpu\lib\site-packages  \tensorflow\python\client\session.py", line 1132, in _do_run
 target_list, options, run_metadata)
 File "C:\Users\divin\Miniconda3\envs\tensorflow_gpu\lib\site-packages  \tensorflow\python\client\session.py", line 1152, in _do_call
 raise type(e)(node_def, op, message)
 tensorflow.python.framework.errors_impl.OutOfRangeError:    RandomShuffleQueue '_2_shuffle_batch/random_shuffle_queue' is closed and has insufficient elements (requested 512, current size 0)
     [[Node: shuffle_batch = QueueDequeueManyV2[component_types=   [DT_FLOAT], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"] (shuffle_batch/random_shuffle_queue, shuffle_batch/n)]]
      [[Node: shuffle_batch/_25 = _Recv[client_terminated=false,     recv_device="/job:localhost/replica:0/task:0/gpu:0",    send_device="/job:localhost/replica:0/task:0/cpu:0",    send_device_incarnation=1, tensor_name="edge_5_shuffle_batch",     tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/gpu:0"]()]]

Caused by op 'shuffle_batch', defined at:
File "super_res_class.py", line 136, in <module>
p = Super_res(1024,1024,512,record_size, weights, biases)   # params  (n_input, n_output, batch_size)
File "super_res_class.py", line 50, in __init__
self.data_batch =   data_reader3.batch_generator([DATA_PATH_OPTICAL_TRAIN],self.record_size, self.batch_size) # train set
 File "E:\google_drive\Doctorate\matlab code\Tensorflow\doctorate_CNN\dong_recreation\data_reader3.py", line 156, in batch_generator
 capacity=capacity, min_after_dequeue=min_after_dequeue)
 File "C:\Users\divin\Miniconda3\envs\tensorflow_gpu\lib\site-packages\tensorflow\python\training\input.py", line 1217, in shuffle_batch
 name=name)
 File "C:\Users\divin\Miniconda3\envs\tensorflow_gpu\lib\site-packages\tensorflow\python\training\input.py", line 788, in _shuffle_batch
dequeued = queue.dequeue_many(batch_size, name=name)
File "C:\Users\divin\Miniconda3\envs\tensorflow_gpu\lib\site-packages \tensorflow\python\ops\data_flow_ops.py", line 457, in dequeue_many
 self._queue_ref, n=n, component_types=self._dtypes, name=name)
File "C:\Users\divin\Miniconda3\envs\tensorflow_gpu\lib\site-packages \tensorflow\python\ops\gen_data_flow_ops.py", line 946, in _queue_dequeue_many_v2
 timeout_ms=timeout_ms, name=name)
 File "C:\Users\divin\Miniconda3\envs\tensorflow_gpu\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 767, in apply_op
op_def=op_def)
 File "C:\Users\divin\Miniconda3\envs\tensorflow_gpu\lib\site-packages\tensorflow\python\framework\ops.py", line 2506, in create_op
original_op=self._default_original_op, op_def=op_def)
 File "C:\Users\divin\Miniconda3\envs\tensorflow_gpu\lib\site-packages\tensorflow\python\framework\ops.py", line 1269, in __init__
self._traceback = _extract_stack()

 OutOfRangeError (see above for traceback): RandomShuffleQueue '_2_shuffle_batch/random_shuffle_queue' is closed and has insufficient elements (requested 512, current size 0)
     [[Node: shuffle_batch = QueueDequeueManyV2[component_types=[DT_FLOAT], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](shuffle_batch/random_shuffle_queue, shuffle_batch/n)]]
     [[Node: shuffle_batch/_25 = _Recv[client_terminated=false,   recv_device="/job:localhost/replica:0/task:0/gpu:0", send_device="/job:localhost/replica:0/task:0/cpu:0", send_device_incarnation=1, tensor_name="edge_5_shuffle_batch", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/gpu:0"]()]]


 (tensorflow_gpu) E:\google_drive\Doctorate\matlab code\Tensorflow\doctorate_CNN\dong_recreation>

When I remove the sess.run() from my pred output, the code seems to operate normally.

 def train(self):
    #self.low_res = self.data1[0]
    #self.high_res = self.data1[1]

    # define loss and optimizer
    #self.cost = tf.reduce_mean(tf.pow(self.data1[1] - self.pred, 2))
    #self.optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(self.cost)

    # Initializing the variables
    init = tf.global_variables_initializer()

    # Initialize session
    with tf.Session() as sess:
        sess.run(init)
        coord = tf.train.Coordinator()
        threads = tf.train.start_queue_runners(coord=coord)
        step = 1
        print("Entering training")

        # Keep  training until reach max iterations
        while step * batch_size < training_iters:
            #_, c = sess.run([self.optimizer, self.cost])
            conv_result = self.pred
            print(conv_result)
            #data2 = self.data1[0]
            #print(data2)

            if step % display_step == 0:
                print("Step:", '%04d' % (step+1))
            #   "cost=", c)
            step = step + 1

        coord.request_stop()
        coord.join(threads)

Could someone please explain this to me? Normally, the graph is only evaluated when run under a session! What gives here?

Answer 1

Just saying conv_result = self.pred won't do anything -- you need, indeed, to do sess.run(self.pred) to get it to execute. The errors you're getting are something else about your model. As they say, your InputProducer has an empty queue. With the information you've given it can't be diagnosed, but I would search further on the site for why your InputProducer isn't filling / has zero size.