Tensorflow summery merge error : Shape [-1,784] ha

I am trying to get summary of a training process of the neural net below.

import tensorflow as tf 
import numpy as np 

from tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets(".\MNIST",one_hot=True)

# Create the model
def train_and_test(hidden1,hidden2, learning_rate, epochs, batch_size):

    with tf.name_scope("first_layer"):
        input_data = tf.placeholder(tf.float32, [batch_size, 784], name = "input")
        weights1  = tf.Variable(
        tf.random_normal(shape =[784, hidden1],stddev=0.1),name = "weights")
        bias = tf.Variable(tf.constant(0.0,shape =[hidden1]), name = "bias")
        activation = tf.nn.relu(
        tf.matmul(input_data, weights1) + bias, name = "relu_act")
        tf.summary.histogram("first_activation", activation)

    with tf.name_scope("second_layer"):
        weights2  = tf.Variable(
        tf.random_normal(shape =[hidden1, hidden2],stddev=0.1),
        name = "weights")
        bias2 = tf.Variable(tf.constant(0.0,shape =[hidden2]), name = "bias")
        activation2 = tf.nn.relu(
        tf.matmul(activation, weights2) + bias2, name = "relu_act")
        tf.summary.histogram("second_activation", activation2)

    with tf.name_scope("output_layer"):
        weights3 = tf.Variable(
            tf.random_normal(shape=[hidden2, 10],stddev=0.5), name = "weights")
        bias3 = tf.Variable(tf.constant(1.0, shape =[10]), name = "bias")
        output = tf.add(
        tf.matmul(activation2, weights3, name = "mul"), bias3, name = "output")
        tf.summary.histogram("output_activation", output)
    y_ = tf.placeholder(tf.float32, [batch_size, 10])

    with tf.name_scope("loss"):
        cross_entropy = tf.reduce_mean(
        tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=output))
        tf.summary.scalar("cross_entropy", cross_entropy)
    with tf.name_scope("train"):
        train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(cross_entropy)

    with tf.name_scope("tests"):
        correct_prediction = tf.equal(tf.argmax(output, 1), tf.argmax(y_, 1))
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    summary_op = tf.summary.merge_all()

    sess = tf.InteractiveSession()
    writer = tf.summary.FileWriter("./data", sess.graph)
    tf.global_variables_initializer().run()

    # Train
    for i in range(epochs):
        batch_xs, batch_ys = mnist.train.next_batch(batch_size)
         _, summary = sess.run([train_step,summary_op], feed_dict={input_data: batch_xs, y_: batch_ys})
     writer.add_summary(summary)

     if i % 10 ==0:
          test_xs, test_ys = mnist.train.next_batch(batch_size)
          test_accuracy = sess.run(accuracy, feed_dict = {input_data : test_xs, y_ : test_ys})
    writer.close()
    return test_accuracy

if __name__ =="__main__":
print(train_and_test(500, 200, 0.001, 10000, 100))

I am testing the model every 10 step with a random batch of test data. The problem is in the summery writer. The sess.run() inside the for loop throws following error.

    Traceback (most recent call last):

  File "<ipython-input-18-78c88c8e6471>", line 1, in <module>
    runfile('C:/Users/Suman 
Nepal/Documents/Projects/MNISTtensorflow/mnist.py', wdir='C:/Users/Suman 
Nepal/Documents/Projects/MNISTtensorflow')

  File "C:\Users\Suman Nepal\Anaconda3\lib\site-
packages\spyder\utils\site\sitecustomize.py", line 880, in runfile
execfile(filename, namespace)

  File "C:\Users\Suman Nepal\Anaconda3\lib\site-
packages\spyder\utils\site\sitecustomize.py", line 102, in execfile
exec(compile(f.read(), filename, 'exec'), namespace)

  File "C:/Users/Suman Nepal/Documents/Projects/MNISTtensorflow/mnist.py", line 68, in <module>
    print(train_and_test(500, 200, 0.001, 100, 100))

  File "C:/Users/Suman Nepal/Documents/Projects/MNISTtensorflow/mnist.py", line 58, in train_and_test
    _, summary = sess.run([train_step,summary_op], feed_dict={input_data: batch_xs, y_: batch_ys})

  File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 789, in run
    run_metadata_ptr)

  File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 997, in _run
feed_dict_string, options, run_metadata)

  File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1132, in _do_run
target_list, options, run_metadata)

  File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1152, in _do_call
raise type(e)(node_def, op, message)

InvalidArgumentError: Shape [-1,784] has negative dimensions
 [[Node: first_layer_5/input = Placeholder[dtype=DT_FLOAT, shape=[?,784], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]

Caused by op 'first_layer_5/input', defined at:
  File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\spyder\utils\ipython\start_kernel.py", line 231, in <module>
main()
  File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\spyder\utils\ipython\start_kernel.py", line 227, in main
kernel.start()
  File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\ipykernel\kernelapp.py", line 477, in start
ioloop.IOLoop.instance().start()
  File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\zmq\eventloop\ioloop.py", line 177, in start
super(ZMQIOLoop, self).start()
  File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\tornado\ioloop.py", line 888, in start
handler_func(fd_obj, events)
  File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\tornado\stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
  File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 440, in _handle_events
self._handle_recv()
  File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 472, in _handle_recv
self._run_callback(callback, msg)
  File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 414, in _run_callback
callback(*args, **kwargs)
  File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\tornado\stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
 File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 283, in dispatcher
return self.dispatch_shell(stream, msg)
 File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 235, in dispatch_shell
handler(stream, idents, msg)
  File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 399, in execute_request
user_expressions, allow_stdin)
  File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\ipykernel\ipkernel.py", line 196, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
  File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\ipykernel\zmqshell.py", line 533, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
  File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2717, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
  File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2827, in run_ast_nodes
if self.run_code(code, result):
  File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2881, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-8-78c88c8e6471>", line 1, in <module>
runfile('C:/Users/Suman Nepal/Documents/Projects/MNISTtensorflow/mnist.py', wdir='C:/Users/Suman Nepal/Documents/Projects/MNISTtensorflow')
  File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 880, in runfile
execfile(filename, namespace)
  File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 102, in execfile
exec(compile(f.read(), filename, 'exec'), namespace)
  File "C:/Users/Suman Nepal/Documents/Projects/MNISTtensorflow/mnist.py", line 86, in <module>
  File "C:/Users/Suman Nepal/Documents/Projects/MNISTtensorflow/mnist.py", line 12, in train_and_test
   input_data = tf.placeholder(tf.float32, [None, 784], name = "input")
  File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\tensorflow\python\ops\array_ops.py", line 1530, in placeholder
return gen_array_ops._placeholder(dtype=dtype, shape=shape, name=name)
  File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\tensorflow\python\ops\gen_array_ops.py", line 1954, in _placeholder
name=name)
  File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 767, in apply_op
op_def=op_def)
  File "C:\Users\Suman Nepal\Anaconda3\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\Suman Nepal\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1269, in __init__
self._traceback = _extract_stack()

InvalidArgumentError (see above for traceback): Shape [-1,784] has negative dimensions
     [[Node: first_layer_5/input = Placeholder[dtype=DT_FLOAT, shape=[?,784], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]

If I deleted all the summary writers and summary, the model runs fine. Can you help me spot the problem here? I tried manipulating the shapes of tensors but got nowhere.

回答1:

From one comment of the deleted answer, from the original poster:

I actually build a neural net under with tf.Graph() as g. I removed the interactive session and started session as with tf.Session(g) as sess. It fixed the problem.

The graph g was not marked as the default graph that way, thus the session (tf.InteractiveSession in the original code) would use another graph instead.

Note that I stumbled upon here because of the same error message. In my case, I had accidentally something like this:

input_data = tf.placeholder(tf.float32, shape=(None, 50))
input_data = tf.tanh(input_data)
session.run(..., feed_dict={input_data: ...})

I.e. I didn't feed the placeholder. It seems that some other tensor operations can then result in this confusing error as internally an undefined dimension is represented as -1.

回答2:

I was also having this problem. Searching around the basic consensus is to check for problems somewhere else in your code.

What fixed it for me was I was doing a sess.run(summary_op) without feeding in data for my placeholders.

Tensorflow seems to be a bit strange with placeholders, often they won't mind you not feeding them if you're trying to evaluate part of the graph that is independent of them. Here though, it did.

回答3:

This has may have to do with the InteractiveSession initialization.

I initialized it at the beginning and then it worked - then initialized the global variables within the session.

I am unable to reproduce the error with the old code, which makes it unpredictable or caching settings somewhere.

import tensorflow as tf
sess = tf.InteractiveSession()


from tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

x = tf.placeholder(tf.float32, [None, 784])

W = tf.Variable(tf.zeros([784,10]))

b = tf.Variable(tf.zeros([10]))

y = tf.nn.softmax(tf.matmul(x, W)+b)

y_ = tf.placeholder(tf.float32, [None,10])



cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))
train_step = tf.train.GradientDescentOptimizer(0.05).minimize(cross_entropy)
sess.run(tf.global_variables_initializer())


for _ in range(1000):
    batch_xs, batch_ys = mnist.train.next_batch(100)
    #print batch_xs.shape, batch_ys.shape
    sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})