Tensorflow Dimension Error on reshape

Question

I am trying to addapt the very simple MNIST example (https://github.com/tensorflow/tensorflow/blob/r1.8/tensorflow/examples/tutorials/layers/cnn_mnist.py) to suit a problem that I have. The problem seems to be somewhere in the dimension of my input ( i believe)

Where the original MNIST data has the following properties (inserted at line 125):

print(train_data.shape) #    (55000, 784)
print(type(train_data)) #    <class 'numpy.ndarray'>
print(train_labels.shape) #  (55000, )
print(type(train_labels)) #  <class 'numpy.ndarray'>

my data has the following shape

Train Data:  (10681, 9216)
Train Data:  <class 'numpy.ndarray'>
Train Labe:  (10681,)
Train Labe:  <class 'numpy.ndarray'>

in particular we have that 784=28*28 and 9216=96*96.Thus, where the original line (31) reads

 input_layer = tf.reshape(features["x"], [-1, 28, 28, 1])

i replaced it with

 input_layer = tf.reshape(features["x"], [-1, 96, 96, 1])

However when I run this, the error that I get is:

Traceback (most recent call last):
  File "/home/j-pc/.local/lib/python3.5/site-packages/tensorflow/python/framework/common_shapes.py", line686, in _call_cpp_shape_fn_impl
    input_tensors_as_shapes, status)
  File "/home/j-pc/.local/lib/python3.5/site-packages/tensorflow/python/framework/errors_impl.py", line 473, in __exit__
    c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Dimension size must be evenly divisible by 3136 but is 3686400 for 'Reshape_1' (op: 'Reshape') with input shapes: [100,24,24,64], [2] and with input tensors computed as partial shapes: input[1] = [?,3136].

During handling of the above exception, another exception occurred:
Traceback (most recent call last):
  File "tensorfuck/learn.py", line 252, in <module>
    tf.app.run()
  File "/home/j-pc/.local/lib/python3.5/site-packages/tensorflow/python/platform/app.py", line 124, in run
    _sys.exit(main(argv))
  File "tensorfuck/learn.py", line 238, in main
    hooks=[logging_hook])
  File "/home/j-pc/.local/lib/python3.5/site-packages/tensorflow/python/estimator/estimator.py", line 314, in train
    loss = self._train_model(input_fn, hooks, saving_listeners)
  File "/home/j-pc/.local/lib/python3.5/site-packages/tensorflow/python/estimator/estimator.py", line 743, in _train_model
    features, labels, model_fn_lib.ModeKeys.TRAIN, self.config)
  File "/home/j-pc/.local/lib/python3.5/site-packages/tensorflow/python/estimator/estimator.py", line 725, in _call_model_fn
    model_fn_results = self._model_fn(features=features, **kwargs)
  File "tensorfuck/learn.py", line 88, in cnn_model_fn
    pool2_flat = tf.reshape(pool2, [-1, 7 * 7 * 64])
  File "/home/j-pc/.local/lib/python3.5/site-packages/tensorflow/python/ops/gen_array_ops.py", line 3997,in reshape
    "Reshape", tensor=tensor, shape=shape, name=name)
  File "/home/j-pc/.local/lib/python3.5/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
    op_def=op_def)
  File "/home/j-pc/.local/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 3162, in create_op
    compute_device=compute_device)
  File "/home/j-pc/.local/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 3208, in _create_op_helper
    set_shapes_for_outputs(op)
  File "/home/j-pc/.local/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 2427, in set_shapes_for_outputs
    return _set_shapes_for_outputs(op)
  File "/home/j-pc/.local/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 2400, in _set_shapes_for_outputs
    shapes = shape_func(op)
  File "/home/j-pc/.local/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 2330, in call_with_requiring
    return call_cpp_shape_fn(op, require_shape_fn=True)
  File "/home/j-pc/.local/lib/python3.5/site-packages/tensorflow/python/framework/common_shapes.py", line627, in call_cpp_shape_fn
    require_shape_fn)
  File "/home/j-pc/.local/lib/python3.5/site-packages/tensorflow/python/framework/common_shapes.py", line691, in _call_cpp_shape_fn_impl
    raise ValueError(err.message)
ValueError: Dimension size must be evenly divisible by 3136 but is 3686400 for 'Reshape_1' (op: 'Reshape') with input shapes: [100,24,24,64], [2] and with input tensors computed as partial shapes: input[1] = [?,3136].

Whats the problem? P.S. I use Python3.5.2 and Tensorflow1.5.0 on Ubuntu16.04 Running the original MNIST example gives no errors.

Answer 1

Problem

Indeed it is a dimensionality problem. It has to do with your general network architecture, which does not match your new input size. You adopted the architecture from cnn_mnist.py. Here line 72 is causing the issue:

pool2_flat = tf.reshape(pool2, [-1, 7 * 7 * 64]) // 7*7*64=3136 

The architecture assumes a [-1, 7, 7, 64] shape, but you are passing [-1,24,24,64].

How to fix it

change pool2_flat to match your acutal output shape:

pool2_flat = tf.reshape(pool2, [-1, 24 * 24 * 64])