CODEWITHSUNDEEP
pythontensorflowdeep-learningconv-neural-network
xmacz
xmacz

Reputation: 444

Shape of logits and labels mismatch

Error:

Traceback (most recent call last):
  File "C:/Users/xx/abc/Final.py", line 167, in <module>
    tf.app.run()
  File "C:\Users\xx\tensorflow\python\platform\app.py", line 126, in run
    _sys.exit(main(argv))
  File "C:/Users/xx/abc/Final.py", line 148, in main
    hooks=[logging_hook])
  File "C:\Users\xx\tensorflow\python\estimator\estimator.py", line 363, in train
    loss = self._train_model(input_fn, hooks, saving_listeners)
  File "C:\Users\xx\tensorflow\python\estimator\estimator.py", line 843, in _train_model
    return self._train_model_default(input_fn, hooks, saving_listeners)
  File "C:\Users\xx\tensorflow\python\estimator\estimator.py", line 856, in _train_model_default
    features, labels, model_fn_lib.ModeKeys.TRAIN, self.config)
  File "C:\Users\xx\tensorflow\python\estimator\estimator.py", line 831, in _call_model_fn
    model_fn_results = self._model_fn(features=features, **kwargs)
  File "C:/Users/xx/abc/Final.py", line 61, in cnn_model_fn
    loss = tf.losses.sparse_softmax_cross_entropy(labels=labels, logits=logits)
  File "C:\Users\xx\tensorflow\python\ops\losses\losses_impl.py", line 853, in sparse_softmax_cross_entropy
    name="xentropy")
  File "C:\Users\xx\tensorflow\python\ops\nn_ops.py", line 2046, in sparse_softmax_cross_entropy_with_logits
    logits.get_shape()))


ValueError: Shape mismatch: The shape of labels (received (100,)) should equal the shape of logits except for the last dimension (received (300, 10)).

Train input function:

train_input_fn = tf.estimator.inputs.numpy_input_fn(
      x={"x": train_data},
      y=train_labels,
      batch_size=100,
      num_epochs=None,
      shuffle=True)

ALL DATASET SHAPES

  print(train_data.shape)
  //Output: (9490, 2352) 

  train_labels = np.asarray(label_MAX[0], dtype=np.int32)


  print(train_labels.shape)
  //Output: (9490,)
  eval_data = datasets[1]  # Returns np.array


  print(eval_data.shape)
  //Output: (3175, 2352)
  eval_labels = np.asarray(label_MAX[1], dtype=np.int32)


  print(eval_labels.shape)
  //Output: (3175,)

I read other StackOverflow questions and most of them pointed to the calculation of the loss function as the point of error. The fact that the code sends a batch of 100 labels is causing an issue?

How can I resolve this? Is the fact that the number of images and labels not being a multiple of 100 the root of this issue?

My model is being trained for only 0 and 1 So I suppose I must make a change to this 

logits = tf.layers.dense(inputs=dropout, units=10)

and change number of units to 2?

Upvotes: 3

Views: 9665

Answers (2)

JSVJ
JSVJ

Reputation: 493

I got the same error. I realized that I didn't Flatten my Image data. Once I included the Flatten() layer I am able to process the neural network properly. Could you try adding a Flatten Layer before the Dense Layers?

Upvotes: 3

Sunreef
Sunreef

Reputation: 4542

The issue comes form the fact that you are using RGB images. The model is designed to be used with grayscale images as shown in the line input_layer = tf.reshape(features["x"], [-1, 28, 28, 1]) near the top of the CNN definition. Having 3 channels instead of 1 means that the batch size here will be three times too large.

To fix that, change that line to input_layer = tf.reshape(features["x"], [-1, 28, 28, 3]).

Upvotes: 3

Related Questions