TensorFlow Error: ValueError("Shapes %s and %s are incompatible" % (self, other))

Question

I'm trying to classify images of PCBs into two categories (defected and undefected) using categorical cross-entropy as the loss function. The code for the same is as below:

import numpy as np
import matplotlib.pyplot as plt

import tensorflow
from tensorflow.keras.applications import ResNet50
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.optimizers import SGD
from tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint


from keras.applications.resnet50 import preprocess_input
from keras.preprocessing.image import ImageDataGenerator

from sklearn.model_selection import train_test_split

def create_compiled_model():
  model = Sequential()
  model.add(ResNet50(include_top=False, weights=RESNET50_WEIGHTS, input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3), pooling=RESNET50_POOLING_AVERAGE))
  model.add(Dense(NUM_CLASSES, activation=DENSE_LAYER_ACTIVATION))
  model.layers[0].trainable = False

  sgd = SGD(lr = 0.01, decay = 1e-6, momentum = 0.9, nesterov = True)
  model.compile(optimizer = sgd, loss = OBJECTIVE_FUNCTION, metrics = LOSS_METRICS)

  return model

def data_splitor():
  x = np.load("/content/data/xtrain.npy")
  y = np.load("/content/data/ytrain.npy")

  # Getting the Test and Train splits
  x_train, x_test, y_train, y_test = train_test_split(x, y, test_size= TRAIN_TEST_SPLIT, shuffle= True)

  # Getting the Train and Validation splits
  x__train, x__valid, y__train, y__valid = train_test_split(x_train, y_train, test_size= TRAIN_TEST_SPLIT, shuffle= True)

  return x__train, x__valid, x_test, y__train, y__valid, y_test

def data_generator(x, y, batch_size, seed=None, shuffle=True):
  data_generator = ImageDataGenerator(horizontal_flip=True, vertical_flip=True, rotation_range=180, brightness_range=[0.3, 1.0], preprocessing_function=preprocess_input)
  generator = data_generator.flow(x_train, y_train, batch_size= batch_size, seed= seed, shuffle=shuffle)
  return generator

def run_program():
  x_train, x_valid, x_test, y_train, y_valid, y_test = data_splitor()
  train_generator = data_generator(x_train, y_train, BATCH_SIZE_TRAINING)
  validation_generator = data_generator(x_valid, y_valid, BATCH_SIZE_VALIDATION)

  cb_early_stopper = EarlyStopping(monitor = 'val_loss', patience = EARLY_STOP_PATIENCE)
  cb_checkpointer = ModelCheckpoint(filepath = '/content/model/best.hdf5', monitor = 'val_loss', save_best_only = True, mode = 'auto')

  model = create_compiled_model()

  fit_history = model.fit_generator(
        train_generator,
        steps_per_epoch=STEPS_PER_EPOCH_TRAINING,
        epochs = NUM_EPOCHS,
        validation_data=validation_generator,
        validation_steps=STEPS_PER_EPOCH_VALIDATION,
        callbacks=[cb_checkpointer, cb_early_stopper]
  )

  plt.figure(1, figsize = (15,8)) 

  plt.subplot(221)
  plt.plot(fit_history.history['acc'])  
  plt.plot(fit_history.history['val_acc'])  
  plt.title('model accuracy')  
  plt.ylabel('accuracy')  
  plt.xlabel('epoch')  
  plt.legend(['train', 'valid']) 

  plt.subplot(222)  
  plt.plot(fit_history.history['loss'])  
  plt.plot(fit_history.history['val_loss'])  
  plt.title('model loss')  
  plt.ylabel('loss')  
  plt.xlabel('epoch')  
  plt.legend(['train', 'valid']) 

  plt.show()


  # Testing
  test_generator = data_generator(x_test, y_test, BATCH_SIZE_TESTING, 123, False)
  test_generator.reset()

  model.load_weights("/content/model/best.hdf5")
  pred = model.predict_generator(test_generator, steps = len(test_generator), verbose = 1)

  predicted_class_indices = np.argmax(pred, axis = 1)


# Running the program
try:
  with tensorflow.device('/device:GPU:0'):
    run_program()
except RuntimeError as e:
  print(e)

And upon executing this, I get the ValueError seen below:

ValueError: in user code:

    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:571 train_function  *
        outputs = self.distribute_strategy.run(
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:951 run  **
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2290 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2649 _call_for_each_replica
        return fn(*args, **kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:533 train_step  **
        y, y_pred, sample_weight, regularization_losses=self.losses)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/compile_utils.py:204 __call__
        loss_value = loss_obj(y_t, y_p, sample_weight=sw)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:143 __call__
        losses = self.call(y_true, y_pred)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:246 call
        return self.fn(y_true, y_pred, **self._fn_kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:1527 categorical_crossentropy
        return K.categorical_crossentropy(y_true, y_pred, from_logits=from_logits)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/backend.py:4561 categorical_crossentropy
        target.shape.assert_is_compatible_with(output.shape)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/tensor_shape.py:1117 assert_is_compatible_with
        raise ValueError("Shapes %s and %s are incompatible" % (self, other))

    ValueError: Shapes (None, 1) and (None, 2) are incompatible

I have already looked at this, this and this, but could not resolve the error.

I really appreciate the help in fixing this.

Thanks Praveen

Here is the complete traceback... link

Answer 1

Seems your y_train data have shape (None,1) while your network is expecting (None,2). There are two options to solve this:

1) Change your model output to 1 unit and change loss to binary crossentropy

or

2) Change your y_train data to categorical. See this

If you can post here your model.summary() and your dataset shapes it will help us to help you.

Answer 2

Your traceback link isn't working. However, try replacing categorical cross-entropy with binary cross entropy since you have only two classes.