Input 0 of layer sequential is incompatible with the layer: expected axis -1 of input shape to have value 3 but received input with shape

Question

it is my first time with tensorflow and I have problem that I can't solve. I found a lot of same problems on stackoverflow, but they don't help me. (probably I just don't know how use it correctly) I have a model, that trained by this algorithm

import seaborn as sns
import matplotlib.pyplot as plt

from tensorflow import keras
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Conv2D, MaxPool2D, Flatten, Dropout
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras import layers

from sklearn.metrics import classification_report, confusion_matrix

import tensorflow as tf

import cv2
import os

import numpy as np

from resources.Globals import *

labels = ['houses', 'other']
img_size = 400


def get_data(data_dir):
    data = []
    for label in labels:
        path = os.path.join(data_dir, label)
        class_num = labels.index(label)
        for img in os.listdir(path):
            try:
                img_arr = cv2.imread(os.path.join(path, img))[..., ::-1]  # Convert BGR to RGB format
                resized_arr = cv2.resize(img_arr, (img_size, img_size))  # Reshaping images to preferred size
                data.append([resized_arr, class_num])
            except Exception as e:
                print(e)
    return np.array(data, dtype="object")


def main():
    train = get_data('E:/Projects/Pycharm Projects/sapper/files/Neural_networks/Train')
    val = get_data('E:/Projects/Pycharm Projects/sapper/files/Neural_networks/Test')

    # Visualize the data
    l = []
    for i in train:
        if i[1] != 0:
            l.append("houses")
        else:
            l.append("other")
    sns.set_style('darkgrid')
    sns.countplot(l)

    # House
    plt.figure(figsize=(5, 5))
    plt.imshow(train[1][0])
    plt.title(labels[train[0][1]])

    # Other
    plt.figure(figsize=(5, 5))
    plt.imshow(train[-1][0])
    plt.title(labels[train[-1][1]])

    # Data Preprocessing
    x_train = []
    y_train = []
    x_val = []
    y_val = []

    for feature, label in train:
        x_train.append(feature)
        y_train.append(label)

    for feature, label in val:
        x_val.append(feature)
        y_val.append(label)

    # Normalize the data
    x_train = np.array(x_train) / 255
    x_val = np.array(x_val) / 255

    x_train.reshape(-1, img_size, img_size, 1)
    y_train = np.array(y_train)

    x_val.reshape(-1, img_size, img_size, 1)
    y_val = np.array(y_val)

    # Data augmentation
    datagen = ImageDataGenerator(
        featurewise_center=False,  # set input mean to 0 over the dataset
        samplewise_center=False,  # set each sample mean to 0
        featurewise_std_normalization=False,  # divide inputs by std of the dataset
        samplewise_std_normalization=False,  # divide each input by its std
        zca_whitening=False,  # apply ZCA whitening
        rotation_range=30,  # randomly rotate images in the range (degrees, 0 to 180)
        zoom_range=0.2,  # Randomly zoom image
        width_shift_range=0.1,  # randomly shift images horizontally (fraction of total width)
        height_shift_range=0.1,  # randomly shift images vertically (fraction of total height)
        horizontal_flip=True,  # randomly flip images
        vertical_flip=False)  # randomly flip images

    print('Pretrain')

    datagen.fit(x_train)

    print('After train')

    # Define the Model
    model = Sequential()
    model.add(Conv2D(32, 3, padding="same", activation="relu", input_shape=(img_size, img_size, 3)))
    model.add(MaxPool2D())

    model.add(Conv2D(64, 3, padding="same", activation="relu"))
    model.add(MaxPool2D())
    model.add(Dropout(DROPOUT))

    model.add(Flatten())
    model.add(Dense(128, activation="relu"))
    model.add(Dense(2, activation="softmax"))

    model.summary()

    # Compile the model
    opt = keras.optimizers.Adam(lr=0.000001)  # Adam as optimizer and SparseCategoricalCrossentropy as the loss function
    model.compile(optimizer=opt, loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
                  metrics=['accuracy'])

    print('Pretrain #2')
    # Train model
    history = model.fit(x_train, y_train, epochs=AMOUNT_OF_EPOCHS, validation_data=(x_val, y_val))
    print('After train #2')

    model.save("../../files/Neural_networks/model/training_3")

    print('Model saved')

    # Evaluating the result
    acc = history.history['accuracy']
    val_acc = history.history['val_accuracy']
    loss = history.history['loss']
    val_loss = history.history['val_loss']

    epochs_range = range(1, AMOUNT_OF_EPOCHS + 1)

    plt.figure(figsize=(15, 15))
    plt.subplot(2, 2, 1)
    plt.plot(epochs_range, acc, label='Training Accuracy')
    plt.plot(epochs_range, val_acc, label='Validation Accuracy')
    plt.legend(loc='lower right')
    plt.title('Training and Validation Accuracy')

    plt.subplot(2, 2, 2)
    plt.plot(epochs_range, loss, label='Training Loss')
    plt.plot(epochs_range, val_loss, label='Validation Loss')
    plt.legend(loc='upper right')
    plt.title('Training and Validation Loss')

    # Precision and accuracy report
    predictions = model.predict_classes(x_val)
    predictions = predictions.reshape(1, -1)[0]
    print(classification_report(y_val, predictions, target_names=['Rugby (Class 0)', 'Soccer (Class 1)']))

    # Show all plots
    plt.show()


if __name__ == '__main__':
    main()

Also I have code, that should predict using my model

import cv2
import tensorflow as tf
import numpy as np
from keras_preprocessing.image import ImageDataGenerator

CATEGORIES = ['houses', 'other']


def prepare(filepath):
    IMG_SIZE = 400  # 50 in txt-based
    img_array = cv2.imread(filepath, cv2.IMREAD_GRAYSCALE)
    new_array = cv2.resize(img_array, (IMG_SIZE, IMG_SIZE))
    new_array = np.array(new_array) / 255
    return new_array.reshape(-1, IMG_SIZE, IMG_SIZE, 1)


model = tf.keras.models.load_model("../../files/Neural_networks/model/training_3")
model.summary()

test = prepare("E:/Projects/Pycharm Projects/sapper/files/Neural_networks/Test/houses/5_frontal.jpg")

pred = test

prediction = model.predict([pred])
print('after predict')
print(prediction)  # will be a list in a list.
print(CATEGORIES[int(prediction[0][0])])

And in second code in line prediction = model.predict([pred]) I have this error: ValueError: Input 0 of layer sequential is incompatible with the layer: expected axis -1 of input shape to have value 3 but received input with shape [None, 400, 400, 1]

Whole error:

Traceback (most recent call last):
  File "E:/Projects/Pycharm Projects/sapper/bin/Main/test_2.py", line 25, in <module>
    prediction = model.predict([pred])
  File "E:\Python versions\Python37\lib\site-packages\tensorflow\python\keras\engine\training.py", line 130, in _method_wrapper
    return method(self, *args, **kwargs)
  File "E:\Python versions\Python37\lib\site-packages\tensorflow\python\keras\engine\training.py", line 1599, in predict
    tmp_batch_outputs = predict_function(iterator)
  File "E:\Python versions\Python37\lib\site-packages\tensorflow\python\eager\def_function.py", line 780, in __call__
    result = self._call(*args, **kwds)
  File "E:\Python versions\Python37\lib\site-packages\tensorflow\python\eager\def_function.py", line 823, in _call
    self._initialize(args, kwds, add_initializers_to=initializers)
  File "E:\Python versions\Python37\lib\site-packages\tensorflow\python\eager\def_function.py", line 697, in _initialize
    *args, **kwds))
  File "E:\Python versions\Python37\lib\site-packages\tensorflow\python\eager\function.py", line 2855, in _get_concrete_function_internal_garbage_collected
    graph_function, _, _ = self._maybe_define_function(args, kwargs)
  File "E:\Python versions\Python37\lib\site-packages\tensorflow\python\eager\function.py", line 3213, in _maybe_define_function
    graph_function = self._create_graph_function(args, kwargs)
  File "E:\Python versions\Python37\lib\site-packages\tensorflow\python\eager\function.py", line 3075, in _create_graph_function
    capture_by_value=self._capture_by_value),
  File "E:\Python versions\Python37\lib\site-packages\tensorflow\python\framework\func_graph.py", line 986, in func_graph_from_py_func
    func_outputs = python_func(*func_args, **func_kwargs)
  File "E:\Python versions\Python37\lib\site-packages\tensorflow\python\eager\def_function.py", line 600, in wrapped_fn
    return weak_wrapped_fn().__wrapped__(*args, **kwds)
  File "E:\Python versions\Python37\lib\site-packages\tensorflow\python\framework\func_graph.py", line 973, in wrapper
    raise e.ag_error_metadata.to_exception(e)
ValueError: in user code:

    E:\Python versions\Python37\lib\site-packages\tensorflow\python\keras\engine\training.py:1462 predict_function  *
        return step_function(self, iterator)
    E:\Python versions\Python37\lib\site-packages\tensorflow\python\keras\engine\training.py:1452 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    E:\Python versions\Python37\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:1211 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    E:\Python versions\Python37\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2585 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    E:\Python versions\Python37\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2945 _call_for_each_replica
        return fn(*args, **kwargs)
    E:\Python versions\Python37\lib\site-packages\tensorflow\python\keras\engine\training.py:1445 run_step  **
        outputs = model.predict_step(data)
    E:\Python versions\Python37\lib\site-packages\tensorflow\python\keras\engine\training.py:1418 predict_step
        return self(x, training=False)
    E:\Python versions\Python37\lib\site-packages\tensorflow\python\keras\engine\base_layer.py:976 __call__
        self.name)
    E:\Python versions\Python37\lib\site-packages\tensorflow\python\keras\engine\input_spec.py:216 assert_input_compatibility
        ' but received input with shape ' + str(shape))

    ValueError: Input 0 of layer sequential is incompatible with the layer: expected axis -1 of input shape to have value 3 but received input with shape [None, 400, 400, 1]

How I should solve it?

Answer 1

There is a problem with your input shape obviously.

The architecture of your model is as below. So the input shape should be (1,400,400,3).

In the function prepare that feeds the data to the network, the output shape is (400,400,1). And that is why you get an error.

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d (Conv2D)              (None, 400, 400, 32)      896       
_________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 200, 200, 32)      0         
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 200, 200, 64)      18496     
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 100, 100, 64)      0         
_________________________________________________________________
dropout (Dropout)            (None, 100, 100, 64)      0         
_________________________________________________________________
flatten (Flatten)            (None, 640000)            0         
_________________________________________________________________
dense (Dense)                (None, 128)               81920128  
_________________________________________________________________
dense_1 (Dense)              (None, 2)                 258       
=================================================================
Total params: 81,939,778
Trainable params: 81,939,778
Non-trainable params: 0

• Start by removing the CV2.IMREAD_GRAYSCALE argument because cv2.imread won't load the three RGB channels of the image and the size would only be (IMG_SIZE,IMG_SIZE). `

a = cv2.imread('Downloads/21.png')

a.shape

(652, 1366,3)

a = cv2.imread('Downloads/21.png',cv2.IMREAD_GRAYSCALE)

a.shape (652, 1366) `

• Then reshape the loaded image to (1,IMG_SIZE,IMG_SIZE,3)

I tried to run the model on np.zeros(1,IMG_SIZE,IMG_SIZE,3) and it works well.