I'm trying to make a CNN (still a beginner). When trying to fit the model I am getting this error:
ValueError: A target array with shape (10000, 10) was passed for output of shape (None, 6, 6, 10) while using as loss categorical_crossentropy
. This loss expects targets to have the same shape as the output.
The shape of labels = (10000, 10) the shape of the image data = (10000, 32, 32, 3)
Code:
import pickle
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import (Dense, Dropout, Activation, Flatten,
Conv2D, MaxPooling2D)
from tensorflow.keras.callbacks import TensorBoard
from keras.utils import to_categorical
import numpy as np
import time
MODEL_NAME = f"_________{int(time.time())}"
BATCH_SIZE = 64
class ConvolutionalNetwork():
'''
A convolutional neural network to be used to classify images
from the CIFAR-10 dataset.
'''
def __init__(self):
'''
self.training_images -- a 10000x3072 numpy array of uint8s. Each
a row of the array stores a 32x32 colour image.
The first 1024 entries contain the red channel
values, the next 1024 the green, and the final
1024 the blue. The image is stored in row-major
order, so that the first 32 entries of the array are the red channel values of the first row of the image.
self.training_labels -- a list of 10000 numbers in the range 0-9.
The number at index I indicates the label
of the ith image in the array data.
'''
# List of image categories
self.label_names = (self.unpickle("cifar-10-batches-py/batches.meta",
encoding='utf-8')['label_names'])
self.training_data = self.unpickle("cifar-10-batches-py/data_batch_1")
self.training_images = self.training_data[b'data']
self.training_labels = self.training_data[b'labels']
# Reshaping the images + scaling
self.shape_images()
# Converts labels to one-hot
self.training_labels = np.array(to_categorical(self.training_labels))
self.create_model()
self.tensorboard = TensorBoard(log_dir=f'logs/{MODEL_NAME}')
def unpickle(self, file, encoding='bytes'):
'''
Unpickles the dataset files.
'''
with open(file, 'rb') as fo:
training_dict = pickle.load(fo, encoding=encoding)
return training_dict
def shape_images(self):
'''
Reshapes the images and scales by 255.
'''
images = list()
for d in self.training_images:
image = np.zeros((32,32,3), dtype=np.uint8)
image[...,0] = np.reshape(d[:1024], (32,32)) # Red channel
image[...,1] = np.reshape(d[1024:2048], (32,32)) # Green channel
image[...,2] = np.reshape(d[2048:], (32,32)) # Blue channel
images.append(image)
for i in range(len(images)):
images[i] = images[i]/255
images = np.array(images)
self.training_images = images
print(self.training_images.shape)
def create_model(self):
'''
Creating the ConvNet model.
'''
self.model = Sequential()
self.model.add(Conv2D(64, (3, 3), input_shape=self.training_images.shape[1:]))
self.model.add(Activation("relu"))
self.model.add(MaxPooling2D(pool_size=(2,2)))
self.model.add(Conv2D(64, (3,3)))
self.model.add(Activation("relu"))
self.model.add(MaxPooling2D(pool_size=(2,2)))
# self.model.add(Flatten())
# self.model.add(Dense(64))
# self.model.add(Activation('relu'))
self.model.add(Dense(10))
self.model.add(Activation(activation='softmax'))
self.model.compile(loss="categorical_crossentropy", optimizer="adam",
metrics=['accuracy'])
def train(self):
'''
Fits the model.
'''
print(self.training_images.shape)
print(self.training_labels.shape)
self.model.fit(self.training_images, self.training_labels, batch_size=BATCH_SIZE,
validation_split=0.1, epochs=5, callbacks=[self.tensorboard])
network = ConvolutionalNetwork()
network.train()
Would appreciate the help, have been trying to fix for an hour.
You need to uncomment the Flatten
layer when creating your model. Essentially what this layer does is that it takes a 4D input (batch_size, height, width, num_filters)
and unrolls it into a 2D one (batch_size, height * width * num_filters)
. This is needed to get the output shape you want.
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With