I am trying to use run a GoogLeNet code using FERET datasets. When I run the code, I get the following error message:

 Traceback (most recent call last):
  File "C:\Users\JoshG\PycharmProjects\GoogLeNet\GoogLeNet5.py", line 221, in <module>
    y_pred = (model.predict_classes(testX))
AttributeError: 'Functional' object has no attribute 'predict_classes''

Can anyone tell me what I am doing wrong? Also, please educate me to make sure that my batch size are correct. The images that I am using at 227 x 227 as well.

I am new to python, so please patient with me understanding.

Below is the full code

# Python: 3.9
# keras: 2.2.4 for GoogLeNet on CIFAR-10
# Tensorflow :1.13.0
# cuda toolkit: 10.0
# cuDNN: 7.4.2
# scikit-learn 0.20.2
# Imutils
# NumPy

# set the matplotlib backend so figures can be saved in the background
import matplotlib
from matplotlib import pyplot
import matplotlib.pyplot as plt
# import packages
from sklearn.metrics import classification_report, confusion_matrix, accuracy_score, precision_score, recall_score, \
    f1_score
from sklearn.preprocessing import LabelBinarizer
from pipeline.nn.conv import MiniGoogLeNet
from pipeline.callbacks import TrainingMonitor
from keras.preprocessing.image import ImageDataGenerator
from keras.callbacks import LearningRateScheduler
from keras.optimizers import SGD
from keras.utils.np_utils import to_categorical
import tensorflow as tf
from keras.datasets import cifar10
from image_dataset_loader import load
import numpy as np
import argparse
from sklearn.model_selection import train_test_split
import os
from sklearn.utils.multiclass import unique_labels

# define the total number of epochs to train for along with initial learning rate
NUM_EPOCHS = 50
INIT_LR = 5e-3


def poly_decay(epoch):
    # initialize the maximum number of epochs, base learning rate,
    # and power of the polynomial
    maxEpochs = NUM_EPOCHS
    baseLR = INIT_LR
    power = 1.0

    # compute the new learning rate based on polynomial decay
    alpha = baseLR * (1 - (epoch / float(maxEpochs))) ** power

    # return the new learning rate
    return alpha


# construct the argument parser
ap = argparse.ArgumentParser()
ap.add_argument("-m", "--model", required=True, help="path to output model")
ap.add_argument("-o", "--output", required=True,
                help="path to output directory (logs, plots, etc.)")
args = vars(ap.parse_args())

# load the training and testing data, converting the image from integers to
print("[INFO] loading FERET Dataset...")

# Josh Plan 1
path = "C:/Users/JoshG/PycharmProjects/Local-Binary-Patterns/Images_FERET/Plan1-DL/Images_AlexNet"
imgPath = "C:/Users/JoshG/PycharmProjects/Local-Binary-Patterns/Images_FERET/Plan1-DL/Images_AlexNet/Josh_Training_ADT_8I_24S_227"
testPath = "C:/Users/JoshG/PycharmProjects/Local-Binary-Patterns/Images_FERET/Plan1-DL/Images_AlexNet/Josh_Testing_ADT_24S_227"

# Keras library for CIFAR dataset
# from keras.datasets import cifar10
(trainX, trainY), (testX, testY) = load(path, [imgPath, testPath])

# ((trainX, trainY), (testX, testY)) = cifar10.load_data()
# Dimension of the datasets
#(trainX, trainY), (testX, testY) = load(path, [imgPath, testPath])
print('Train: X = %s, Y= %s' % (trainX.shape, trainY.shape))
print('Test: X = %s, y= %s' % (testX.shape, testY.shape))

# plot first few images
for i in range(9):
    # define subplot
    pyplot.subplot(330   1   i)
    # plot raw pixel datapython.exe googlenet_cifar10.py --model output/minigooglenet_cifar10.hdf5 --output output
    pyplot.imshow(trainX[i])
# show the figure
pyplot.show()

# Print out first test to make sure we can see images
trainX = trainX.astype("float")
testX = testX.astype("float")

# apply mean subtraction to the data
mean = np.mean(trainX, axis=0)
trainX -= mean
testX -= mean

print('------------------- Test 1 -----------------------------')
print('')

temp = []
for label in trainY:
    temp.append([label])
trainY = np.array(temp)
print('-------------------------4')
#print(trainY)
temp = []
for label in testY:
    temp.append([label])
testY = np.array(temp)
print('-------------------------5')
#print(testY)

# Train-validation-test split
trainX, x_val, trainY, y_val = train_test_split(trainX, trainY, test_size=.12)

# Since we have 10 classes we should expect the shape[1] of trainY,y_val and testY to change from 1 to 10
trainY = to_categorical(trainY)
y_val = to_categorical(y_val)
testY = to_categorical(testY)

# Verifying the dimension after one hot encoding
print((trainX.shape, trainY.shape))
print((x_val.shape, y_val.shape))
print((testX.shape, testY.shape))

# Image Data Augmentation
train_generator = ImageDataGenerator(rotation_range=2, horizontal_flip=True, zoom_range=.1)
val_generator = ImageDataGenerator(rotation_range=2, horizontal_flip=True, zoom_range=.1)
test_generator = ImageDataGenerator(rotation_range=2, horizontal_flip=True, zoom_range=.1)

# Fitting the augmentation defined above to the data
train_generator.fit(trainX)
val_generator.fit(x_val)
test_generator.fit(testX)

# construct the image generator for data augmentation
aug = ImageDataGenerator(width_shift_range=0.1, height_shift_range=0.1,
                         horizontal_flip=True, fill_mode="nearest")

# construct the set of callbacks
figPath = os.path.sep.join([args["output"], "{}.png".format(os.getpid())])
jsonPath = os.path.sep.join([args["output"], "{}.json".format(os.getpid())])
callbacks = [TrainingMonitor(figPath, jsonPath=jsonPath),
             LearningRateScheduler(poly_decay)]

# initialize the optimizer and model
print("[INFO] compiling model...")
opt = SGD(lr=INIT_LR, momentum=0.9)
model = MiniGoogLeNet.build(width=227, height=227, depth=3, classes=24)
model.compile(loss="categorical_crossentropy", optimizer=opt, metrics=["accuracy"])
model.evaluate(testX, testY)


# train the network
print("[INFO] training network...")
model.fit_generator(aug.flow(trainX, trainY, batch_size=8),
                    validation_data=(testX, testY), steps_per_epoch=len(trainX) // 64,
                    epochs=NUM_EPOCHS, callbacks=callbacks, verbose=1)

# Plotting the training and validation loss
f, ax = plt.subplots(1, 1)  # Creates 2 subplots under 1 column

# Assigning the first subplot to graph training loss and validation loss
ax.plot(model.history.history['loss'], color='b', label='Training Loss')
ax.plot(model.history.history['val_loss'], color='r', label='Validation Loss')
plt.legend()
plt.show()
f, ax = plt.subplots(1, 1)  # Creates 2 subplots under 1 column

# Plotting the training accuracy and validation accuracy
ax.plot(model.history.history['accuracy'], color='b', label='Training Accuracy')
ax.plot(model.history.history['val_accuracy'], color='r', label='Validation Accuracy')
plt.legend()
plt.show()


# Defining function for confusion matrix plot
def plot_confusion_matrix(y_true, y_pred, classes,
                          normalize=False,
                          title=None,
                          cmap=plt.cm.Blues):
    if not title:
        if normalize:
            title = 'Normalized confusion matrix'
        else:
            title = 'Confusion matrix, without normalization'

    # Compute confusion matrix
    cm = confusion_matrix(y_true, y_pred)
    if normalize:
        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
        print("Normalized confusion matrix")
    else:
        print('Confusion matrix, without normalization')

    # Print Confusion matrix
    fig, ax = plt.subplots(figsize=(4, 4))
    im = ax.imshow(cm, interpolation='nearest', cmap=cmap)
    ax.figure.colorbar(im, ax=ax)
    # We want to show all ticks...
    ax.set(xticks=np.arange(cm.shape[1]),
           yticks=np.arange(cm.shape[0]),
           xticklabels=classes, yticklabels=classes,
           title=title,
           ylabel='True label',
           xlabel='Predicted label')

    # Rotate the tick labels and set their alignment.
    plt.setp(ax.get_xticklabels(), rotation=45, ha="right",
             rotation_mode="anchor")
    # Loop over data dimensions and create text annotations.
    fmt = '.2f' if normalize else 'd'
    thresh = cm.max() / 2.
    for i in range(cm.shape[0]):
        for j in range(cm.shape[1]):
            ax.text(j, i, format(cm[i, j], fmt),
                    ha="center", color="white"
                if cm[i, j] > thresh else "black")
    plt.tight_layout()
    return ax

# Making prediction
y_pred = (model.predict_classes(testX))
y_true = np.argmax(testY, axis=1)
print(y_pred)
print(y_pred.shape)

# Plotting the confusion matrix
confusion_mtx = confusion_matrix(y_true, y_pred)

CLASS_NAMES = [f.name for f in os.scandir(imgPath) if f.is_dir()]
class_names = CLASS_NAMES
print(class_names)

print("ypred\n", y_pred)
print("ytrue", y_true)

# Plotting non-normalized confusion matrix
plot_confusion_matrix(y_true, y_pred, classes=class_names, title='Confusion matrix, without normalization')
plt.show()
# Plotting normalized confusion matrix
# plot_confusion_matrix(y_true, y_pred, classes=class_names, normalize=True, title='Normalized confusion matrix')
# plt.show()

# Classification Metrics
acc_score = accuracy_score(y_true, y_pred)
print('\n\n\t\t  Accuracy Score: ', str(round((100 * acc_score), 2)), '%')
prec_score = precision_score(y_true, y_pred, average='macro')
print('   Precision Score Macro: ', str(round((100 * prec_score), 2)), '%')
prec_score = precision_score(y_true, y_pred, average='micro')
print('   Precision Score Micro: ', str(round((100 * prec_score), 2)), '%')
prec_score = precision_score(y_true, y_pred, average='weighted')
print('Precision Score Weighted: ', str(round((100 * prec_score), 2)), '%')
rec_score = recall_score(y_true, y_pred, average='macro')
print('\t\t\tRecall Macro: ', str(round((100 * rec_score), 2)), '%')
rec_score = recall_score(y_true, y_pred, average='micro')
print('\t\t\tRecall Micro: ', str(round((100 * rec_score), 2)), '%')
rec_score = recall_score(y_true, y_pred, average='weighted')
print('\t\t Recall Weighted: ', str(round((100 * rec_score), 2)), '%')
f_score = f1_score(y_true, y_pred, average='macro')
print('\t\t  F1 Score Macro: ', str(round((100 * f_score), 2)), '%')
f_score = f1_score(y_true, y_pred, average='micro')
print('\t\t  F1 Score Micro: ', str(round((100 * f_score), 2)), '%')
f_score = f1_score(y_true, y_pred, average='weighted')
print('\t   F1 Score Weighted: ', str(round((100 * f_score), 2)), '%')

# Run Command: python.exe GoogLeNet5.py --model output/minigooglenet_cifar10.hdf5 --output output

CodePudding user response：

I was able to fix my issue by making the following changes.

From:

# Making prediction
y_pred = (model.predict_classes(testX))
y_true = np.argmax(testY, axis=1)
print(y_pred)
print(y_pred.shape)

To:

# Making prediction
testX_arg = np.argmax(testY, axis=1)
y_pred = np.argmax(model.predict(testX), axis=1)
y_true = np.argmax(testY, axis=1)
print(y_pred)
print(y_pred.shape)