def main():
IMG_SIZE = (80, 80)
channels = 1
char_path = r'../input/the-simpsons-characters-dataset/simpsons_dataset'
char_dict = {}
for char in os.listdir(char_path):
char_dict[char] = len(os.listdir(os.path.join(char_path, char)))
# Sort in descending order
char_dict = caer.sort_dict(char_dict, descending=True)
# Get top 10 characters
characters = []
count = 0
for i in char_dict:
characters.append(i[0])
count += 1
if count >= 10:
break
# Create the training data
train = caer.preprocess_from_dir(char_path,
characters,
channels=channels,
IMG_SIZE=IMG_SIZE,
isShuffle=True)
# Separate feature set and labels
featureSet, labels = caer.sep_train(train, IMG_SIZE=IMG_SIZE)
# Normalize the featureSet in (0, 1)
featureSet = caer.normalize(featureSet)
labels = to_categorical(labels, len(characters))
x_train, x_test, y_train, y_test = caer.train_val_split(featureSet,
labels,
val_ratio=0.2)
del train
del featureSet
del labels
gc.collect()
BATCH_SIZE = 32
EPOCHS = 10
# Create new data generator
data_gen = canaro.generators.imageDataGenerator()
train_gen = data_gen.flow(np.array(x_train),
np.array(y_train),
batch_size=BATCH_SIZE)
# Create a model
model = canaro.models.createSimpsonsModel(IMG_SIZE=IMG_SIZE,
channels=channels,
output_dim=len(characters),
loss='binary_crossentropy',
decay=1e-6,
learning_rate=0.001,
momentum=0.9,
nesterov=True)
callbacks_list = [LearningRateScheduler(canaro.lr_schedule)]
training = model.fit(train_gen,
steps_per_epoch=len(x_train) // BATCH_SIZE,
epochs=EPOCHS,
validation_data=(np.array(x_test), np.array(y_test)),
validation_steps=len(y_test) // BATCH_SIZE,
callbacks=callbacks_list)
test_path = r'../input/the-simpsons-characters-dataset/kaggle_simpson_testset/kaggle_simpson_testset/charles_montgomery_burns_0.jpg'
img = cv2.imread(test_path)
predictions = model.predict(prepare(img))
print(characters[np.argmax(predictions[0])])
# Sort in descending order
char_dict = caer.sort_dict(char_dict, descending=True)
char_dict
# Getting the first 10 categories with the most number of images
characters = []
count = 0
for i in char_dict:
characters.append(i[0])
count += 1
if count >= 10:
break
characters
# Create the training data
train = caer.preprocess_from_dir(char_path, characters, channels=channels, IMG_SIZE=IMG_SIZE, isShuffle=True)
# Number of training samples
len(train)
# Visualizing the data (OpenCV doesn't display well in Jupyter notebooks)
plt.figure(figsize=(30,30))
plt.imshow(train[0][0], cmap='gray')
plt.show()
# Separating the array and corresponding labels
featureSet, labels = caer.sep_train(train, IMG_SIZE=IMG_SIZE)
# Normalize the featureSet ==> (0,1)
featureSet = caer.normalize(featureSet)
print(trial_dict)
characters = []
count = 0
for keys in trial_dict:
characters.append(keys[0])
count += 1
if count > 10:
break
print(characters)
# create a training data
train = caer.preprocess_from_dir(DIR=base_path,
classes=characters,
IMG_SIZE=image_size,
channels=channels,
isShuffle=True)
print(f'Number of images used for training: {len(train)}')
# seperate features and labels
features, labels = caer.sep_train(data=train,
IMG_SIZE=image_size,
channels=channels)
# normalize the features and we have to labels from numerical integers to one hot encode
features = caer.normalize(features)
labels = to_categorical(y=labels, num_classes=len(characters))
split_data = skm.train_test_split(features, labels, test_size=.2)
x_train, x_val, y_train, y_val = (np.array(item) for item in split_data)
