def load_extract_dataset(size, samples):
dataset_path = "/home/shouki/Desktop/Programming/Python/AI/Datasets/ImageData/ISSM/Extracted"
if os.path.exists(
os.path.join(dataset_path,
"extracted_{}_{}_vgg16.pkl".format(samples,
size))) == False:
x_train, _ = load_regulized_train_dataset(samples, size)
prepare_extract_dataset(x_train, size, samples)
with open(
os.path.join(dataset_path,
"extracted_{}_{}_vgg16.pkl".format(samples, size)),
"rb") as f:
x_train = pickle.load(f)
return x_train
from unbalance import load_regulized_train_dataset
import numpy as np
import matplotlib.pyplot as plt
x_trian, y_train = load_regulized_train_dataset(1000)
unique, count = np.unique(y_train, return_counts=True)
plt.bar(unique, count)
plt.xlabel("Labels")
plt.ylabel("Label Count")
plt.title("ISSM Dataset Labels")
plt.savefig("./issm_regulized_label.png")
from keras.preprocessing.image import ImageDataGenerator
import numpy as np
import pickle
import tensorflow as tf
from sklearn.model_selection import train_test_split
physical_devices = tf.config.experimental.list_physical_devices("GPU")
tf.config.experimental.set_memory_growth(physical_devices[0], True)
batch_size = 64
epochs = 200
samples = 20000
size = 64
input_size = (size, size, 3)
x_train, y_train = load_regulized_train_dataset(samples, size)
y_train = to_categorical(y_train)
x_train, x_validation, y_train, y_validation = train_test_split(
x_train, y_train, test_size=0.2, stratify=y_train)
model = cnn_model(input_size)
callbacks = [
ModelCheckpoint(filepath="./models/model_{epoch:02d}.h5"),
TensorBoard(log_dir="./logs")
]
model_history = model.fit(x_train,
y_train,
epochs=epochs,
callbacks=callbacks,
