কেরাস ব্যবহার করে কীভাবে পাইথনে একটি চিত্র শ্রেণিবদ্ধ করা যায়

pip3 install keras numpy matplotlib tensorflow

from keras.datasets import cifar10 # importing the dataset from keras
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.callbacks import ModelCheckpoint, TensorBoard
from keras.utils import to_categorical
import os

হাইপার পরামিতি

# hyper-parameters
batch_size = 64
# 10 categories of images (CIFAR-10)
num_classes = 10
# number of training epochs
epochs = 30

সিআইএফএআর -10 ডেটাসেট বোঝা এবং লোড হচ্ছে

• ডেটাসেটে 10 টি শ্রেণির চিত্র রয়েছে যা এর লেবেলগুলি 0 থেকে 9 অবধি:
  • 0 : বিমান।
  • 1 : অটোমোবাইল।
  • 2 : পাখি।
  • 3 : বিড়াল।
  • 4 : হরিণ।
  • 5 : কুকুর।
  • 6 : ব্যাঙ
  • 7 : ঘোড়া।
  • 8 : জাহাজ
  • 9 : ট্রাক।
• প্রশিক্ষণের ডেটার জন্য 50000 নমুনা এবং ডেটা পরীক্ষার জন্য 10000 নমুনা।
• প্রতিটি নমুনা 32x32x3 পিক্সেলের একটি চিত্র (প্রস্থ এবং 32 এবং 3 গভীরতার উচ্চতা যা আরজিবি মান।

def load_data():
    """This function loads CIFAR-10 dataset, normalized, and labels one-hot encoded"""
    # loading the CIFAR-10 dataset, splitted between train and test sets
    (X_train, y_train), (X_test, y_test) = cifar10.load_data()
    print("Training samples:", X_train.shape[0])
    print("Testing samples:", X_test.shape[0])
    print(f"Images shape: {X_train.shape[1:]}")
    # converting image labels to binary class matrices
    y_train = to_categorical(y_train, num_classes)
    y_test = to_categorical(y_test, num_classes)
    # convert to floats instead of int, so we can divide by 255
    X_train = X_train.astype("float32")
    X_test = X_test.astype("float32")
    X_train /= 255
    X_test /= 255
    return (X_train, y_train), (X_test, y_test)

• To_categorical ফাংশনটি ব্যবহার করে একটি-হট এনকোড লেবেল : এই প্রক্রিয়াটি সত্যই গুরুত্বপূর্ণ কারণ এটি লেবেলগুলিকে 10 সংখ্যার ভেক্টর হিসাবে সক্ষম করে তাই এটি নিউরাল নেটওয়ার্কের জন্য উপযুক্ত for উদাহরণস্বরূপ, 7 টির মান সহ একটি ঘোড়া এটিকে এনকোড করা হবে: [0, 0, 0, 0, 0, 0, 0, 1, 0, 0] ।
• চিত্রগুলিকে সাধারণীকরণ করা: যেহেতু নিউরাল নেটওয়ার্কগুলি প্রশিক্ষণের জন্য 0 থেকে 255 পিক্সেলের সংখ্যাগুলি খুব বড়, তাই আমরা এই পিক্সেলগুলিকে 0 থেকে 1 এর মধ্যে রাখতে স্বাভাবিক করব।

মডেল নির্মাণ

def create_model(input_shape):
    # building the model
    model = Sequential()
    model.add(Conv2D(filters=32, kernel_size=(3, 3), padding="same", input_shape=input_shape))
    model.add(Activation("relu"))
    model.add(Conv2D(filters=32, kernel_size=(3, 3), padding="same"))
    model.add(Activation("relu"))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.25))
    model.add(Conv2D(filters=64, kernel_size=(3, 3), padding="same"))
    model.add(Activation("relu"))
    model.add(Conv2D(filters=64, kernel_size=(3, 3), padding="same"))
    model.add(Activation("relu"))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.25))
    model.add(Conv2D(filters=128, kernel_size=(3, 3), padding="same"))
    model.add(Activation("relu"))
    model.add(Conv2D(filters=128, kernel_size=(3, 3), padding="same"))
    model.add(Activation("relu"))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.25))
    # flattening the convolutions
    model.add(Flatten())
    # fully-connected layer
    model.add(Dense(1024))
    model.add(Activation("relu"))
    model.add(Dropout(0.5))
    model.add(Dense(num_classes, activation="softmax"))
    # print the summary of the model architecture
    model.summary()
    # training the model using rmsprop optimizer
    model.compile(loss="categorical_crossentropy", optimizer="adam", metrics=["accuracy"])
    return model

মডেল প্রশিক্ষণ

if __name__ == "__main__":
    # load the data
    (X_train, y_train), (X_test, y_test) = load_data()
    # constructs the model
    model = create_model(input_shape=X_train.shape[1:])
    # some nice callbacks
    tensorboard = TensorBoard(log_dir="logs/cifar10-model-v1")
    checkpoint = ModelCheckpoint("results/cifar10-loss-{val_loss:.2f}-acc-{val_acc:.2f}.h5",
                                save_best_only=True,
                                verbose=1)
    # make sure results folder exist
    if not os.path.isdir("results"):
        os.mkdir("results")
    # train
    model.fit(X_train, y_train,
            batch_size=batch_size,
            epochs=epochs,
            validation_data=(X_test, y_test),
            callbacks=[tensorboard, checkpoint],
            shuffle=True)

Epoch 1/30
50000/50000 [==============================] - 26s 520us/step - loss: 1.6408 - acc: 0.3937 - val_loss: 1.2063 - val_acc: 0.5559

Epoch 00001: val_loss improved from inf to 1.20628, saving model to results/cifar10-loss-1.21-acc-0.56.h5
Epoch 2/30
50000/50000 [==============================] - 26s 525us/step - loss: 1.1885 - acc: 0.5716 - val_loss: 0.9982 - val_acc: 0.6473

Epoch 29/30
50000/50000 [==============================] - 27s 534us/step - loss: 0.4225 - acc: 0.8539 - val_loss: 0.5863 - val_acc: 0.8093

Epoch 00029: val_loss did not improve from 0.56407
Epoch 30/30
50000/50000 [==============================] - 27s 549us/step - loss: 0.4205 - acc: 0.8517 - val_loss: 0.5782 - val_acc: 0.8154

Epoch 00030: val_loss did not improve from 0.56407

tensorboard --logdir="logs"

মডেল পরীক্ষা করা হচ্ছে

from train import load_data
from keras.models import load_model
import matplotlib.pyplot as plt
import numpy as np

# CIFAR-10 classes
categories = {
    0: "airplane",
    1: "automobile",
    2: "bird",
    3: "cat",
    4: "deer",
    5: "dog",
    6: "frog",
    7: "horse",
    8: "ship",
    9: "truck"
}

# load the testing set
(_, _), (X_test, y_test) = load_data()
# load the model with optimal weights
model = load_model("results/cifar10-loss-0.58-acc-0.81.h5")

# evaluation
loss, accuracy = model.evaluate(X_test, y_test)
print("Test accuracy:", accuracy*100, "%")

# get prediction for this image
sample_image = X_test[7500]
prediction = np.argmax(model.predict(sample_image.reshape(-1, *sample_image.shape))[0])
print(categories[prediction])

10000/10000 [==============================] - 3s 331us/step
Test accuracy: 81.17999999999999 %
frog

# show the image
plt.axis('off')
plt.imshow(sample_image)
plt.show()

উপসংহার

Code for How to Make an Image Classifier in Python using Keras

from keras.datasets import cifar10 # importing the dataset from keras
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.callbacks import ModelCheckpoint, TensorBoard
from keras.utils import to_categorical
import os

# hyper-parameters
batch_size = 64
# 10 categories of images (CIFAR-10)
num_classes = 10
# number of training epochs
epochs = 30

def create_model(input_shape):

    # building the model
    model = Sequential()

    model.add(Conv2D(filters=32, kernel_size=(3, 3), padding="same", input_shape=input_shape))
    model.add(Activation("relu"))
    model.add(Conv2D(filters=32, kernel_size=(3, 3), padding="same"))
    model.add(Activation("relu"))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.25))

    model.add(Conv2D(filters=64, kernel_size=(3, 3), padding="same"))
    model.add(Activation("relu"))
    model.add(Conv2D(filters=64, kernel_size=(3, 3), padding="same"))
    model.add(Activation("relu"))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.25))

    model.add(Conv2D(filters=128, kernel_size=(3, 3), padding="same"))
    model.add(Activation("relu"))
    model.add(Conv2D(filters=128, kernel_size=(3, 3), padding="same"))
    model.add(Activation("relu"))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.25))

    # flattening the convolutions
    model.add(Flatten())
    # fully-connected layers
    model.add(Dense(1024))
    model.add(Activation("relu"))
    model.add(Dropout(0.5))
    model.add(Dense(num_classes, activation="softmax"))

    # print the summary of the model architecture
    model.summary()

    # training the model using rmsprop optimizer
    model.compile(loss="categorical_crossentropy", optimizer="adam", metrics=["accuracy"])
    return model


def load_data():
    """
    This function loads CIFAR-10 dataset, normalized, and labels one-hot encoded
    """
    # loading the CIFAR-10 dataset, splitted between train and test sets
    (X_train, y_train), (X_test, y_test) = cifar10.load_data()
    print("Training samples:", X_train.shape[0])
    print("Testing samples:", X_test.shape[0])
    print(f"Images shape: {X_train.shape[1:]}")

    # converting image labels to binary class matrices
    y_train = to_categorical(y_train, num_classes)
    y_test = to_categorical(y_test, num_classes)

    # convert to floats instead of int, so we can divide by 255
    X_train = X_train.astype("float32")
    X_test = X_test.astype("float32")
    X_train /= 255
    X_test /= 255

    return (X_train, y_train), (X_test, y_test)


if __name__ == "__main__":

    # load the data
    (X_train, y_train), (X_test, y_test) = load_data()

    # constructs the model
    model = create_model(input_shape=X_train.shape[1:])

    # some nice callbacks
    tensorboard = TensorBoard(log_dir="logs/cifar10-model-v1")
    checkpoint = ModelCheckpoint("results/cifar10-loss-{val_loss:.2f}-acc-{val_acc:.2f}.h5",
                                save_best_only=True,
                                verbose=1)

    # make sure results folder exist
    if not os.path.isdir("results"):
        os.mkdir("results")

    # train
    model.fit(X_train, y_train,
            batch_size=batch_size,
            epochs=epochs,
            validation_data=(X_test, y_test),
            callbacks=[tensorboard, checkpoint],
            shuffle=True)

from train import load_data
from keras.models import load_model
import matplotlib.pyplot as plt
import numpy as np

# CIFAR-10 classes
categories = {
    0: "airplane",
    1: "automobile",
    2: "bird",
    3: "cat",
    4: "deer",
    5: "dog",
    6: "frog",
    7: "horse",
    8: "ship",
    9: "truck"
}

# load the testing set
(_, _), (X_test, y_test) = load_data()
# load the model with optimal weights
model = load_model("results/cifar10-loss-0.58-acc-0.81.h5")
# evaluation
loss, accuracy = model.evaluate(X_test, y_test)
print("Test accuracy:", accuracy*100, "%")

# get prediction for this image
sample_image = X_test[7500]
prediction = np.argmax(model.predict(sample_image.reshape(-1, *sample_image.shape))[0])
print(categories[prediction])

# show the first image
plt.axis('off')
plt.imshow(sample_image)
plt.savefig("frog.png")
plt.show()