8382_Ershov_Mikhail_lb4

8382/Ershov/lb/4/main.py

@@ -0,0 +1,59 @@
+import tensorflow as tf
+import matplotlib.pyplot as plt
+from tensorflow.keras.utils import to_categorical
+from tensorflow.keras.layers import Dense, Flatten
+from tensorflow.keras.models import Sequential
+import numpy as np
+from PIL import Image
+from tensorflow.keras import optimizers
+from tensorflow.keras.preprocessing.image import load_img
+from tensorflow.keras.preprocessing.image import img_to_array
+
+
+mnist = tf.keras.datasets.mnist
+
+(train_images, train_labels), (test_images, test_labels) = mnist.load_data()
+
+train_images = train_images / 255.0
+test_images = test_images / 255.0
+train_labels = to_categorical(train_labels)
+test_labels = to_categorical(test_labels)
+
+def build_model():
+    model = Sequential()
+    model.add(Flatten())
+    model.add(Dense(256, activation='relu'))
+    model.add(Dense(10, activation='softmax'))
+
+    return model
+
+def get_image(filename):
+    img = load_img(filename, color_mode='grayscale', target_size=(28, 28))
+    img = img_to_array(img)
+    img = img.reshape(1, 28, 28, 1)
+    img = img.astype('float32') / 255.0
+    return img
+
+model = build_model()
+model.compile(optimizer=optimizers.Adam(learning_rate=0.1),loss='categorical_crossentropy', metrics=['accuracy'])
+history = model.fit(train_images, train_labels, epochs=5, batch_size=128, validation_data=(test_images, test_labels))
+
+plt.title('Training and test accuracy Adam 0.1')
+plt.plot(history.history['accuracy'], 'r', label='Training acc')
+plt.plot(history.history['val_accuracy'], 'b', label='Validation acc')
+plt.xlabel('Epochs')
+plt.ylabel('Accuracy')
+plt.legend()
+#plt.show()
+
+plt.plot(history.history['loss'], 'r', label='Training loss')
+plt.plot(history.history['val_loss'], 'b', label='Validation loss')
+plt.title('Training and validation accuracy Adam 0.1')
+plt.xlabel('Epochs')
+plt.ylabel('Loss')
+plt.legend()
+#plt.show()
+
+img = get_image("8.png")
+digit = np.argmax(model.predict(img), axis=-1)
+print(digit[0])