Similar presentations:
Deep learning in computer vision. Нейронные сети
1.
Deep learning in computervision
Попов Максим
Synesis, RnD
2. Задача классификации
3.
4.
5. Искусственная нейросеть
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18. Softmax function
19.
20.
21.
22. Пример кода на Keras
Model = keras.Sequential([keras.layers.Flatten(input_shape = (28,28)),
keras.layers.Dense(128, activation = “relu”),
keras.layers.Dense(10, activation = “softmax”)
])
model.compile(optimizer=“sgd”,
loss = “categorical_crossentropy”,
metrics = [“accuracy”])
model.fit(train_images, train_labels, epoch = 10)
predict = model.predict(test_images)