 在 TensorFlow.org 上檢視
|
 在 Google Colab 中執行
|
 在 GitHub 上檢視原始碼
|
 下載筆記本
|
這是 Google Colaboratory 筆記本檔案。Python 程式直接在瀏覽器中執行，是學習和使用 TensorFlow 的絕佳方式。如要按照本教學課程操作，請按一下本頁頂端的按鈕，在 Google Colab 中執行筆記本。
- 在 Colab 中，連線至 Python 執行階段：在選單列的右上角，選取「連線」。
- 執行所有筆記本程式碼儲存格：選取「執行階段」>「全部執行」。
下載並安裝 TensorFlow 2。將 TensorFlow 匯入您的程式
將 TensorFlow 匯入您的程式
import tensorflow as tf
print("TensorFlow version:", tf.__version__)
from tensorflow.keras.layers import Dense, Flatten, Conv2D
from tensorflow.keras import Model
2024-07-13 06:54:42.012604: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:479] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2024-07-13 06:54:42.038839: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:10575] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2024-07-13 06:54:42.038874: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1442] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered TensorFlow version: 2.16.2
載入並準備 MNIST 資料集。
mnist = tf.keras.datasets.mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0
# Add a channels dimension
x_train = x_train[..., tf.newaxis].astype("float32")
x_test = x_test[..., tf.newaxis].astype("float32")
使用 tf.data 批次處理並隨機排序資料集
train_ds = tf.data.Dataset.from_tensor_slices(
(x_train, y_train)).shuffle(10000).batch(32)
test_ds = tf.data.Dataset.from_tensor_slices((x_test, y_test)).batch(32)
使用 Keras 模型子類別化 API，建構 tf.keras 模型
class MyModel(Model):
def __init__(self):
super().__init__()
self.conv1 = Conv2D(32, 3, activation='relu')
self.flatten = Flatten()
self.d1 = Dense(128, activation='relu')
self.d2 = Dense(10)
def call(self, x):
x = self.conv1(x)
x = self.flatten(x)
x = self.d1(x)
return self.d2(x)
# Create an instance of the model
model = MyModel()
為訓練選擇最佳化工具和損失函數
loss_object = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)
optimizer = tf.keras.optimizers.Adam()
選取指標來衡量模型的損失和準確度。這些指標會累計各個週期 (epoch) 的值，然後印出整體結果。
train_loss = tf.keras.metrics.Mean(name='train_loss')
train_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='train_accuracy')
test_loss = tf.keras.metrics.Mean(name='test_loss')
test_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='test_accuracy')
使用 tf.GradientTape 訓練模型
@tf.function
def train_step(images, labels):
with tf.GradientTape() as tape:
# training=True is only needed if there are layers with different
# behavior during training versus inference (e.g. Dropout).
predictions = model(images, training=True)
loss = loss_object(labels, predictions)
gradients = tape.gradient(loss, model.trainable_variables)
optimizer.apply_gradients(zip(gradients, model.trainable_variables))
train_loss(loss)
train_accuracy(labels, predictions)
測試模型
@tf.function
def test_step(images, labels):
# training=False is only needed if there are layers with different
# behavior during training versus inference (e.g. Dropout).
predictions = model(images, training=False)
t_loss = loss_object(labels, predictions)
test_loss(t_loss)
test_accuracy(labels, predictions)
EPOCHS = 5
for epoch in range(EPOCHS):
# Reset the metrics at the start of the next epoch
train_loss.reset_state()
train_accuracy.reset_state()
test_loss.reset_state()
test_accuracy.reset_state()
for images, labels in train_ds:
train_step(images, labels)
for test_images, test_labels in test_ds:
test_step(test_images, test_labels)
print(
f'Epoch {epoch + 1}, '
f'Loss: {train_loss.result():0.2f}, '
f'Accuracy: {train_accuracy.result() * 100:0.2f}, '
f'Test Loss: {test_loss.result():0.2f}, '
f'Test Accuracy: {test_accuracy.result() * 100:0.2f}'
)
2024-07-13 06:54:53.279724: W tensorflow/core/framework/local_rendezvous.cc:404] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence 2024-07-13 06:54:53.895273: W tensorflow/core/framework/local_rendezvous.cc:404] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence Epoch 1, Loss: 0.13, Accuracy: 96.00, Test Loss: 0.06, Test Accuracy: 97.85 2024-07-13 06:54:58.213183: W tensorflow/core/framework/local_rendezvous.cc:404] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence 2024-07-13 06:54:58.613194: W tensorflow/core/framework/local_rendezvous.cc:404] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence Epoch 2, Loss: 0.04, Accuracy: 98.70, Test Loss: 0.05, Test Accuracy: 98.36 2024-07-13 06:55:03.021925: W tensorflow/core/framework/local_rendezvous.cc:404] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence 2024-07-13 06:55:03.409904: W tensorflow/core/framework/local_rendezvous.cc:404] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence Epoch 3, Loss: 0.02, Accuracy: 99.30, Test Loss: 0.06, Test Accuracy: 98.23 2024-07-13 06:55:07.799603: W tensorflow/core/framework/local_rendezvous.cc:404] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence 2024-07-13 06:55:08.205513: W tensorflow/core/framework/local_rendezvous.cc:404] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence Epoch 4, Loss: 0.01, Accuracy: 99.55, Test Loss: 0.06, Test Accuracy: 98.14 2024-07-13 06:55:12.538723: W tensorflow/core/framework/local_rendezvous.cc:404] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence Epoch 5, Loss: 0.01, Accuracy: 99.74, Test Loss: 0.07, Test Accuracy: 98.26 2024-07-13 06:55:12.943937: W tensorflow/core/framework/local_rendezvous.cc:404] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence
圖片分類器現已完成訓練，在此資料集上的準確度約為 98%。如要進一步瞭解，請參閱 TensorFlow 教學課程。