关于TensorFlow核心组件全面解读

import tensorflow as tf

# 创建张量
a = tf.constant([[1, 2], [3, 4]])
b = tf.constant([[5, 6], [7, 8]])

# 矩阵乘法
c = tf.matmul(a, b)
print(c)

converter = tf.lite.TFLiteConverter.from_saved_model(saved_model_dir)
tflite_model = converter.convert()

with open('model.tflite', 'wb') as f:
    f.write(tflite_model)

from tensorflow.keras import layers, models

model = models.Sequential([
    layers.Conv2D(32, (3, 3), activation='relu', input_shape=(28, 28, 1)),
    layers.MaxPooling2D((2, 2)),
    layers.Flatten(),
    layers.Dense(10, activation='softmax')
])

model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

import tensorflow_hub as hub

model = tf.keras.Sequential([
    hub.KerasLayer("https://tfhub.dev/google/imagenet/mobilenet_v2_100_224/feature_vector/4",
                   trainable=False),
    tf.keras.layers.Dense(10, activation='softmax')
])

strategy = tf.distribute.MirroredStrategy()

with strategy.scope():
    model = tf.keras.Sequential([
        tf.keras.layers.Dense(10, activation='softmax')
    ])
    model.compile(loss='sparse_categorical_crossentropy', optimizer='adam')

dataset = tf.data.Dataset.from_tensor_slices((x_train, y_train))
dataset = dataset.shuffle(buffer_size=1024).batch(32).prefetch(tf.data.AUTOTUNE)

model.save('saved_model', save_format='tf')

docker run -p 8501:8501 \
    --mount type=bind,source=/path/to/saved_model,target=/models/model \
    -e MODEL_NAME=model -t tensorflow/serving

@tf.function
def custom_op(x):
    return x * x + 2 * x + 1

result = custom_op(tf.constant(3.0))
print(result)