1. tensorflow 3个平台测试

1. 官方测试代码：

import tensorflow as tf
import time

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

model = tf.keras.models.Sequential([
  tf.keras.layers.Flatten(input_shape=(28, 28)),
  tf.keras.layers.Dense(128, activation='relu'),
  tf.keras.layers.Dropout(0.2),
  tf.keras.layers.Dense(10, activation='softmax')
])

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


start = time.time()

model.fit(x_train, y_train, epochs=5)

end = time.time()

model.evaluate(x_test, y_test)
print(end - start)

2. 测试平台成绩：
   windows 11:

• cpu: r7-3700x 8 core
• gpu: GTX-1060
• ram: 32GB DDR4-3200Mhz

• tensorflow: v2.3.0
  测试成绩

  
  
  1634743513(1).png

macos 12:

• cpu: M1 8 core
• gpu: M1 7 core gpu
• ram: 8GB

• tensorflow: v2.6.0
  测试成绩：

  
  
  9862d6ec49d310d64446961760b8c07.jpg

树莓派3B+

• cpu: 4 core 1.4Ghz Cortex-A53
• Ram: 1gb ddr2

• tensorflow: v1.14

  
  
  c20526df870bb9acbae223266a7b549.jpg

纯粹娱乐。。。
M1芯片的强势，1060功耗的强大，树莓派的节能。