NumPy arrays and TensorFlow Tensors的區別和聯系
1，tensor的特點
- Tensors can be backed by accelerator memory (like GPU, TPU).
- Tensors are immutable
2，雙向轉換
- TensorFlow operations automatically convert NumPy ndarrays to Tensors.
- NumPy operations automatically convert Tensors to NumPy ndarrays
3，轉換的代價
Tensors can be explicitly converted to NumPy ndarrays by invoking the .numpy()
4，使用tensor時如何測定和選擇gpu
x = tf.random_uniform([3, 3])
print("Is there a GPU available: "),
print(tf.test.is_gpu_available())
print("Is the Tensor on GPU #0: "),
print(x.device.endswith(‘GPU:0‘))
print(tf.test.is_built_with_cuda())
5，顯式指定運行的xpu
import time
def time_matmul(x):
start = time.time()
tf.matmul(x, x)
result = time.time()-start
print("10 loops: {:0.2f}ms".format(1000*result))
# Force execution on CPU
print("On CPU:")
with tf.device("CPU:0"):
x = tf.random_uniform([900, 900])
assert x.device.endswith("CPU:0")
time_matmul(x)
# Force execution on GPU #0 if available
if tf.test.is_gpu_available():
with tf.device("GPU:0"): # Or GPU:1 for the 2nd GPU, GPU:2 for the 3rd etc.
x = tf.random_uniform([1000, 1000])
assert x.device.endswith("GPU:0")
time_matmul(x)
NumPy arrays and TensorFlow Tensors的區別和聯系