TensorFlow 基础

snowkylin · April 11, 2020, 2:55pm

TensorFlow 基础

如果程序报错，建议包含以下信息以帮助排除问题：

TensorFlow 版本（请检查 TensorFlow 版本为 2.1）

import tensorflow as tf
print (tf.__version__)

完整的最小可运行程序代码（建议将代码在 IDE 中运行而不是交互式环境）
完整的报错信息（Traceback）

ryan_stark · April 21, 2020, 3:37pm

这里有一个问题，教程中关于均方差损失函数的引用 4 公式前面的系数应该是
1/5 不是 1/2

snowkylin · April 21, 2020, 5:00pm

大概两点：

由于均方误差取均值的系数 1/N 在训练过程中一般为常数（N 一般为批次大小，比如这里是 5），对损失函数乘以常数等价于调整学习率，所以这里为了简化表达式而省略了。可以参考 http://speech.ee.ntu.edu.tw/~tlkagk/courses/ML_2017/Lecture/Regression.pdf
乘以 1/2 其实是为了后面求导方便的一个小技巧，可以参考 https://blog.csdn.net/u012874209/article/details/78131899 ，不过考虑到造成读者疑惑现在就删掉了

David_Lee · April 23, 2020, 9:16am

在自动求导机制中，y 和 y_grad 的输出为什么不是 tensor 呢？

snowkylin · April 23, 2020, 9:32am

不好意思，是没及时更新造成的错误，已修改。

PhysicalElective2 · April 23, 2020, 12:03pm

optimizer = tf.keras.optimizers.SGD (learning_rate=5e-4)
在 tensorflow 的程序示例中 learning_rate 和下文中 “ 在这里，我们使用了前文的方式计算了损失函数关于参数的偏导数。同时，使用 tf.keras.optimizers.SGD (learning_rate=1e-3) 声明了一个梯度下降 优化器 （Optimizer），其学习率为 1e-3。” 的 learning_rate 不一致

David_Lee · April 24, 2020, 7:06am

谢谢大佬，我以为自己的基础没打牢，看来可以自信一点点了，感谢感谢

David_Lee · April 24, 2020, 7:27am

大佬可否介绍一下 pycharm 环境的配置，申请了个 prof 版，环境不太会配置，以前都是用 colab

snowkylin · April 24, 2020, 11:50am

已修正，感谢提醒~

snowkylin · April 24, 2020, 11:53am

PyCharm 的配置应该还是比较亲民的，网上的教程也很多。我在 “IDE 配置” 里也写了一些内容。如果还有问题可以具体提问。

chenglu · April 24, 2020, 12:04pm

IDE 设置的文档链接是：https://tf.wiki/zh/basic/installation.html#ide

David_Lee · April 25, 2020, 3:29am

配置好了，但是每次运行的时候总是出现以下错误代码，是什么原因呢：
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/dtypes.py:516: FutureWarning: Passing (type, 1) or ‘1type’ as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / ‘(1,) type’.
_np_qint8 = np.dtype ([(“qint8”, np.int8, 1)])
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/dtypes.py:517: FutureWarning: Passing (type, 1) or ‘1type’ as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / ‘(1,) type’.
_np_quint8 = np.dtype ([(“quint8”, np.uint8, 1)])
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/dtypes.py:518: FutureWarning: Passing (type, 1) or ‘1type’ as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / ‘(1,) type’.
_np_qint16 = np.dtype ([(“qint16”, np.int16, 1)])
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/dtypes.py:519: FutureWarning: Passing (type, 1) or ‘1type’ as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / ‘(1,) type’.
_np_quint16 = np.dtype ([(“quint16”, np.uint16, 1)])
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/dtypes.py:520: FutureWarning: Passing (type, 1) or ‘1type’ as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / ‘(1,) type’.
_np_qint32 = np.dtype ([(“qint32”, np.int32, 1)])
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or ‘1type’ as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / ‘(1,) type’.
np_resource = np.dtype ([(“resource”, np.ubyte, 1)])
/home/fish/.local/lib/python3.6/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:541: FutureWarning: Passing (type, 1) or ‘1type’ as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / ‘(1,) type’.
_np_qint8 = np.dtype ([(“qint8”, np.int8, 1)])
/home/fish/.local/lib/python3.6/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:542: FutureWarning: Passing (type, 1) or ‘1type’ as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / ‘(1,) type’.
_np_quint8 = np.dtype ([(“quint8”, np.uint8, 1)])
/home/fish/.local/lib/python3.6/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:543: FutureWarning: Passing (type, 1) or ‘1type’ as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / ‘(1,) type’.
_np_qint16 = np.dtype ([(“qint16”, np.int16, 1)])
/home/fish/.local/lib/python3.6/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:544: FutureWarning: Passing (type, 1) or ‘1type’ as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / ‘(1,) type’.
_np_quint16 = np.dtype ([(“quint16”, np.uint16, 1)])
/home/fish/.local/lib/python3.6/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:545: FutureWarning: Passing (type, 1) or ‘1type’ as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / ‘(1,) type’.
_np_qint32 = np.dtype ([(“qint32”, np.int32, 1)])
/home/fish/.local/lib/python3.6/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:550: FutureWarning: Passing (type, 1) or ‘1type’ as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / ‘(1,) type’.
np_resource = np.dtype ([(“resource”, np.ubyte, 1)])
2020-04-25 11:25:56.201023: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Could not dlopen library ‘libcuda.so.1’; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory
2020-04-25 11:25:56.201044: E tensorflow/stream_executor/cuda/cuda_driver.cc:318] failed call to cuInit: UNKNOWN ERROR (303)
2020-04-25 11:25:56.201061: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (fish-desktop): /proc/driver/nvidia/version does not exist
2020-04-25 11:25:56.201256: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2020-04-25 11:25:56.235142: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 3591575000 Hz
2020-04-25 11:25:56.235842: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x5ba5910 executing computations on platform Host. Devices:
2020-04-25 11:25:56.235864: I tensorflow/compiler/xla/service/service.cc:175] StreamExecutor device

laili731236225 · April 26, 2020, 7:01am

大佬你好, 我想请问一下我遇到的这个问题怎么解决:

InvalidArgumentError                      Traceback (most recent call last)
<ipython-input-24-dfbd31710005> in <module>
     11 for e in range (num_epoch):
     12     with tf.GradientTape () as tape:
---> 13         y_pred = a * X + b
     14         loss = tf.reduce_sum (tf.square (y - y_pred))
     15     grads = tape.gradient (loss, variables)

InvalidArgumentError: cannot compute Mul as input #1 (zero-based) was expected to be a float tensor but is a double tensor [Op:Mul] name: mul/

看上去像是数据类型的问题, 应该怎么解决呢?

zknyy · April 26, 2020, 8:47am

import tensorflow as tf
X = tf.constant ([[1., 2.], [3., 4.]])
y = tf.constant ([[1.], [2.]])
w = tf.Variable (initial_value=[[1.], [2.]])
b = tf.Variable (initial_value=1.)
with tf.GradientTape () as tape:
    L = tf.reduce_sum (tf.square (tf.matmul (X, w) + b - y))
w_grad, b_grad = tape.gradient (L, [w, b])        # 计算 L (w, b) 关于 w, b 的偏导数
print (L, w_grad, b_grad)

上面这段执行完后报错如下，请赐教如何修改，谢谢。

2020-04-26 16:31:11.896090: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
Traceback (most recent call last):
  File "E:/[RemoteSync]/Shared/PycharmProjects/test/src/03.partial_derivative.py", line 8, in <module>
    L = tf.reduce_sum (tf.square (tf.matmul (X, w) + b - y))
  File "C:\Users\demo\AppData\Local\conda\conda\envs\tf2\lib\site-packages\tensorflow_core\python\util\dispatch.py", line 180, in wrapper
    return target (*args, **kwargs)
  File "C:\Users\demo\AppData\Local\conda\conda\envs\tf2\lib\site-packages\tensorflow_core\python\ops\math_ops.py", line 1595, in reduce_sum
    _ReductionDims (input_tensor, axis))
  File "C:\Users\demo\AppData\Local\conda\conda\envs\tf2\lib\site-packages\tensorflow_core\python\ops\math_ops.py", line 1473, in _ReductionDims
    return constant_op.constant (np.arange (rank, dtype=np.int32))
  File "C:\Users\demo\AppData\Local\conda\conda\envs\tf2\lib\site-packages\tensorflow_core\python\framework\constant_op.py", line 258, in constant
    allow_broadcast=True)
  File "C:\Users\demo\AppData\Local\conda\conda\envs\tf2\lib\site-packages\tensorflow_core\python\framework\constant_op.py", line 266, in _constant_impl
    t = convert_to_eager_tensor (value, ctx, dtype)
  File "C:\Users\demo\AppData\Local\conda\conda\envs\tf2\lib\site-packages\tensorflow_core\python\framework\constant_op.py", line 96, in convert_to_eager_tensor
    return ops.EagerTensor (value, ctx.device_name, dtype)
ValueError: Attempt to convert a value (0) with an unsupported type (<class 'numpy.int32'>) to a Tensor.

Process finished with exit code 1

snowkylin · April 26, 2020, 12:05pm

请检查一下你的X变量的数据类型，如果是float64的话转为float32。

X_raw = np.array ([2013, 2014, 2015, 2016, 2017], dtype=np.float32)
y_raw = np.array ([12000, 14000, 15000, 16500, 17500], dtype=np.float32)

X = (X_raw - X_raw.min ()) / (X_raw.max () - X_raw.min ())
y = (y_raw - y_raw.min ()) / (y_raw.max () - y_raw.min ())

注意代码中的 dtype

snowkylin · April 26, 2020, 12:09pm

请检查你的 TensorFlow 版本是否为 2.1 正式版

import tensorflow as tf
print (tf.__version__)

laili731236225 · April 26, 2020, 2:09pm

感谢回复! 上面的问题确实是数据类型的问题, 已经解决了. 可是在下一条语句又遇到了问题

<ipython-input-9-4a00192d6d84> in <module>
      8 y = tf.constant (y)
      9 
---> 10 a = tf.Variable (initial_value=0.)
     11 b = tf.Variable (initial_value=0.)
     12 variables = [a, b]

InvalidArgumentError: assertion failed: [0] [Op:Assert] name: EagerVariableNameReuse

这里又出现了问题, 能麻烦大佬再帮忙解答一下吗

snowkylin · April 26, 2020, 3:36pm

建议在 IDE 里新开一个.py文件，将要运行的代码写好，然后直接运行代码。在没有上下文的情况下很难确定 ipython 环境里的报错是怎么回事。

snowkylin · April 26, 2020, 3:43pm

这里面并没有真正意义上的异常报错，基本都是提示信息。

Snowden · April 27, 2020, 2:24am

想问问这个 X 和 y 计算出的是什么，没搞懂