《版本問(wèn)題?。。?！》win10下選擇CUDA版本和Cudnn版本，以及匹配tensorflow和Keras。

ruyue 2024-12-28 疾病百科 1 次瀏覽 0個(gè)評(píng)論

CUDA ToolkitLinux x86_64 Driver VersionWindows x86_64 Driver VersionCUDA 11.1.1 Update 1>=455.32>=456.81CUDA 11.1 GA>=455.23>=456.38CUDA 11.0.3 Update 1>= 450.51.06>= 451.82CUDA 11.0.2 GA>= 450.51.05>= 451.48CUDA 11.0.1 RC>= 450.36.06>= 451.22CUDA 10.2.89>= 440.33>= 441.22CUDA 10.1 (10.1.105 general release, and updates)>= 418.39>= 418.96CUDA 10.0.130>= 410.48>= 411.31CUDA 9.2 (9.2.148 Update 1)>= 396.37>= 398.26CUDA 9.2 (9.2.88)>= 396.26>= 397.44CUDA 9.1 (9.1.85)>= 390.46>= 391.29CUDA 9.0 (9.0.76)>= 384.81>= 385.54CUDA 8.0 (8.0.61 GA2)>= 375.26>= 376.51CUDA 8.0 (8.0.44)>= 367.48>= 369.30CUDA 7.5 (7.5.16)>= 352.31>= 353.66CUDA 7.0 (7.0.28)>= 346.46>= 347.62

版本

ython 版本

編譯器構(gòu)建工具cuDNNCUDAtensorflow_gpu-2.3.03.5-3.8MSVC 2019Bazel 3.1.07.410.1tensorflow_gpu-2.2.03.5-3.8MSVC 2019Bazel 2.0.07.410.1tensorflow_gpu-2.1.03.5-3.7MSVC 2019Bazel 0.27.1-0.29.17.410.1tensorflow_gpu-2.0.03.5-3.7MSVC 2017Bazel 0.26.17.410tensorflow_gpu-1.15.03.5-3.7MSVC 2017Bazel 0.26.17.410tensorflow_gpu-1.14.03.5-3.7MSVC 2017Bazel 0.24.1-0.25.27.410tensorflow_gpu-1.13.03.5-3.7MSVC 2015 update 3Bazel 0.19.0-0.21.07.410tensorflow_gpu-1.12.03.5-3.6MSVC 2015 update 3Bazel 0.15.079tensorflow_gpu-1.11.03.5-3.6MSVC 2015 update 3Bazel 0.15.079tensorflow_gpu-1.10.03.5-3.6MSVC 2015 update 3Cmake v3.6.379tensorflow_gpu-1.9.03.5-3.6MSVC 2015 update 3Cmake v3.6.379tensorflow_gpu-1.8.03.5-3.6MSVC 2015 update 3Cmake v3.6.379tensorflow_gpu-1.7.03.5-3.6MSVC 2015 update 3Cmake v3.6.379tensorflow_gpu-1.6.03.5-3.6MSVC 2015 update 3Cmake v3.6.379tensorflow_gpu-1.5.03.5-3.6MSVC 2015 update 3Cmake v3.6.379tensorflow_gpu-1.4.03.5-3.6MSVC 2015 update 3Cmake v3.6.368tensorflow_gpu-1.3.03.5-3.6MSVC 2015 update 3Cmake v3.6.368tensorflow_gpu-1.2.03.5-3.6MSVC 2015 update 3Cmake v3.6.35.18tensorflow_gpu-1.1.03.5MSVC 2015 update 3Cmake v3.6.35.18tensorflow_gpu-1.0.03.5MSVC 2015 update 3Cmake v3.6.35.18

FrameworkEnv name (--env parameter)DescriptionDocker ImagePackages and Nvidia SettingsTensorFlow 2.2tensorflow-2.2TensorFlow 2.2.0 + Keras 2.3.1 on Python 3.7.floydhub/tensorflowTensorFlow-2.2TensorFlow 2.1tensorflow-2.1TensorFlow 2.1.0 + Keras 2.3.1 on Python 3.6.floydhub/tensorflowTensorFlow-2.1TensorFlow 2.0tensorflow-2.0TensorFlow 2.0.0 + Keras 2.3.1 on Python 3.6.floydhub/tensorflowTensorFlow-2.0TensorFlow 1.15tensorflow-1.15TensorFlow 1.15.0 + Keras 2.3.1 on Python 3.6.floydhub/tensorflowTensorFlow-1.15TensorFlow 1.14tensorflow-1.14TensorFlow 1.14.0 + Keras 2.2.5 on Python 3.6.floydhub/tensorflowTensorFlow-1.14TensorFlow 1.13tensorflow-1.13TensorFlow 1.13.0 + Keras 2.2.4 on Python 3.6.floydhub/tensorflowTensorFlow-1.13TensorFlow 1.12tensorflow-1.12TensorFlow 1.12.0 + Keras 2.2.4 on Python 3.6.floydhub/tensorflowTensorFlow-1.12tensorflow-1.12:py2TensorFlow 1.12.0 + Keras 2.2.4 on Python 2.floydhub/tensorflowTensorFlow 1.11tensorflow-1.11TensorFlow 1.11.0 + Keras 2.2.4 on Python 3.6.floydhub/tensorflowTensorFlow-1.11tensorflow-1.11:py2TensorFlow 1.11.0 + Keras 2.2.4 on Python 2.floydhub/tensorflowTensorFlow 1.10tensorflow-1.10TensorFlow 1.10.0 + Keras 2.2.0 on Python 3.6.floydhub/tensorflowTensorFlow-1.10tensorflow-1.10:py2TensorFlow 1.10.0 + Keras 2.2.0 on Python 2.floydhub/tensorflowTensorFlow 1.9tensorflow-1.9TensorFlow 1.9.0 + Keras 2.2.0 on Python 3.6.floydhub/tensorflowTensorFlow-1.9tensorflow-1.9:py2TensorFlow 1.9.0 + Keras 2.2.0 on Python 2.floydhub/tensorflowTensorFlow 1.8tensorflow-1.8TensorFlow 1.8.0 + Keras 2.1.6 on Python 3.6.floydhub/tensorflowTensorFlow-1.8tensorflow-1.8:py2TensorFlow 1.8.0 + Keras 2.1.6 on Python 2.floydhub/tensorflowTensorFlow 1.7tensorflow-1.7TensorFlow 1.7.0 + Keras 2.1.6 on Python 3.6.floydhub/tensorflowTensorFlow-1.7tensorflow-1.7:py2TensorFlow 1.7.0 + Keras 2.1.6 on Python 2.floydhub/tensorflowTensorFlow 1.5tensorflow-1.5TensorFlow 1.5.0 + Keras 2.1.6 on Python 3.6.floydhub/tensorflowTensorFlow-1.5tensorflow-1.5:py2TensorFlow 1.5.0 + Keras 2.1.6 on Python 2.floydhub/tensorflowTensorFlow 1.4tensorflow-1.4TensorFlow 1.4.0 + Keras 2.0.8 on Python 3.6.floydhub/tensorflowtensorflow-1.4:py2TensorFlow 1.4.0 + Keras 2.0.8 on Python 2.floydhub/tensorflowTensorFlow 1.3tensorflow-1.3TensorFlow 1.3.0 + Keras 2.0.6 on Python 3.6.floydhub/tensorflowtensorflow-1.3:py2TensorFlow 1.3.0 + Keras 2.0.6 on Python 2.floydhub/tensorflowTensorFlow 1.2tensorflow-1.2TensorFlow 1.2.0 + Keras 2.0.6 on Python 3.5.floydhub/tensorflowtensorflow-1.2:py2TensorFlow 1.2.0 + Keras 2.0.6 on Python 2.floydhub/tensorflowTensorFlow 1.1tensorflowTensorFlow 1.1.0 + Keras 2.0.6 on Python 3.5.floydhub/tensorflowtensorflow:py2TensorFlow 1.1.0 + Keras 2.0.6 on Python 2.floydhub/tensorflowTensorFlow 1.0tensorflow-1.0TensorFlow 1.0.0 + Keras 2.0.6 on Python 3.5.floydhub/tensorflowtensorflow-1.0:py2TensorFlow 1.0.0 + Keras 2.0.6 on Python 2.floydhub/tensorflowTensorFlow 0.12tensorflow-0.12TensorFlow 0.12.1 + Keras 1.2.2 on Python 3.5.floydhub/tensorflowtensorflow-0.12:py2TensorFlow 0.12.1 + Keras 1.2.2 on Python 2.floydhub/tensorflow

我們尊重新鮮事物的產(chǎn)生，我們也非常喜歡新鮮事物，新的版本代表著新的功能和新的效果。但是新的并非最好。特別是涉及到版本兼容問(wèn)題時(shí)。

經(jīng)實(shí)際測(cè)試效果，如果裝tensorflow 2以上的版本，會(huì)出現(xiàn)各種問(wèn)題。原因如下：第一句翻譯：TF2.0中很多API要么....要么...。所以呀，為了眼下的方便，不考慮以后的話。先裝TF1.0版本吧。

Many APIs are either gone or moved in TF 2.0. Some of the major changes include removing tf.app, tf.flags, and tf.logging in favor of the now open-source absl-py, rehoming projects that lived in tf.contrib, and?cleaning up the main tf.* namespace?by moving lesser used functions into subpackages like tf.math.

根據(jù)：TF版本，觀察Cuda的版本，我們發(fā)現(xiàn)10.1都對(duì)應(yīng)TF2.0，所以，我們退一步，讓一步，選擇CUDA10.0。這樣讓我們接下來(lái)選擇的空間更大。CUDA10.0讓我們可進(jìn)可退。后續(xù)轉(zhuǎn)TF2.0也支持。

本人筆記本NVIDIA GeForce GTX 1070。選擇CUDA10.0。對(duì)應(yīng)顯卡驅(qū)動(dòng)版本CUDA Toolkit and Compatible Driver Versions>=411.31。只要大于這個(gè)版本都支持。這個(gè)可以放心選擇。CuDnn按照表推薦7.4。

CUDNN7.4限制tensorFlow對(duì)應(yīng)的版本，也限制在了tensorFlow1.13以上的版本?？蛇x項(xiàng)只有13,14,15三個(gè)版本。15在匹配Keras的時(shí)候，需要匹配最新keras，所以我們選擇13或者14。穩(wěn)妥點(diǎn)選擇13。

TensorFlow建議keras2.2.4。這下子所有版本齊了。

考慮Python的版本，你要考慮你的其他使用場(chǎng)景，要讓Python支持更多的場(chǎng)景。目前根據(jù)我的應(yīng)用場(chǎng)景選擇3.6穩(wěn)妥些。因?yàn)槲业男枨笾杏行┠K點(diǎn)明不支持3.5以下版本，有些模塊又不支持太新3.7也不妥。完全是被動(dòng)呀。不過(guò)你看表3.6支持的版本最多呀。欣慰至甚，歡欣甚慰。以此你也可以看出python3.6目前也是Python比較好的一個(gè)版本選擇。

如果安裝anaconda：請(qǐng)參照下圖：

?選擇anaconda 3.5.2合適。

先裝顯卡驅(qū)動(dòng)，后裝CUDA，然后復(fù)制替換CUDNN。

安裝完CUDA后需要配置環(huán)境變量。

檢測(cè)CMD下輸入：nvcc -V
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2018 NVIDIA Corporation
Built on Sat_Aug_25_21:08:04_Central_Daylight_Time_2018
Cuda compilation tools, release 10.0, V10.0.130

安裝Python3.6.5。

然后安裝Tensorflow。

或者下面的命令適合你：