怎么做站旅游网站上泡到妞,网页制作模板ppt制作,dede模板网站教程,网站制作产品资料windows10安装Tensorflow-gpu 2.10.0
本文主要目的是 从0开始演示 在windows10 平台安装Tensorflow-gpu 2.10.0。 Tensorflow-gpu 2.10.0 之后的版本#xff0c;不再支持这样的安装方式#xff0c;如果有需要#xff0c;请参考wsl安装ubuntu的方式#xff0c;进行安装。
…windows10安装Tensorflow-gpu 2.10.0
本文主要目的是 从0开始演示 在windows10 平台安装Tensorflow-gpu 2.10.0。 Tensorflow-gpu 2.10.0 之后的版本不再支持这样的安装方式如果有需要请参考wsl安装ubuntu的方式进行安装。
1.安装miniconda
https://docs.anaconda.com/free/miniconda/index.html
2.安装CUDA
tensorflow-cuda-cudnn对应版本 tensorflow-cuda-cudnn 下载 CUDA11.2 cuda11.2 | https://developer.nvidia.com/cuda-toolkit-archive cuda安装完之后已经配置好环境路径了直接在cmd中查看
nvcc -V下载cudnn8.10 cudnn | https://developer.nvidia.com/rdp/cudnn-archive
把cudnn8.10解压出来的文件拷贝到cuda下有对应的文件下名称对应拷贝过去。
3.创建python环境
conda create --name tf2.10 python3.10.14conda activate tf2.104.安装Tensorflow-GPU 2.10.0
Tensorflow-GPU 2.10.0
pip install tensorflow-gpu2.10.0 -i https://pypi.tuna.tsinghua.edu.cn/simple/安装一些常用常用包
pip install scikit-learn einops ipywidgets pandas tqdm jupyterlab matplotlib seaborn -i https://pypi.tuna.tsinghua.edu.cn/simple/测试
python ./mnist.py
import tensorflow as tf
print(tf.__version__)
print(tf.config.list_physical_devices(GPU))
print(tf.test.is_built_with_cuda())import tensorflow as tf
import seaborn as sns
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.image as mpimgprint(tf.__version__)
print(tf.config.list_physical_devices(GPU))mnist tf.keras.datasets.mnist
(x_train, y_train), (x_test, y_test) mnist.load_data(pathmnist.npz)input_shape (28, 28, 1)x_trainx_train.reshape(x_train.shape[0], x_train.shape[1], x_train.shape[2], 1)
x_trainx_train / 255.0
x_test x_test.reshape(x_test.shape[0], x_test.shape[1], x_test.shape[2], 1)
x_testx_test/255.0y_train tf.one_hot(y_train.astype(np.int32), depth10)
y_test tf.one_hot(y_test.astype(np.int32), depth10)batch_size 64
num_classes 10
epochs 5model tf.keras.models.Sequential([tf.keras.layers.Conv2D(32, (5,5), paddingsame, activationrelu, input_shapeinput_shape),tf.keras.layers.Conv2D(32, (5,5), paddingsame, activationrelu),tf.keras.layers.MaxPool2D(),tf.keras.layers.Dropout(0.25),tf.keras.layers.Conv2D(64, (3,3), paddingsame, activationrelu),tf.keras.layers.Conv2D(64, (3,3), paddingsame, activationrelu),tf.keras.layers.MaxPool2D(strides(2,2)),tf.keras.layers.Dropout(0.25),tf.keras.layers.Flatten(),tf.keras.layers.Dense(128, activationrelu),tf.keras.layers.Dropout(0.5),tf.keras.layers.Dense(num_classes, activationsoftmax)
])model.compile(optimizertf.keras.optimizers.RMSprop(epsilon1e-08), losscategorical_crossentropy, metrics[acc])class myCallback(tf.keras.callbacks.Callback):def on_epoch_end(self, epoch, logs{}):if(logs.get(acc)0.995):print(\nReached 99.5% accuracy so cancelling training!)self.model.stop_training Truecallbacks myCallback()history model.fit(x_train, y_train,batch_sizebatch_size,epochsepochs,validation_split0.1,callbacks[callbacks])test_loss, test_acc model.evaluate(x_test, y_test)
