win10+RTX3050ti+TensorFlow+cudn+cudnn配置深度学习环境的方法

来源：jb51　　时间：2022/6/21 12:20:46　　对本文有异议

避坑1：RTX30系列显卡不支持cuda11.0以下版本，具体上限版本可自行查阅：

方法一，在cmd中输入nvidia-smi查看

方法二：

由此可以看出本电脑最高适配cuda11.2.1版本；

注意需要版本适配，这里我们选择TensorFlow-gpu = 2.5，cuda=11.2.1，cudnn=8.1，python3.7

接下来可以下载cudn和cundnn：

官网：https://developer.nvidia.com/cuda-toolkit-archive

下载对应版本exe文件打开默认安装就可；

验证是否安装成功：

官网：cuDNN Archive | NVIDIA Developer

把下载文件进行解压把bin+lib+include文件复制到C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.2文件下；

进入环境变量设置（cuda会自动设置，如果没有的补全）：

查看是否安装成功：

cd C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.2\extras\demo_suite
bandwidthTest.exe

安装tensorflow-gpu:

pip install tensorflow-gpu==2.5

最后我们找相关程序来验证一下：

第一步：

import tensorflow as tf
print(tf.__version__)
print('GPU', tf.test.is_gpu_available())

第二步：

# _*_ coding=utf-8 _*_
'''
@author: crazy jums
@time: 2021-01-24 20:55
@desc: 添加描述
'''
# 指定GPU训练
import os
os.environ["CUDA_VISIBLE_DEVICES"]="0"  ##表示使用GPU编号为0的GPU进行计算
import numpy as np
from tensorflow.keras.models import Sequential  # 采用贯序模型
from tensorflow.keras.layers import Dense, Dropout, Conv2D, MaxPool2D, Flatten
from tensorflow.keras.datasets import mnist
from tensorflow.keras.utils import to_categorical
from tensorflow.keras.callbacks import TensorBoard
import time
def create_model():
    model = Sequential()
    model.add(Conv2D(32, (5, 5), activation='relu', input_shape=[28, 28, 1]))  # 第一卷积层
    model.add(Conv2D(64, (5, 5), activation='relu'))  # 第二卷积层
    model.add(MaxPool2D(pool_size=(2, 2)))  # 池化层
    model.add(Flatten())  # 平铺层
    model.add(Dropout(0.5))
    model.add(Dense(128, activation='relu'))
    model.add(Dropout(0.5))
    model.add(Dense(10, activation='softmax'))
    return model
def compile_model(model):
    model.compile(loss='categorical_crossentropy', optimizer="adam", metrics=['acc'])
    return model
def train_model(model, x_train, y_train, batch_size=32, epochs=10):
    tbCallBack = TensorBoard(log_dir="model", histogram_freq=1, write_grads=True)
    history = model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs, shuffle=True, verbose=2,
                        validation_split=0.2, callbacks=[tbCallBack])
    return history, model
if __name__ == "__main__":
    import tensorflow as tf
    print(tf.__version__)
    from tensorflow.python.client import device_lib
    print(device_lib.list_local_devices())
    (x_train, y_train), (x_test, y_test) = mnist.load_data()  # mnist的数据我自己已经下载好了的
    print(np.shape(x_train), np.shape(y_train), np.shape(x_test), np.shape(y_test))
    x_train = np.expand_dims(x_train, axis=3)
    x_test = np.expand_dims(x_test, axis=3)
    y_train = to_categorical(y_train, num_classes=10)
    y_test = to_categorical(y_test, num_classes=10)
    print(np.shape(x_train), np.shape(y_train), np.shape(x_test), np.shape(y_test))
    model = create_model()
    model = compile_model(model)
    print("start training")
    ts = time.time()
    history, model = train_model(model, x_train, y_train, epochs=2)
    print("start training", time.time() - ts)