目录：

1.激活环境

2.版本选择

突发情况：ModuleNotFoundError: No module named 'paddle'

检验是否安装成功

---

1.激活环境

Anaconda：

conda remove -n paddle --all
conda activate paddle

2.版本选择

打开链接：https://www.paddlepaddle.org.cn/install/quick?docurl=/documentation/docs/zh/install/conda/windows-conda.html

以conda11.7为例：

conda install paddlepaddle-gpu==2.4.1 cudatoolkit=11.7 -c https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/Paddle/ -c conda-forge

静候等待安装完成

---

突发情况：ModuleNotFoundError: No module named 'paddle'

解决方法：anaconda内：python -m pip install paddlepaddle -i https://mirror.baidu.com/pypi/simple

---

检验是否安装成功

进入python解释器:

import paddle.fluid as fluid ，

fluid.install_check.run_check()

出现Your Paddle Fluid is installed succesfully!，说明您已成功安装。

测试：手写数字识别

import paddle
import numpy as np
from paddle.vision.transforms import Normalize

transform = Normalize(mean=[127.5], std=[127.5], data_format='CHW')
# 下载数据集并初始化 DataSet
train_dataset = paddle.vision.datasets.MNIST(mode='train', transform=transform)
test_dataset = paddle.vision.datasets.MNIST(mode='test', transform=transform)

# 模型组网并初始化网络
lenet = paddle.vision.models.LeNet(num_classes=10)
model = paddle.Model(lenet)

# 模型训练的配置准备，准备损失函数，优化器和评价指标
model.prepare(paddle.optimizer.Adam(parameters=model.parameters()),
              paddle.nn.CrossEntropyLoss(),
              paddle.metric.Accuracy())

# 模型训练
model.fit(train_dataset, epochs=5, batch_size=64, verbose=1)
# 模型评估
model.evaluate(test_dataset, batch_size=64, verbose=1)

# 保存模型
model.save('./output/mnist')
# 加载模型
model.load('output/mnist')

# 从测试集中取出一张图片
img, label = test_dataset[0]
# 将图片shape从1*28*28变为1*1*28*28，增加一个batch维度，以匹配模型输入格式要求
img_batch = np.expand_dims(img.astype('float32'), axis=0)

# 执行推理并打印结果，此处predict_batch返回的是一个list，取出其中数据获得预测结果
out = model.predict_batch(img_batch)[0]
pred_label = out.argmax()
print('true label: {}, pred label: {}'.format(label[0], pred_label))
# 可视化图片
from matplotlib import pyplot as plt
plt.imshow(img[0])

item 2/2 [===========================>..] - ETA: 0s - 500us/itemThe loss value printed in the log is the current step, and the metric is the average value of previous steps.
Epoch 1/5
step 938/938 [==============================] - loss: 0.0808 - acc: 0.9364 - 15ms/step          
Epoch 2/5
step 938/938 [==============================] - loss: 0.0375 - acc: 0.9772 - 14ms/step          
Epoch 3/5
step 938/938 [==============================] - loss: 0.0103 - acc: 0.9816 - 14ms/step          
Epoch 4/5
step 938/938 [==============================] - loss: 0.0147 - acc: 0.9838 - 15ms/step          
Epoch 5/5
step 938/938 [==============================] - loss: 0.0159 - acc: 0.9853 - 14ms/step          
Eval begin...
step 157/157 [==============================] - loss: 5.4424e-04 - acc: 0.9821 - 5ms/step      
Eval samples: 10000
true label: 7, pred label: 7

进程已结束,退出代码0