安装飞桨paddle2.6.1+cuda11.7+paddleRS-develop开发版
安装时间：2024-8-30
#(一)查看环境
conda info --env
conda env list
下载安装conda3
https://mirrors.tuna.tsinghua.edu.cn/anaconda/archive/?C=M\&O=A
下载版本文件：Anaconda3-2024.06-1-Windows-x86_64.exe
下载安装到磁盘空闲空间要大的D:\ProgramData\Anaconda3
设置添加系统变量Path
D:\ProgramData\Anaconda3
D:\ProgramData\Anaconda3\Scripts
D:\ProgramData\Anaconda3\Library\bin
D:\ProgramData\Anaconda3\Library\mingw-w64\bin
安装完后：python版本3.12.4
conda --version
conda 24.7.1
#(二)创建paddleRS环境空间(python=3.9.13)
#创建rs环境空间(python=3.9.13),会自动生成到目录中C:\Users\Administrator.conda\envs\rs
conda create -n rs python=3.9.13
conda remove -n rs --all
conda activate rs
conda deactivate
#测试用--创建cwgis环境空间(python=3.9.13),会自动生成到目录中C:\Users\Administrator.conda\envs\cwgis
conda create -n cwgis python=3.9.13
conda remove -n cwgis --all
conda activate base
conda activate cwgis
conda deactivate
#也可自定义路径的cwgis环境空间
D:\ProgramData\anaconda3\envs
conda create --prefix=D:\ProgramData\anaconda3\envs\cwgis python=3.9.13
下载CUDA11.7.1安装
测试是否cuda安装成功
nvcc -V
命令行输入检查该计算机适配的CUDA版本：
nvidia-smi
下载CUDA的安装（开发者工具包)CUDA11.7.1并运行
https://developer.nvidia.com/cuda-toolkit-archive
cuda_11.7.1_516.94_windows.exe
安装后有目录：C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7
系统path自动添加：
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\bin
下载CUDNN的安装(8.9.4.25)
https://developer.nvidia.com/rdp/cudnn-download
https://developer.nvidia.com/rdp/cudnn-archive
必须注册账户登录后下载
cudnn-windows-x86_64-8.9.4.25_cuda11-archive.zip
将解压后得到的的bin ，include 和lib文件夹分别复制到cuda安装路径下与cuda的bin ，include 和lib文件夹合并
bin copy to C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\bin
include copy to C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\include
lib copy to C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\lib
采用中科大源
conda config --add channels https://mirrors.ustc.edu.cn/anaconda/pkgs/free/
conda config --add channels https://mirrors.ustc.edu.cn/anaconda/pkgs/main/
conda config --add channels https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge/
#(三)安装飞桨paddlepaddle-gpu==2.6.1 cuda11.7
以管理员身份运行cmd.exe
conda env list
conda init cmd.exe
conda init powershell
conda activate rs
conda deactivate
conda install paddlepaddle-gpu==2.6.1 cudatoolkit=11.7 -c https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/Paddle/ -c conda-forge
conda list
#安装到目录中D:\ProgramData\anaconda3\pkgs
报错问题：无法加载文件 C:\Users\Administrator\Documents\WindowsPowerShell\profile.ps1
解决办法：
以管理员身份打开PowerShell 输入
Set-ExecutionPolicy -Scope CurrentUser
set-executionpolicy remotesigned
（四）下载安装PaddleRS-develop平台开发版源代码
下载PaddleRS-develop 源代码 解压后目录
G:\app2024\MyProject深度学习AI项目\rs_code\PaddleRS-develop
特别注意：#由develop 改为1.0.0
修改PaddleRS-develop/paddlers/.version = '1.0.0'
或
修改PaddleRS-develop/paddlers/init .py/version = '1.0.0'
conda activate rs
cd G:\app2024\MyProject深度学习AI项目\rs_code\PaddleRS-develop
#搜索conda仓库上可用版本号
python
conda search numpy
1.21.0 1.21.6
1.22.0 1.22.4
1.23.0 1.23.5
1.24.0 1.24.4
1.25.0 1.25.2
1.26.0 1.26.4
2.0.0 2.0.2
2.1.0
conda search xarray
2024.7.0
2024.6.0
2024.5.0
2024.3.0
2024.2.0
2024.1.0 2024.1.1
2023.12.0
2023.11.0需要提前安装的依赖包列表：
python
pip install scikit-learn==0.24.2 #安装成功OK
conda install gdal==3.4.0 #安装成功OK
conda install pillow==9.0.1 #安装成功OK
conda install numpy==1.22.0 #安装成功OK，测试安装没报问题ImportError: numpy.core.multiarray failed to import
conda install opencv==4.4.0 #安装成功OK 测试代码可用
conda install filterpy==1.4.5 #安装成功 OK
pip install opencv-contrib-python==4.4.0.46 #安装成功OK 选择与opencv4.4.0版本一致
conda install numpy==1.22.0 #再安装一次
pip install setuptools==68.0.0 #built lap时需要68.0.0版本才能编译通过，否则会报错如：74.0.0版本
pip install scikit-image==0.21.0 #需要降级到0.21.0 否则下面numpy==1.22.4安装兼容性报错
pip install numba==0.56.2
pip install pandas==2.0.3
conda install gdal==3.1.3
pip install xarray==2023.12.0
pip install numpy==1.22.4报错问题：ERROR: Failed to build installable wheels for some pyproject.toml based projects (lap)
解决办法：
python
pip install setuptools==68.0.0
更新pip
python -m pip install --upgrade pip setuptools wheel
或
python -m pip install --upgrade pip下载安装git
#==================================
1.先安装git Git-2.38.0-64-bit.exe
2.再安装 TortoiseGit-2.13.0.1-64bit.msi 安装后配置git path
#安装PaddleRS-develop版本
python
pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple/
#===========================================================
conda install numba==0.56.2
conda install numpy==1.21.6 #中间需要执行此句，否则会报错：ImportError: numpy._core.multiarray failed to import
或
pip install numba==0.56.2
pip install pandas==2.0.3
conda install gdal==3.1.3
pip install xarray==2023.12.0
pip install numpy==1.22.4 #conda list中显示为 numpy 2.0.2 pypi
#===========================================================
python setup.py install(五) 测试安装情况代码一结果
python
(rs) PS G:\app2024\MyProject深度学习AI项目\web> & C:/Users/Administrator/.conda/envs/rs/python.exe g:/app2024/MyProject深度学习AI项目/web/test.py
2.6.1
Running verify PaddlePaddle program ...
I0829 17:55:25.061661 23132 program_interpreter.cc:212] New Executor is Running.
W0829 17:55:25.062655 23132 gpu_resources.cc:119] Please NOTE: device: 0, GPU Compute Capability: 6.1, Driver API Version: 12.6, Runtime API Version: 11.7
I0829 17:55:26.218680 23132 interpreter_util.cc:624] Standalone Executor is Used.
PaddlePaddle works well on 1 GPU.
PaddlePaddle is installed successfully! Let's stconda --versionng with PaddlePaddle now.
python
# 查看 paddle能够调用 gpu
import paddle
print(paddle.__version__); #2.6.1
#paddle.fluid.is_compiled_with_cuda() #2.4.2版本
paddle.is_compiled_with_cuda(); #2.6.1版本
paddle.utils.run_check()
'''
特别注意：
在vscode中使用创建的虚拟环境
选择python的解释器：在vscode中按住快捷键Ctrl+shift+P,输入Python然后执行如下图：
Python:Select Interpreter
select D:\ProgramData\Anaconda3\python.exe
'''测试安装情况代码二及结果：
python
(rs) PS G:\app2024\MyProject深度学习AI项目\web> & C:/Users/Administrator/.conda/envs/rs/python.exe g:/app2024/MyProject深度学习AI项目/web/MNIST_Good.py
10.4.0
2.6.1
视觉相关数据集： ['DatasetFolder', 'ImageFolder', 'MNIST', 'FashionMNIST', 'Flowers', 'Cifar10', 'Cifar100', 'VOC2012']
自然语言相关数据集： []
数据处理方法： ['BaseTransform', 'Compose', 'Resize', 'RandomResizedCrop', 'CenterCrop', 'RandomHorizontalFlip', 'RandomVerticalFlip', 'Transpose', 'Normalize', 'BrightnessTransform', 'SaturationTransform', 'ContrastTransform', 'HueTransform', 'ColorJitter', 'RandomCrop', 'Pad', 'RandomAffine', 'RandomRotation', 'RandomPerspective', 'Grayscale', 'ToTensor', 'RandomErasing', 'to_tensor', 'hflip', 'vflip', 'resize', 'pad', 'affine', 'rotate', 'perspective', 'to_grayscale', 'crop', 'center_crop', 'adjust_brightness', 'adjust_contrast', 'adjust_hue', 'normalize', 'erase']
g:\app2024\MyProject深度学习AI项目
训练数据集数量: 60000
第一个图片为 (28, 28) [5]
W0829 19:02:45.002585 17368 gpu_resources.cc:119] Please NOTE: device: 0, GPU Compute Capability: 6.1, Driver API Version: 12.6, Runtime API Version: 11.7
W0829 19:02:45.008549 17368 gpu_resources.cc:164] device: 0, cuDNN Version: 8.4.
loading mnist dataset from ./train/mnist.json.gz ......
mnist dataset load done
训练数据集数量: 50000
epoch: 0, batch: 0, loss is: 2.789569139480591
epoch: 0, batch: 200, loss is: 0.09251288324594498
epoch: 0, batch: 400, loss is: 0.06473854184150696
epoch: 1, batch: 0, loss is: 0.1018374040722847
epoch: 1, batch: 200, loss is: 0.07876559346914291
epoch: 1, batch: 400, loss is: 0.03011542186141014
epoch: 2, batch: 0, loss is: 0.056242216378450394
epoch: 2, batch: 200, loss is: 0.03451666235923767
epoch: 2, batch: 400, loss is: 0.011802399531006813
epoch: 3, batch: 0, loss is: 0.025893133133649826
epoch: 3, batch: 200, loss is: 0.00430287653580308
epoch: 3, batch: 400, loss is: 0.010484364815056324
epoch: 4, batch: 0, loss is: 0.004997999407351017
epoch: 4, batch: 200, loss is: 0.0019390254747122526
epoch: 4, batch: 400, loss is: 0.08761590719223022
epoch: 5, batch: 0, loss is: 0.05072423815727234
epoch: 5, batch: 200, loss is: 0.07972753047943115
epoch: 5, batch: 400, loss is: 0.033000100404024124
epoch: 6, batch: 0, loss is: 0.014615577645599842
epoch: 6, batch: 200, loss is: 0.0034718234091997147
epoch: 6, batch: 400, loss is: 0.05304107815027237
epoch: 7, batch: 0, loss is: 0.013993428088724613
epoch: 7, batch: 200, loss is: 0.047364864498376846
epoch: 7, batch: 400, loss is: 0.006570461671799421
epoch: 8, batch: 0, loss is: 0.05435584858059883
epoch: 8, batch: 200, loss is: 0.003356481436640024
epoch: 8, batch: 400, loss is: 0.0032313629053533077
epoch: 9, batch: 0, loss is: 0.0165287796407938
epoch: 9, batch: 200, loss is: 9.04486223589629e-05
epoch: 9, batch: 400, loss is: 0.0011677269358187914
运行时间Cost time: 71.6329174041748
本次预测的数字是: 0测试安装情况代码二：
python
#MNIST_Good.py
#数据处理部分之前的代码，加入部分数据处理的库
#需要安装：conda install matplotlib==3.5.0
import paddle
from paddle.nn import Conv2D, MaxPool2D, Linear
import paddle.nn.functional as F
import os
import sys
import gzip
import json
import random
import numpy as np
import matplotlib.pyplot as plt
# 导入图像读取第三方库
from PIL import Image,ImageFilter
print(Image.__version__) #10.4.0
#原来是在pillow的10.0.0版本中，ANTIALIAS方法被删除了，使用新的方法即可Image.LANCZOS
#或降级版本为9.5.0,安装pip install Pillow==9.5.0
print(paddle.__version__) #2.6.1
print('视觉相关数据集：', paddle.vision.datasets.__all__)
print('自然语言相关数据集：', paddle.text.datasets.__all__)
print('数据处理方法：', paddle.vision.transforms.__all__)
object_path = os.path.join(os.path.abspath(os.path.dirname(os.path.dirname(__file__))))
print(object_path)
sys.path.append(object_path) #
import common
#data=json.load(open("./work/train-images-idx3-ubyte.gz"))
#print(len(data))
#获取训练集train_dataset
train_dataset = paddle.vision.datasets.MNIST(mode='train')
print('训练数据集数量:',len(train_dataset)) # 60000
#取第一张图片和标签=5
i=0
#for i in range(20):
train_data0 = np.array(train_dataset[i][0])
train_label_0 = np.array(train_dataset[i][1])
print('第一个图片为',train_data0.shape,train_label_0) #(28,28),5
'''
plt.figure("Image") # 图像窗口名称
plt.figure(figsize=(2,2))
plt.imshow(train_data0, cmap=plt.cm.binary)
plt.axis('on') # 关掉坐标轴为 off
plt.title('image') # 图像题目
plt.show()
def sigmoid(x):
# 直接返回sigmoid函数
return 1. / (1. + np.exp(-x))
# param:起点，终点，间距
x = np.arange(-8, 8, 0.2)
y = sigmoid(x)
plt.plot(x, y)
plt.show()
'''
#===========================================
def load_data(mode='train'):
datafile = './train/mnist.json.gz'
print('loading mnist dataset from {} ......'.format(datafile))
# 加载json数据文件
data = json.load(gzip.open(datafile))
print('mnist dataset load done')
# 数据集相关参数，图片高度IMG_ROWS, 图片宽度IMG_COLS
IMG_ROWS = 28
IMG_COLS = 28
# 读取到的数据区分训练集，验证集，测试集
train_set, val_set, eval_set = data
if mode=='train':
# 获得训练数据集
imgs, labels = train_set[0], train_set[1]
elif mode=='valid':
# 获得验证数据集
imgs, labels = val_set[0], val_set[1]
elif mode=='eval':
# 获得测试数据集
imgs, labels = eval_set[0], eval_set[1]
else:
raise Exception("mode can only be one of ['train', 'valid', 'eval']")
print("训练数据集数量: ", len(imgs))
# 校验数据
imgs_length = len(imgs)
assert len(imgs) == len(labels), \
"length of train_imgs({}) should be the same as train_labels({})".format(len(imgs), len(labels))
# 获得数据集长度
imgs_length = len(imgs)
# 定义数据集每个数据的序号，根据序号读取数据
index_list = list(range(imgs_length))
# 读入数据时用到的批次大小
BATCHSIZE = 100
# 定义数据生成器
def data_generator():
if mode == 'train':
# 训练模式下打乱数据
random.shuffle(index_list)
imgs_list = []
labels_list = []
for i in index_list:
# 将数据处理成希望的类型
img = np.array(imgs[i]).astype('float32')
label = np.array(labels[i]).astype('float32')
# 在使用卷积神经网络结构时，uncomment 下面两行代码
img = np.reshape(imgs[i], [1, IMG_ROWS, IMG_COLS]).astype('float32')
#label = np.reshape(labels[i], [1]).astype('float32')
label = np.reshape(labels[i], [1]).astype('int64')
imgs_list.append(img)
labels_list.append(label)
if len(imgs_list) == BATCHSIZE:
# 获得一个batchsize的数据，并返回
yield np.array(imgs_list), np.array(labels_list)
# 清空数据读取列表
imgs_list = []
labels_list = []
# 如果剩余数据的数目小于BATCHSIZE，
# 则剩余数据一起构成一个大小为len(imgs_list)的mini-batch
if len(imgs_list) > 0:
yield np.array(imgs_list), np.array(labels_list)
return data_generator
#===========================================
#数据处理部分之后的代码，数据读取的部分调用Load_data函数
'''
# 定义多层全连接神经网络
class MNIST(paddle.nn.Layer):
def __init__(self):
super(MNIST, self).__init__()
# 定义两层全连接隐含层，输出维度是10，当前设定隐含节点数为10，可根据任务调整
self.fc1 = Linear(in_features=784, out_features=10)
self.fc2 = Linear(in_features=10, out_features=10)
# 定义一层全连接输出层，输出维度是1
self.fc3 = Linear(in_features=10, out_features=1)
# 定义网络的前向计算，隐含层激活函数为sigmoid，输出层不使用激活函数
def forward(self, inputs):
# inputs = paddle.reshape(inputs, [inputs.shape[0], 784])
outputs1 = self.fc1(inputs)
outputs1 = F.sigmoid(outputs1)
outputs2 = self.fc2(outputs1)
outputs2 = F.sigmoid(outputs2)
outputs_final = self.fc3(outputs2)
return outputs_final
'''
#===========================================
''' '''
#在卷积神经网络中，通常使用2×2大小的池化窗口，步幅也使用2，填充为0
#通过这种方式的池化，输出特征图的高和宽都减半，但通道数不会改变。
# 多层卷积神经网络实现
class MNIST(paddle.nn.Layer):
def __init__(self):
super(MNIST, self).__init__()
# 定义卷积层，输出特征通道out_channels设置为20，卷积核的大小kernel_size为5，卷积步长stride=1，padding=2
self.conv1 = Conv2D(in_channels=1, out_channels=20, kernel_size=5, stride=1, padding=2)
# 定义池化层，池化核的大小kernel_size为2，池化步长为2
self.max_pool1 = MaxPool2D(kernel_size=2, stride=2)
# 定义卷积层，输出特征通道out_channels设置为20，卷积核的大小kernel_size为5，卷积步长stride=1，padding=2
self.conv2 = Conv2D(in_channels=20, out_channels=20, kernel_size=5, stride=1, padding=2)
# 定义池化层，池化核的大小kernel_size为2，池化步长为2
self.max_pool2 = MaxPool2D(kernel_size=2, stride=2)
# 定义一层全连接层，输出维度是10
self.fc = Linear(in_features=980, out_features=10)
# 定义网络前向计算过程，卷积后紧接着使用池化层，最后使用全连接层计算最终输出
# 卷积层激活函数使用Relu，全连接层不使用激活函数
def forward(self, inputs):
x = self.conv1(inputs)
x = F.relu(x)
x = self.max_pool1(x)
x = self.conv2(x)
x = F.relu(x)
x = self.max_pool2(x)
x = paddle.reshape(x, [x.shape[0], -1])
x = self.fc(x)
return x
#===========================================
# 训练配置，并启动训练过程
#网络结构部分之后的代码，保持不变
def train(model):
#开启GPU #运行时间Cost time: 69.26997494697571
use_gpu = True
paddle.device.set_device('gpu:0') if use_gpu else paddle.device.set_device('cpu')
model.train()
#调用加载数据的函数，获得MNIST训练数据集
train_loader = load_data('train')
#优化模型参数
# 使用SGD优化器，learning_rate设置为0.01时loss下降明显最优 #cost time=705.9078650474548=11.75分钟
#opt = paddle.optimizer.SGD(learning_rate=0.01, parameters=model.parameters()) #运行时间cost time: 705.9078650474548
#opt = paddle.optimizer.SGD(learning_rate=0.001, parameters=model.parameters()) #运行时间Cost time: 705.5072021484375
#opt = paddle.optimizer.SGD(learning_rate=0.0001, parameters=model.parameters()) #运行时间Cost time: 708.7056725025177
#opt = paddle.optimizer.Momentum(learning_rate=0.01, momentum=0.9, parameters=model.parameters()) #运行时间Cost time: 707.7317929267883
#opt = paddle.optimizer.Adagrad(learning_rate=0.01, parameters=model.parameters()) #运行时间Cost time: 756.807531118393
opt = paddle.optimizer.Adam(learning_rate=0.01, parameters=model.parameters()) #运行时间Cost time: 702.2813944816589
# 训练5轮
EPOCH_NUM = 10
# MNIST图像高和宽
IMG_ROWS, IMG_COLS = 28, 28
loss_list = []
for epoch_id in range(EPOCH_NUM):
for batch_id, data in enumerate(train_loader()):
#准备数据
images, labels = data
images = paddle.to_tensor(images)
labels = paddle.to_tensor(labels)
#前向计算的过程
predicts = model(images)
#计算损失，使用交叉熵损失函数，取一个批次样本损失的平均值
loss = F.cross_entropy(predicts, labels)
avg_loss = paddle.mean(loss)
#每训练200批次的数据，打印下当前Loss的情况
if batch_id % 200 == 0:
loss = avg_loss.numpy(); #[0]
loss_list.append(loss)
print("epoch: {}, batch: {}, loss is: {}".format(epoch_id, batch_id, loss))
#后向传播，更新参数的过程
avg_loss.backward()
# 最小化loss,更新参数
opt.step()
# 清除梯度
opt.clear_grad()
#保存模型参数
paddle.save(model.state_dict(), 'mnist_test.pdparams')
return loss_list
startTime=common.startTime()
model = MNIST()
loss_list = train(model)
common.runTime(startTime)
# 读取一张本地的样例图片，转变成模型输入的格式
def load_image(img_path):
# 从img_path中读取图像，并转为灰度图
im = Image.open(img_path).convert('L')
im = im.resize((28, 28), Image.LANCZOS)
im = np.array(im).reshape(1, 1, 28, 28).astype(np.float32)
# 图像归一化
im = 1.0 - im / 255.
return im
# 定义预测过程
model = MNIST()
params_file_path = 'mnist_test.pdparams'
img_path = './data/example_0.jpg'
# 加载模型参数
param_dict = paddle.load(params_file_path)
model.load_dict(param_dict)
# 灌入数据
model.eval()
tensor_img = load_image(img_path)
#模型反馈10个分类标签的对应概率
results = model(paddle.to_tensor(tensor_img))
#取概率最大的标签作为预测输出
lab = np.argsort(results.numpy())
print("本次预测的数字是: ", lab[0][-1])安装后环境组件列表：
python
(rs) G:\app2024\MyProject深度学习AI项目\rs_code\PaddleRS-develop>conda list
# packages in environment at C:\Users\Administrator\.conda\envs\rs:
#
# Name Version Build Channel
anyio 4.4.0 pyhd8ed1ab_0 conda-forge
astor 0.8.1 pyh9f0ad1d_0 conda-forge
babel 2.16.0 pypi_0 pypi
bce-python-sdk 0.9.19 pypi_0 pypi
beautifulsoup4 4.12.3 pypi_0 pypi
blinker 1.8.2 pypi_0 pypi
blosc 1.21.1 hcbbf2c4_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
boost-cpp 1.76.0 h54f0996_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
branca 0.7.2 pypi_0 pypi
brotli 1.1.0 hcfcfb64_1 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
brotli-bin 1.1.0 hcfcfb64_1 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
brotli-python 1.1.0 py39h99910a6_1 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
bzip2 1.0.8 h2466b09_7 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
ca-certificates 2024.7.4 h56e8100_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
cachetools 5.5.0 pypi_0 pypi
cairo 1.16.0 hd28d34b_1006 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
certifi 2024.7.4 pyhd8ed1ab_0 conda-forge
cffi 1.17.0 py39ha55e580_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
cfitsio 3.470 h0af3d06_7 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
chardet 5.2.0 pypi_0 pypi
charset-normalizer 3.3.2 pyhd8ed1ab_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
click 8.1.7 pypi_0 pypi
cloudpickle 3.0.0 pypi_0 pypi
colorama 0.4.6 pypi_0 pypi
cudatoolkit 11.7.1 haa0b59a_13 conda-forge
cudnn 8.4.1.50 hf5f08ae_0 conda-forge
curl 8.1.2 h68f0423_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
cycler 0.12.1 pyhd8ed1ab_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
cython 3.0.11 pypi_0 pypi
dask 2024.8.0 pypi_0 pypi
decorator 5.1.1 pyhd8ed1ab_0 conda-forge
earthengine-api 0.1.418 pypi_0 pypi
easydict 1.13 pypi_0 pypi
ee-extra 0.0.15 pypi_0 pypi
eemont 0.3.6 pypi_0 pypi
et-xmlfile 1.1.0 pypi_0 pypi
exceptiongroup 1.2.2 pyhd8ed1ab_0 conda-forge
expat 2.6.2 h63175ca_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
filelock 3.15.4 pypi_0 pypi
filterpy 1.4.5 py_1 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
flask 3.0.3 pypi_0 pypi
flask-babel 4.0.0 pypi_0 pypi
foliume 0.0.1 pypi_0 pypi
font-ttf-dejavu-sans-mono 2.37 hab24e00_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
font-ttf-inconsolata 3.000 h77eed37_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
font-ttf-source-code-pro 2.038 h77eed37_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
font-ttf-ubuntu 0.83 h77eed37_2 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
fontconfig 2.14.2 hbde0cde_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
fonts-conda-ecosystem 1 0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
fonts-conda-forge 1 0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
fonttools 4.53.1 py39ha55e580_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
freetype 2.12.1 hdaf720e_2 conda-forge
freexl 1.0.6 h67ca5e6_1 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
fsspec 2024.6.1 pypi_0 pypi
future 1.0.0 pypi_0 pypi
gdal 3.1.3 py39hda8168b_1 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
geographiclib 2.0 pypi_0 pypi
geojson 3.1.0 pypi_0 pypi
geopy 2.4.1 pypi_0 pypi
geos 3.8.1 he025d50_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
geotiff 1.6.0 h8884d1a_3 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
gettext 0.22.5 h5728263_3 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
gettext-tools 0.22.5 h5a7288d_3 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
glib 2.80.2 h0df6a38_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
glib-tools 2.80.2 h2f9d560_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
google-api-core 2.19.2 pypi_0 pypi
google-api-python-client 2.143.0 pypi_0 pypi
google-auth 2.34.0 pypi_0 pypi
google-auth-httplib2 0.2.0 pypi_0 pypi
google-cloud-core 2.4.1 pypi_0 pypi
google-cloud-storage 2.18.2 pypi_0 pypi
google-crc32c 1.5.0 pypi_0 pypi
google-resumable-media 2.7.2 pypi_0 pypi
googleapis-common-protos 1.65.0 pypi_0 pypi
gst-plugins-base 1.24.4 hba88be7_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
gstreamer 1.24.4 h5006eae_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
h11 0.14.0 pyhd8ed1ab_0 conda-forge
h2 4.1.0 pyhd8ed1ab_0 conda-forge
hdf4 4.2.15 h1b1b6ef_5 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
hdf5 1.10.6 nompi_h5268f04_1114 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
hpack 4.0.0 pyh9f0ad1d_0 conda-forge
httpcore 1.0.5 pyhd8ed1ab_0 conda-forge
httplib2 0.22.0 pypi_0 pypi
httpx 0.27.2 pyhd8ed1ab_0 conda-forge
hyperframe 6.0.1 pyhd8ed1ab_0 conda-forge
icu 67.1 h33f27b4_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
idna 3.8 pyhd8ed1ab_0 conda-forge
imageio 2.35.1 pypi_0 pypi
importlib-metadata 8.4.0 pypi_0 pypi
intel-openmp 2024.2.1 h57928b3_1083 conda-forge
itsdangerous 2.2.0 pypi_0 pypi
jinja2 3.1.4 pypi_0 pypi
joblib 1.4.2 pypi_0 pypi
jpeg 9e h8ffe710_2 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
kealib 1.4.14 h96bfa42_2 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
kiwisolver 1.4.5 py39h1f6ef14_1 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
krb5 1.20.1 h6609f42_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
lap 0.4.0 pypi_0 pypi
lazy-loader 0.4 pypi_0 pypi
lcms2 2.12 h2a16943_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
lerc 3.0 h0e60522_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libasprintf 0.22.5 h5728263_3 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libasprintf-devel 0.22.5 h5728263_3 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libblas 3.9.0 23_win64_mkl conda-forge
libbrotlicommon 1.1.0 hcfcfb64_1 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libbrotlidec 1.1.0 hcfcfb64_1 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libbrotlienc 1.1.0 hcfcfb64_1 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libcblas 3.9.0 23_win64_mkl conda-forge
libclang 10.0.1 default_hf44288c_1 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libclang13 16.0.0 default_h45d3cf4_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libcurl 8.1.2 h68f0423_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libdeflate 1.10 h8ffe710_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libexpat 2.6.2 h63175ca_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libffi 3.4.2 h8ffe710_5 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libgdal 3.1.3 h0e5aa5a_1 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libgettextpo 0.22.5 h5728263_3 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libgettextpo-devel 0.22.5 h5728263_3 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libglib 2.80.2 h0df6a38_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libhwloc 2.11.1 default_h8125262_1000 conda-forge
libiconv 1.17 hcfcfb64_2 conda-forge
libintl 0.22.5 h5728263_3 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libintl-devel 0.22.5 h5728263_3 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libjpeg-turbo 2.1.4 hcfcfb64_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libkml 1.3.0 hd45a9bc_1016 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
liblapack 3.9.0 23_win64_mkl conda-forge
liblapacke 3.9.0 23_win64_mkl https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libnetcdf 4.7.4 nompi_h3a9aa94_107 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libogg 1.3.5 h2466b09_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libopencv 4.4.0 py39_3 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libpng 1.6.43 h19919ed_0 conda-forge
libpq 12.15 hb652d5d_1 https://mirrors.ustc.edu.cn/anaconda/pkgs/main
librttopo 1.1.0 h6a4060e_4 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libspatialite 5.0.1 h37d8b57_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libsqlite 3.46.0 h2466b09_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libssh2 1.10.0 h680486a_3 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libtiff 4.2.0 h763f289_2 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libvorbis 1.3.7 h0e60522_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libwebp 1.4.0 h2466b09_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libwebp-base 1.4.0 hcfcfb64_0 conda-forge
libxcb 1.13 hcd874cb_1004 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libxml2 2.12.7 h283a6d9_1 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libzip 1.9.2 hfed4ece_1 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libzlib 1.2.13 h2466b09_6 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
libzlib-wapi 1.2.13 h2466b09_6 conda-forge
llvmlite 0.39.1 pypi_0 pypi
locket 1.0.0 pypi_0 pypi
lz4-c 1.9.3 h8ffe710_1 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
m2w64-gcc-libgfortran 5.3.0 6 conda-forge
m2w64-gcc-libs 5.3.0 7 conda-forge
m2w64-gcc-libs-core 5.3.0 7 conda-forge
m2w64-gmp 6.1.0 2 conda-forge
m2w64-libwinpthread-git 5.0.0.4634.697f757 2 conda-forge
markupsafe 2.1.5 pypi_0 pypi
matplotlib 3.5.0 py39hcbf5309_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
matplotlib-base 3.5.0 py39h581301d_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
mkl 2024.1.0 h66d3029_694 conda-forge
motmetrics 1.4.0 pypi_0 pypi
msys2-conda-epoch 20160418 1 conda-forge
munch 4.0.0 pypi_0 pypi
munkres 1.1.4 pyh9f0ad1d_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
natsort 8.4.0 pypi_0 pypi
networkx 3.2.1 pypi_0 pypi
numba 0.56.2 pypi_0 pypi
numpy 1.22.4 pypi_0 pypi
opencv 4.4.0 py39_3 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
opencv-contrib-python 3.4.18.65 pypi_0 pypi
opencv-python 4.6.0.66 pypi_0 pypi
openjpeg 2.3.1 h48faf41_3 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
openpyxl 3.1.5 pypi_0 pypi
openssl 1.1.1w hcfcfb64_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
opt_einsum 3.3.0 pyhc1e730c_2 conda-forge
packaging 24.1 pyhd8ed1ab_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
paddlepaddle-gpu 2.6.1.post117 pypi_0 pypi
paddlers 1.0.0 pypi_0 pypi
paddleslim 0.0.0.dev0 pypi_0 pypi
pandas 2.0.3 pypi_0 pypi
partd 1.4.2 pypi_0 pypi
pcre 8.45 h0e60522_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
pcre2 10.43 h17e33f8_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
pillow 10.4.0 pypi_0 pypi
pip 24.2 pyhd8ed1ab_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
pixman 0.43.4 h63175ca_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
platformdirs 4.2.2 pyhd8ed1ab_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
ply 3.11 pyhd8ed1ab_2 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
pooch 1.8.2 pyhd8ed1ab_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
poppler 0.89.0 h7c6e155_3 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
poppler-data 0.4.12 hd8ed1ab_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
postgresql 12.15 hb652d5d_1 https://mirrors.ustc.edu.cn/anaconda/pkgs/main
proj 7.1.1 h7d85306_3 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
proto-plus 1.24.0 pypi_0 pypi
psutil 6.0.0 pypi_0 pypi
pthread-stubs 0.4 hcd874cb_1001 conda-forge
pthreads-win32 2.9.1 hfa6e2cd_3 conda-forge
py-opencv 4.4.0 py39h9cd51e4_3 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
pyasn1 0.6.0 pypi_0 pypi
pyasn1-modules 0.4.0 pypi_0 pypi
pycocotools 2.0.8 pypi_0 pypi
pycparser 2.22 pyhd8ed1ab_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
pycryptodome 3.20.0 pypi_0 pypi
pyparsing 3.1.4 pyhd8ed1ab_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
pyqt 5.12.3 py39hcbf5309_8 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
pyqt-impl 5.12.3 py39h415ef7b_8 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
pyqt5-sip 4.19.18 py39h415ef7b_8 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
pyqtchart 5.12 py39h415ef7b_8 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
pyqtwebengine 5.12.1 py39h415ef7b_8 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
pysocks 1.7.1 pyh0701188_6 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
python 3.9.15 h0269646_0_cpython https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
python-box 7.2.0 pypi_0 pypi
python-dateutil 2.9.0 pyhd8ed1ab_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
python_abi 3.9 5_cp39 conda-forge
pytz 2024.1 pypi_0 pypi
pywavelets 1.6.0 pypi_0 pypi
pyyaml 6.0.2 pypi_0 pypi
pyzmq 26.2.0 pypi_0 pypi
qt 5.12.9 hb2cf2c5_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
rarfile 4.2 pypi_0 pypi
requests 2.32.3 pyhd8ed1ab_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
rsa 4.9 pypi_0 pypi
scikit-image 0.21.0 pypi_0 pypi
scikit-learn 0.24.2 pypi_0 pypi
scipy 1.13.1 pypi_0 pypi
seaborn 0.13.2 pypi_0 pypi
setuptools 59.8.0 pypi_0 pypi
shapely 2.0.6 pypi_0 pypi
sip 6.7.12 py39h99910a6_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
six 1.16.0 pyh6c4a22f_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
snappy 1.1.10 hfb803bf_1 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
sniffio 1.3.1 pyhd8ed1ab_0 conda-forge
soupsieve 2.6 pypi_0 pypi
spyndex 0.6.0 pypi_0 pypi
sqlite 3.46.0 h2466b09_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
swig 4.2.1 pypi_0 pypi
tbb 2021.12.0 hc790b64_4 conda-forge
threadpoolctl 3.5.0 pypi_0 pypi
tifffile 2024.8.28 pypi_0 pypi
tiledb 2.1.6 hf84e3da_1 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
tk 8.6.13 h5226925_1 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
toml 0.10.2 pyhd8ed1ab_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
tomli 2.0.1 pyhd8ed1ab_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
toolz 0.12.1 pypi_0 pypi
tornado 6.4.1 py39ha55e580_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
tqdm 4.66.5 pypi_0 pypi
typing_extensions 4.12.2 pyha770c72_0 conda-forge
tzdata 2024.1 pypi_0 pypi
ucrt 10.0.22621.0 h57928b3_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
unicodedata2 15.1.0 py39ha55989b_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
uriparser 0.9.8 h5a68840_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
uritemplate 4.1.1 pypi_0 pypi
urllib3 2.2.2 pyhd8ed1ab_1 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
vc 14.3 h8a93ad2_20 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
vc14_runtime 14.40.33810 hcc2c482_20 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
visualdl 2.5.3 pypi_0 pypi
vs2015_runtime 14.40.33810 h3bf8584_20 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
werkzeug 3.0.4 pypi_0 pypi
wheel 0.44.0 pyhd8ed1ab_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
win_inet_pton 1.1.0 pyhd8ed1ab_6 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
xarray 2023.12.0 pypi_0 pypi
xerces-c 3.2.5 he0c23c2_1 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
xmltodict 0.13.0 pypi_0 pypi
xorg-libxau 1.0.11 hcd874cb_0 conda-forge
xorg-libxdmcp 1.1.3 hcd874cb_0 conda-forge
xz 5.2.6 h8d14728_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
zipp 3.20.1 pypi_0 pypi
zlib 1.2.13 h2466b09_6 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
zstandard 0.19.0 py39ha55989b_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
zstd 1.4.9 h6255e5f_0 https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
(rs) G:\app2024\MyProject深度学习AI项目\rs_code\PaddleRS-develop>本blog地址：https://blog.csdn.net/hsg77