Build caffe using qmake (ubuntu&windows)

最新推荐文章于 2022-01-29 10:05:00 发布
最新推荐文章于 2022-01-29 10:05:00 发布
阅读量901 收藏
点赞数
分类专栏： caffe qt 文章标签： windows qt
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/DuinoDu/article/details/54405993
版权
caffe 同时被 2 个专栏收录
9 篇文章 0 订阅
订阅专栏
qt
6 篇文章 0 订阅
订阅专栏

1. Problem

I want to build caffe on windows. Windows official version is a little complex, since I need to change dependent libs frequently. For a cross-platform solution, Qt is an awesome choice.

2. Solution

Platform: Windows10(x64)+ VS2013 (msvc120)

2.1 Prepare

Caffe uses a lot of cpp libs: boost, gflags, glog, hdf5, LevelDB, Imdb, openblas, opencv, protobuf. I upload msvc120_x64 version here.

2.2 Code

Qt uses qmake to manage project. All you need just a *.pro file, as CMakeLists.txt for cmake.

Here is libcaffe.pro

TEMPLATE = lib
CONFIG(debug, debug|release): TARGET = libcaffed
CONFIG(release, debug|release): TARGET = libcaffe
INCLUDEPATH += include src include/caffe/proto
DEFINES += USE_OPENCV CPU_ONLY
CONFIG += dll staticlib

# Input
HEADERS += \
    include/caffe/blob.hpp\
    include/caffe/caffe.hpp\
    include/caffe/common.hpp\
    include/caffe/data_reader.hpp\
    include/caffe/data_transformer.hpp\
    include/caffe/filler.hpp\
    include/caffe/internal_thread.hpp\
    include/caffe/layer.hpp\
    include/caffe/layers/absval_layer.hpp\
    include/caffe/layers/accuracy_layer.hpp\
    include/caffe/layers/argmax_layer.hpp\
    include/caffe/layers/base_conv_layer.hpp\
    include/caffe/layers/base_data_layer.hpp\
    include/caffe/layers/batch_norm_layer.hpp\
    include/caffe/layers/batch_reindex_layer.hpp\
    include/caffe/layers/bias_layer.hpp\
    include/caffe/layers/bnll_layer.hpp\
    include/caffe/layers/box_annotator_ohem_layer.hpp\
    include/caffe/layers/concat_layer.hpp\
    include/caffe/layers/contrastive_loss_layer.hpp\
    include/caffe/layers/conv_layer.hpp\
    include/caffe/layers/crop_layer.hpp\
    include/caffe/layers/cudnn_conv_layer.hpp\
    include/caffe/layers/cudnn_lcn_layer.hpp\
    include/caffe/layers/cudnn_lrn_layer.hpp\
    include/caffe/layers/cudnn_pooling_layer.hpp\
    include/caffe/layers/cudnn_relu_layer.hpp\
    include/caffe/layers/cudnn_sigmoid_layer.hpp\
    include/caffe/layers/cudnn_softmax_layer.hpp\
    include/caffe/layers/cudnn_tanh_layer.hpp\
    include/caffe/layers/data_layer.hpp\
    include/caffe/layers/deconv_layer.hpp\
    include/caffe/layers/dropout_layer.hpp\
    include/caffe/layers/dummy_data_layer.hpp\
    include/caffe/layers/eltwise_layer.hpp\
    include/caffe/layers/elu_layer.hpp\
    include/caffe/layers/embed_layer.hpp\
    include/caffe/layers/euclidean_loss_layer.hpp\
    include/caffe/layers/exp_layer.hpp\
    include/caffe/layers/filter_layer.hpp\
    include/caffe/layers/flatten_layer.hpp\
    include/caffe/layers/hdf5_data_layer/.hpp\
    include/caffe/layers/hdf5_output_layer.hpp\
    include/caffe/layers/hinge_loss_layer.hpp\
    include/caffe/layers/im2col_layer.hpp\
    include/caffe/layers/image_data_layer.hpp\
    include/caffe/layers/infogain_loss_layer.hpp\
    include/caffe/layers/inner_product_layer.hpp\
    include/caffe/layers/input_layer.hpp\
    include/caffe/layers/log_layer.hpp\
    include/caffe/layers/loss_layer.hpp\
    include/caffe/layers/lrn_layer.hpp\
    include/caffe/layers/lstm_layer.hpp\
    include/caffe/layers/memory_data_layer.hpp\
    include/caffe/layers/multinomial_logistic_loss_layer.hpp\
    include/caffe/layers/mvn_layer.hpp\
    include/caffe/layers/neuron_layer.hpp\
    include/caffe/layers/parameter_layer.hpp\
    include/caffe/layers/pooling_layer.hpp\
    include/caffe/layers/power_layer.hpp\
    include/caffe/layers/prelu_layer.hpp\
    include/caffe/layers/psroi_pooling_layer.hpp\
    include/caffe/layers/python_layer.hpp\
    include/caffe/layers/recurrent_layer.hpp\
    include/caffe/layers/reduction_layer.hpp\
    include/caffe/layers/relu_layer.hpp\
    include/caffe/layers/reshape_layer.hpp\
    include/caffe/layers/rnn_layer.hpp\
    include/caffe/layers/roi_pooling_layer.hpp\
    include/caffe/layers/scale_layer.hpp\
    include/caffe/layers/sigmoid_cross_entropy_loss_layer.hpp\
    include/caffe/layers/sigmoid_layer.hpp\
    include/caffe/layers/silence_layer.hpp\
    include/caffe/layers/slice_layer.hpp\
    include/caffe/layers/smooth_l1_loss_layer.hpp\
    include/caffe/layers/smooth_l1_loss_ohem_layer.hpp\
    include/caffe/layers/softmax_layer.hpp\
    include/caffe/layers/softmax_loss_layer.hpp\
    include/caffe/layers/softmax_loss_ohem_layer.hpp\
    include/caffe/layers/split_layer.hpp\
    include/caffe/layers/spp_layer.hpp\
    include/caffe/layers/tanh_layer.hpp\
    include/caffe/layers/threshold_layer.hpp\
    include/caffe/layers/tile_layer.hpp\
    include/caffe/layers/window_data_layer.hpp\
    include/caffe/layer_factory.hpp\
    include/caffe/net.hpp\
    include/caffe/parallel.hpp\
    include/caffe/proto/caffe.pb.h\
    include/caffe/sgd_solvers.hpp\
    include/caffe/solver.hpp\
    include/caffe/solver_factory.hpp\
    include/caffe/syncedmem.hpp\
    include/caffe/util/benchmark.hpp\
    include/caffe/util/blocking_queue.hpp\
    include/caffe/util/cudnn.hpp\
    include/caffe/util/db.hpp\
    include/caffe/util/db_leveldb.hpp\
    include/caffe/util/db_lmdb.hpp\
    include/caffe/util/device_alternate.hpp\
    include/caffe/util/format.hpp\
    include/caffe/util/hdf5.hpp\
    include/caffe/util/im2col.hpp\
    include/caffe/util/insert_splits.hpp\
    include/caffe/util/io.hpp\
    include/caffe/util/math_functions.hpp\
    include/caffe/util/mkl_alternate.hpp\
    include/caffe/util/rng.hpp\
    include/caffe/util/signal_handler.h\
    include/caffe/util/upgrade_proto.hpp

SOURCES += \
   src/caffe/blob.cpp \
   src/caffe/common.cpp \
   src/caffe/data_reader.cpp \
   src/caffe/data_transformer.cpp \
   src/caffe/internal_thread.cpp \
   src/caffe/layer.cpp \
   src/caffe/layers/absval_layer.cpp \
   src/caffe/layers/accuracy_layer.cpp \
   src/caffe/layers/argmax_layer.cpp \
   src/caffe/layers/base_conv_layer.cpp \
   src/caffe/layers/base_data_layer.cpp \
   src/caffe/layers/batch_norm_layer.cpp \
   src/caffe/layers/batch_reindex_layer.cpp \
   src/caffe/layers/bias_layer.cpp \
   src/caffe/layers/bnll_layer.cpp \
   src/caffe/layers/box_annotator_ohem_layer.cpp \
   src/caffe/layers/concat_layer.cpp \
   src/caffe/layers/contrastive_loss_layer.cpp \
   src/caffe/layers/conv_layer.cpp \
   src/caffe/layers/crop_layer.cpp \
   src/caffe/layers/cudnn_conv_layer.cpp \
   src/caffe/layers/cudnn_lcn_layer.cpp \
   src/caffe/layers/cudnn_lrn_layer.cpp \
   src/caffe/layers/cudnn_pooling_layer.cpp \
   src/caffe/layers/cudnn_relu_layer.cpp \
   src/caffe/layers/cudnn_sigmoid_layer.cpp \
   src/caffe/layers/cudnn_softmax_layer.cpp \
   src/caffe/layers/cudnn_tanh_layer.cpp \
   src/caffe/layers/data_layer.cpp \
   src/caffe/layers/deconv_layer.cpp \
   src/caffe/layers/dropout_layer.cpp \
   src/caffe/layers/dummy_data_layer.cpp \
   src/caffe/layers/eltwise_layer.cpp \
   src/caffe/layers/elu_layer.cpp \
   src/caffe/layers/embed_layer.cpp \
   src/caffe/layers/euclidean_loss_layer.cpp \
   src/caffe/layers/exp_layer.cpp \
   src/caffe/layers/filter_layer.cpp \
   src/caffe/layers/flatten_layer.cpp \
   src/caffe/layers/hdf5_data_layer.cpp \
   src/caffe/layers/hdf5_output_layer.cpp \
   src/caffe/layers/hinge_loss_layer.cpp \
   src/caffe/layers/im2col_layer.cpp \
   src/caffe/layers/image_data_layer.cpp \
   src/caffe/layers/infogain_loss_layer.cpp \
   src/caffe/layers/inner_product_layer.cpp \
   src/caffe/layers/input_layer.cpp \
   src/caffe/layers/log_layer.cpp \
   src/caffe/layers/loss_layer.cpp \
   src/caffe/layers/lrn_layer.cpp \
   src/caffe/layers/lstm_layer.cpp \
   src/caffe/layers/lstm_unit_layer.cpp \
   src/caffe/layers/memory_data_layer.cpp \
   src/caffe/layers/multinomial_logistic_loss_layer.cpp \
   src/caffe/layers/mvn_layer.cpp \
   src/caffe/layers/neuron_layer.cpp \
   src/caffe/layers/parameter_layer.cpp \
   src/caffe/layers/pooling_layer.cpp \
   src/caffe/layers/power_layer.cpp \
   src/caffe/layers/prelu_layer.cpp \
   src/caffe/layers/psroi_pooling_layer.cpp \
   src/caffe/layers/recurrent_layer.cpp \
   src/caffe/layers/reduction_layer.cpp \
   src/caffe/layers/relu_layer.cpp \
   src/caffe/layers/reshape_layer.cpp \
   src/caffe/layers/rnn_layer.cpp \
   src/caffe/layers/roi_pooling_layer.cpp \
   src/caffe/layers/scale_layer.cpp \
   src/caffe/layers/sigmoid_cross_entropy_loss_layer.cpp \
   src/caffe/layers/sigmoid_layer.cpp \
   src/caffe/layers/silence_layer.cpp \
   src/caffe/layers/slice_layer.cpp \
   src/caffe/layers/smooth_l1_loss_layer.cpp \
   src/caffe/layers/smooth_L1_loss_ohem_layer.cpp \
   src/caffe/layers/softmax_layer.cpp \
   src/caffe/layers/softmax_loss_layer.cpp \
   src/caffe/layers/softmax_loss_ohem_layer.cpp \
   src/caffe/layers/split_layer.cpp \
   src/caffe/layers/spp_layer.cpp \
   src/caffe/layers/tanh_layer.cpp \
   src/caffe/layers/threshold_layer.cpp \
   src/caffe/layers/tile_layer.cpp \
   src/caffe/layers/window_data_layer.cpp \
   src/caffe/layer_factory.cpp \
   src/caffe/net.cpp \
   src/caffe/parallel.cpp \
   src/caffe/solver.cpp \
   src/caffe/solvers/adadelta_solver.cpp \
   src/caffe/solvers/adagrad_solver.cpp \
   src/caffe/solvers/adam_solver.cpp \
   src/caffe/solvers/nesterov_solver.cpp \
   src/caffe/solvers/rmsprop_solver.cpp \
   src/caffe/solvers/sgd_solver.cpp \
   src/caffe/syncedmem.cpp \
   src/caffe/util/benchmark.cpp \
   src/caffe/util/blocking_queue.cpp \
   src/caffe/util/cudnn.cpp \
   src/caffe/util/db.cpp \
   src/caffe/util/db_leveldb.cpp \
   src/caffe/util/db_lmdb.cpp \
   src/caffe/util/hdf5.cpp \
   src/caffe/util/im2col.cpp \
   src/caffe/util/insert_splits.cpp \
   src/caffe/util/io.cpp \
   src/caffe/util/math_functions.cpp \
   src/caffe/util/signal_handler.cpp \
   src/caffe/util/upgrade_proto.cpp \
   src/caffe/proto/caffe.pb.cc

win32{

# opencv
PATH_OPENCV_INCLUDE   = "H:\3rdparty\OpenCV\opencv310\build\include"
PATH_OPENCV_LIBRARIES = "H:\3rdparty\OpenCV\opencv310\build\x64\vc12\lib"
VERSION_OPENCV        = 310
INCLUDEPATH += $${PATH_OPENCV_INCLUDE}
CONFIG(debug, debug|release){
LIBS += -L$${PATH_OPENCV_LIBRARIES} -lopencv_core$${VERSION_OPENCV}d
LIBS += -L$${PATH_OPENCV_LIBRARIES} -lopencv_highgui$${VERSION_OPENCV}d
LIBS += -L$${PATH_OPENCV_LIBRARIES} -lopencv_imgcodecs$${VERSION_OPENCV}d
LIBS += -L$${PATH_OPENCV_LIBRARIES} -lopencv_imgproc$${VERSION_OPENCV}d
}
CONFIG(release, debug|release){
LIBS += -L$${PATH_OPENCV_LIBRARIES} -lopencv_core$${VERSION_OPENCV}
LIBS += -L$${PATH_OPENCV_LIBRARIES} -lopencv_highgui$${VERSION_OPENCV}
LIBS += -L$${PATH_OPENCV_LIBRARIES} -lopencv_imgcodecs$${VERSION_OPENCV}
LIBS += -L$${PATH_OPENCV_LIBRARIES} -lopencv_imgproc$${VERSION_OPENCV}
}
#glog
INCLUDEPATH += H:\3rdparty\glog\include
LIBS += -LH:\3rdparty\glog\lib\x64\v120\Debug\dynamic -llibglog

#boost
INCLUDEPATH += H:\3rdparty\boost\boost_1_59_0
CONFIG(debug, debug|release): BOOST_VERSION = "-vc120-mt-gd-1_59"
CONFIG(release, debug|release): BOOST_VERSION = "-vc120-mt-1_59"
LIBS += -LH:\3rdparty\boost\boost_1_59_0\lib64-msvc-12.0 \
    -llibboost_system$${BOOST_VERSION} \
    -llibboost_date_time$${BOOST_VERSION} \
    -llibboost_filesystem$${BOOST_VERSION} \
    -llibboost_thread$${BOOST_VERSION} \
    -llibboost_regex$${BOOST_VERSION}

#gflags
INCLUDEPATH += H:\3rdparty\gflags\include
CONFIG(debug, debug|release): LIBS += -LH:\3rdparty\gflags\x64\v120\dynamic\Lib -lgflagsd
CONFIG(release, debug|release): LIBS += -LH:\3rdparty\gflags\x64\v120\dynamic\Lib -lgflags

#protobuf
INCLUDEPATH += H:\3rdparty\protobuf\include
CONFIG(debug, debug|release): LIBS += -LH:\3rdparty\protobuf\lib\x64\v120\Debug -llibprotobuf
CONFIG(release, debug|release): LIBS += -LH:\3rdparty\protobuf\lib\x64\v120\Release -llibprotobuf

# hdf5
INCLUDEPATH += H:\3rdparty\hdf5\include
LIBS += -LH:\3rdparty\hdf5\lib\x64 -lhdf5 -lhdf5_hl -lhdf5_tools -lhdf5_cpp

# levelDb
INCLUDEPATH += H:\3rdparty\LevelDB\include
CONFIG(debug, debug|release): LIBS += -LH:\3rdparty\LevelDB\lib\x64\v120\Debug -lLevelDb
CONFIG(release, debug|release): LIBS += -LH:\3rdparty\LevelDB\lib\x64\v120\Release -lLevelDb

# lmdb
INCLUDEPATH += H:\3rdparty\lmdb\include
CONFIG(debug, debug|release): LIBS += -LH:\3rdparty\lmdb\lib\x64 -llmdbD
CONFIG(release, debug|release): LIBS += -LH:\3rdparty\lmdb\lib\x64 -llmdb

#openblas
INCLUDEPATH += H:\3rdparty\openblas\include
LIBS += -LH:\3rdparty\openblas\lib\x64 -llibopenblas
}

You neeed to change library path to your own.

Done.

You can find caffe project on my github

DuinoDu
关注
  • 0
    点赞
  • 踩
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
专栏目录
win7+cuda8.0+cudnn5.1+caffe-master(microsoft)+faster-rcnn完整配置手册
m0_37973394的博客
01-28 3374
首先给出一些下载地址: Cudnn下载： https://developer.nvidia.com/rdp/cudnn-download Vs2013下载： http://download.microsoft.com/download/9/3/E/93EA27FF-DB02-4822-8771-DCA0238957E9/vs2013.5_ult_chs.iso?type=ISO Caff
winsows10下用ninja编译配置caffe
thomaszhaoyc的博客
03-30 9947
出于好奇自己想在windows上配置一下caffe环境，于是在网上找了一些教程。发现都和caffe官网上的说法有些不同，于是抱着作死的心态去按照官网上的做法走了一遍。自己也是新手，还有许多不明白的地方，随手mark一下。 参考：https://github.com/BVLC/caffe/tree/windows Requirements Visual Studio 2
qmake手册——平台笔记
loufand的博客
08-21 439
平台笔记使用基本的qmake设置已经可以处理许多跨平台的项目了，但是有时使用一些平台特有的特性也是有用甚至必须的。 qmake知道许多这些功能，可以通过仅在相关平台上生效的特定变量进行访问。OS X 和 iOSFeatures specific to these platforms include support for creating universal binaries, framework
Ubuntu18.04 + Caffe + python3.7 + CUDA11 + cuDNN8编译记录
weixin_39161727的博客
09-06 3105
Ubuntu18.04 + Caffe + python3.7 + CUDA11 + cuDNN8编译记录背景基础环境安装过程Python3.7安装caffe官方代码下载及配置文件修改caffe与python3.7/cuDNN8适配cudnn_conv_layer.cpp和cudnn_deconv_layer.cppcuDNN版本指定libboost_python.so链接版本修改开始编译caffe调用caffe 背景 这两天接手了一个在两年前基于caffe实现的交互式活体检测的项目，想要让他在python
教程 | Caffe在Windows10系统上安装与配置
小白学视觉
01-29 5449
点击上方“小白学视觉”，选择加"星标"或“置顶”重磅干货，第一时间送达软件下载和安装预先安装软件与版本CMake 3.13.4Anaconda with Python 2 on 64-bi...
py-R-FCN源码分析
Marshall的专栏
01-05 6744
softmax_loss_ohem_layer.cu #include #include #include #include "caffe/layers/softmax_loss_ohem_layer.hpp" #include "caffe/util/math_functions.hpp" namespace caffe { template __global__ void
搭建及训练py-R-FCN遇到的问题
Bankeey的博客
08-25 2366
搭建py-R-FCN遇到的问题记录。 make pycaffe 报错 src/caffe/layers/box_annotator_ohem_layer.cu(49): error: a template argument may not reference a local type           detected during instantiation of "void caf
Caffe2 build_windows.bat（修改后）
10-05
Caffe2 对git clone后在...\pytorch\scripts中的build_windows.bat进行修改 ...执行 build_windows.bat，成功之后会出现提示信息： "Caffe2 built successfully" 在CAFFE2_ROOT目录下会出现 build文件夹
在windows和ubuntu上面使用caffe
03-13
里面收录了比较全的caffe安装教程，适合初次在Windows或者Ubuntu操作系统下实战caffe的安装，及实战mnist,cifar10数据集的举例博客，是caffe初学者的首选
ubuntu18.04安装caffe-gpu
最新发布
12-08
Ubuntu 18.04 安装 Caffe-GPU 一、环境安装预览 在 Ubuntu 18.04 上安装 Caffe-GPU 需要在 NVIDIA Driver 515.43、CUDA 11.7 和 cuDNN 8.6.0 的环境中进行。在安装之前，需要先安装 NVIDIA Driver 和 CUDA，然后再...
Ubuntu下caffe前期环境配置1
08-03
在Ubuntu系统上安装Caffe深度学习框架之前，首先需要确保你的计算机拥有NVIDIA显卡并正确安装了对应的驱动和CUDA工具包。本篇文章将详细介绍如何在Ubuntu环境下配置这些前期条件。 首先，你需要访问NVIDIA的官方...
论文笔记 OHEM: Training Region-based Object Detectors with Online Hard Example Mining
xiaoxiang_AQ 的博客
10-08 2万+
CVPR2016的文章，CMU与rbg大神的合作。原谅我一直没有对这篇文章做一个笔记~~ 文章提出了一种通过online hard example mining（OHEM）算法训练基于区域的卷积检测算子的高效目标检测算法，能够对简单样本和一些小数量样本进行抑制，使得训练过程更加高效。该方法利用显著的bootstrapping技术（SVM中被普遍利用），对SGD算法进行一定的修改，使得原有的reg
caffe随记（二） --- 数据结构简介
朝花&夕拾
08-03 1626
caffe随记（二） --- 数据结构简介 1、Blob Blob其实从代码的角度看，它是一个模板类。Blob封装了运行时的数据信息（存储、交换和处理网络中正反向传播时的数据和导数信息），并且在CPU和GPU之间具有同步处理的能力。   对于图像处理来说，Blob是一个四维数组，（N, C, H ,W）, 其中N表示图片的数量，C表示图片的通道数，H表示图片的高度， W表示图片
深度学习（五）caffe环境搭建
热门推荐
hjimce的专栏
09-28 5万+
对于caffe的系统一般使用linux系统，当然也有windows版本的caffe，不过如果你一开始使用了windows下面的caffe，后面学习的过程中，会经常遇到各种错误，网上下载的一些源码、模型也往往不能快速的跑起来，因为貌似caffe的官方只提供了linux版本。本篇博文主要讲解快速搭建caffe环境： 电脑系统：ubuntu 14.04 显卡：GTX 850
caffe随记（五）---/build/tools/caffe.bin工具简析
朝花&夕拾
08-06 3750
1、怎么用这个命令   在caffe根目录下输入如下命令：  ./build/tools/caffe.bin, 得到如下显示 usage：caffe # 这个是告诉你使用格式， caffe 后接上 一个command命令，后面再接其他参数   commands： #你能选择的命令有一下这么几种 train #训练或者微调一个模型 test  #对一个模型打分 dev
caffe学习3——layers
weixin_33968104的博客
01-23 57
1 layer是模型的本质，是计算的基本单元。Layers convolve filters, pool, take inner products, apply nonlinearities like rectified-linear and sigmoid and other elementwise transformations, normalize, load data, and compu...
caffe学习系列三添加新的Layer
zhang_shuai12的专栏
09-30 1540
参考：https://github.com/BVLC/caffe/issues/6841、Add a class declaration for your layer to the appropriate one of common_layers.hpp, data_layers.hpp, loss_layers.hpp, neuron_layers.hpp, or vision_layers.hp
Ubuntu和Windows平台上安装Caffe的详细步骤
Caffe 安装指南（Windows 和 Ubuntu） Caffe 是一个流行的深度学习框架，但是在安装时经常会遇到一些问题。因此，本文将提供 Caffe 在 Windows 和 Ubuntu 环境下的安装方法。 Ubuntu 环境下的 Caffe 安装 在 ...

“相关推荐”对你有帮助么？

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值