┣━mksz259 – 深度学习之神经网络（CNN RNN GAN）算法原理+实战
┣━第5章 卷积神经网络调参
┣━5-7 activation-initializer-optimizer-实战[2].mp4
┣━5-6 fine-tune-实战[2].mp4
┣━5-2 激活函数到调参技巧（1）[2].mp4
┣━5-11 批归一化实战（2）[2].mp4
┣━5-9 图像增强实战[2].mp4
┣━5-3 激活函数到调参技巧（2）[2].mp4
┣━5-1 adagrad_adam[2].mp4
┣━5-4 Tensorboard实战（1）[2].mp4
┣━5-10 批归一化实战（1）[2].mp4
┣━5-4 Tensorboard实战（1） (1)[2].mp4
┣━5-8 图像增强api使用[2].mp4
┣━第6章 图像风格转换
┣━6-8 图像风格转换计算图构建与损失函数计算[2].mp4
┣━6-6 VGG16模型搭建与载入类的封装[2].mp4
┣━6-3 图像风格转换V1算法[2].mp4
┣━6-4 VGG16预训练模型格式[2].mp4
┣━6-1 卷积神经网络的应用[2].mp4
┣━6-12 图像风格转换V3算法[2].mp4
┣━6-5 VGG16预训练模型读取函数封装[2].mp4
┣━6-7 图像风格转换算法定义输入与调用VGG-Net[2].mp4
┣━6-9 图像风格转换训练流程代码实现[2].mp4
┣━6-2 卷积神经网络的能力[2].mp4
┣━6-11 图像风格转换V2算法[2].mp4
┣━6-10 图像风格转换效果展示[2].mp4
┣━第11章 课程总结
┣━11-1 课程总结[2].mp4
┣━第3章 卷积神经网络
┣━3-3 卷积神经网络（2）[2].mp4
┣━3-2 卷积神经网络（1）[2].mp4
┣━3-1 神经网络进阶[2].mp4
┣━3-4 卷积神经网络实战[2].mp4
┣━第1章 课程介绍
┣━1-1 课程导学[2].mp4
┣━第7章 循环神经网络
┣━7-14 计算图实现[2].mp4
┣━7-7 数据预处理之分词[2].mp4
┣━7-12 数据集封装[2].mp4
┣━7-5 基于CNN的文本分类模型(TextCNN)[2].mp4
┣━7-1 序列式问题[2].mp4
┣━7-4 基于LSTM的文本分类模型(TextRNN与HAN)[2].mp4
┣━7-2 循环神经网络[2].mp4
┣━7-17 LSTM单元内部结构实现[2].mp4
┣━7-9 实战代码模块解析[2].mp4
┣━7-11 词表封装与类别封装[2].mp4
┣━7-13 计算图输入定义[2].mp4
┣━7-10 超参数定义[2].mp4
┣━7-3 长短期记忆网络[2].mp4
┣━7-6 RNN与CNN融合解决文本分类[2].mp4
┣━7-18 TextCNN实现[2].mp4
┣━7-15 指标计算与梯度算子实现[2].mp4
┣━7-8 数据预处理之词表生成与类别表生成[2].mp4
┣━7-16 训练流程实现[2].mp4
┣━7-19 循环神经网络总结[2].mp4
┣━第10章 自动机器学习网络-AutoML
┣━10-2 自动网络结构搜索算法一_深度学习之神经网络RNNGAN算法原理实战[2].mp4
┣━10-1 AutoML引入_深度学习之神经网络RNNGAN算法原理实战[2].mp4
┣━10-4 自动网络结构搜索算法二_深度学习之神经网络RNNGAN算法原理实战[2].mp4
┣━10-5 自动网络结构搜索算法三_深度学习之神经网络RNNGAN算法原理实战[2].mp4
┣━10-3 自动网络结构搜索算法一的分布式训练_深度学习之神经网络RNNGAN算法原理实战[2].mp4
┣━第2章 神经网络入门
┣━2-6 数据处理与模型图构建(2)[2].mp4
┣━2-8 神经网络实现（多分类逻辑斯蒂回归模型实现）[2].mp4
┣━2-2 神经元-逻辑斯底回归模型[2].mp4
┣━2-1 机器学习、深度学习简介[2].mp4
┣━2-7 神经元实现（二分类逻辑斯蒂回归模型实现）[2].mp4
┣━2-5 数据处理与模型图构建(1)[2].mp4
┣━2-4 梯度下降[2].mp4
┣━2-3 神经元多输出[2].mp4
┣━第8章 图像生成文本
┣━8-4 Multi-Modal RNN模型[2].mp4
┣━8-1 图像生成文本问题引入⼊[2].mp4
┣━8-16 ImageCaptionData类封装-批数据生成[2].mp4
┣━8-21 文本生成图像问题引入与本节课总结[2].mp4
┣━8-7 Bottom-up Top-down Attention模型[2].mp4
┣━8-8 图像生成文本模型对比与总结[2].mp4
┣━8-20 训练流程代码[2].mp4
┣━8-19 计算图构建-rnn结构实现、损失函数与训练算子实现[2].mp4
┣━8-17 计算图构建-辅助函数实现[2].mp4
┣━8-18 计算图构建-图片与词语embedding[2].mp4
┣━8-2 图像生成文本评测指标[2].mp4
┣━8-10 图像特征抽取(1)-文本描述文件解析[2].mp4
┣━8-3 Encoder-Decoder框架与Beam Search算法生成文本[2].mp4
┣━8-5 Show and Tell模型[2].mp4
┣━8-9 数据介绍，词表生成[2].mp4
┣━8-15 ImageCaptionData类封装-图片特征读取[2].mp4
┣━8-11 图像特征抽取(2)-InceptionV3预训练模型抽取图像特征[2].mp4
┣━8-12 输入输出文件与默认参数定义[2].mp4
┣━8-13 词表载入(www.itzixue.top)[2].mp4
┣━8-14 文本描述转换为ID表示[2].mp4
┣━8-6 Show attend and Tell 模型[2].mp4
┣━课程资料
┣━image_caption_data代码
┣━checkpoint_inception_v3
┣━inception-2015-12-05.tgz
┣━imagenet_synset_to_human_label_map.txt
┣━imagenet_2012_challenge_label_map_proto.pbtxt
┣━cropped_panda.jpg
┣━LICENSE
┣━inception_v3_graph_def.pb
┣━feature_extraction_inception_v3
┣━image_features-30.pickle
┣━image_features-24.pickle
┣━image_features-20.pickle
┣━image_features-18.pickle
┣━image_features-10.pickle
┣━image_features-26.pickle
┣━image_features-31.pickle
┣━image_features-25.pickle
┣━image_features-2.pickle
┣━image_features-19.pickle
┣━image_features-16.pickle
┣━image_features-29.pickle
┣━image_features-28.pickle
┣━image_features-6.pickle
┣━image_features-14.pickle
┣━image_features-9.pickle
┣━image_features-17.pickle
┣━image_features-4.pickle
┣━image_features-8.pickle
┣━image_features-23.pickle
┣━image_features-1.pickle
┣━image_features-27.pickle
┣━image_features-11.pickle
┣━image_features-22.pickle
┣━image_features-3.pickle
┣━image_features-15.pickle
┣━image_features-0.pickle
┣━image_features-13.pickle
┣━image_features-12.pickle
┣━image_features-7.pickle
┣━image_features-5.pickle
┣━image_features-21.pickle
┣━results_20130124.token
┣━vocab.txt
┣━课程数据代码
┣━text_classification_data
┣━.ipynb_checkpoints
┣━pre-processing-checkpoint.ipynb
┣━cnews.test.txt
┣━cnews.train.txt
┣━cnews.val.txt
┣━cifar-10-batches-py
┣━test_batch
┣━data_batch_4
┣━readme.html
┣━data_batch_1
┣━batches.meta
┣━data_batch_5
┣━data_batch_3
┣━data_batch_2
┣━image_caption_data
┣━results_20130124.token
┣━feature_extraction_inception_v3
┣━image_features-27.pickle
┣━image_features-19.pickle
┣━image_features-12.pickle
┣━image_features-21.pickle
┣━image_features-10.pickle
┣━image_features-18.pickle
┣━image_features-24.pickle
┣━image_features-1.pickle
┣━image_features-29.pickle
┣━image_features-2.pickle
┣━image_features-31.pickle
┣━image_features-5.pickle
┣━image_features-6.pickle
┣━image_features-23.pickle
┣━image_features-7.pickle
┣━image_features-15.pickle
┣━image_features-14.pickle
┣━image_features-25.pickle
┣━image_features-26.pickle
┣━image_features-30.pickle
┣━image_features-0.pickle
┣━image_features-8.pickle
┣━image_features-13.pickle
┣━image_features-20.pickle
┣━image_features-4.pickle
┣━image_features-11.pickle
┣━image_features-3.pickle
┣━image_features-9.pickle
┣━image_features-16.pickle
┣━image_features-17.pickle
┣━image_features-22.pickle
┣━image_features-28.pickle
┣━checkpoint_inception_v3
┣━LICENSE
┣━cropped_panda.jpg
┣━inception_v3_graph_def.pb
┣━imagenet_2012_challenge_label_map_proto.pbtxt
┣━inception-2015-12-05.tgz
┣━imagenet_synset_to_human_label_map.txt
┣━vocab.txt
┣━style_transfer_data
┣━xingkong.jpeg
┣━gugong.jpg
┣━vgg16.npy
┣━资料
┣━coding-259-master.zip
┣━神经网络常用算法.zip
┣━第9章 对抗神经网络
┣━9-5 图像翻译Pix2Pix_深度学习之神经网络RNNGAN算法原理实战[2].mp4
┣━9-12 数据生成器实现_深度学习之神经网络RNNGAN算法原理实战[2].mp4
┣━9-11 DCGAN实战引⼊——www.itzixue.top[2].mp4
┣━9-10 对抗生成网络总结_深度学习之神经网络RNNGAN算法原理实战[2].mp4
┣━9-2 深度卷积对抗生成网络DCGAN(1)[2].mp4
┣━9-3 反卷积[2].mp4
┣━9-13 DCGAN生成器器实现[2].mp4
┣━9-15 DCGAN计算图构建实现与损失函数实现_深度学习之神经网络RNNGAN算法原理实战[2].mp4
┣━9-8 多领域图像翻译StarGAN_深度学习之神经网络RNNGAN算法原理实战[2].mp4
┣━9-9 文本生成图像Text2Img_深度学习之神经网络RNNGAN算法原理实战[2].mp4
┣━9-14 DCGAN判别器实现[2].mp4
┣━9-7 无配对图像翻译CycleGAN(2)_深度学习之神经网络RNNGAN算法原理实战[2].mp4
┣━9-6 无配对图像翻译CycleGAN(1)_深度学习之神经网络RNNGAN算法原理实战[2].mp4
┣━9-17 训练流程实现与效果展示_深度学习之神经网络RNNGAN算法原理实战[2].mp4
┣━9-4 深度卷积对抗生成网络DCGAN(2)_深度学习之神经网络RNNGAN算法原理实战[2].mp4
┣━9-1 对抗生成网络原理[2].mp4
┣━9-16 DCGAN训练算子实现_深度学习之神经网络RNNGAN算法原理实战[2].mp4
┣━第4章 卷积神经网络进阶
┣━4-7 Inception-mobile_net（2）[2].mp4
┣━4-2 卷积神经网络进阶（Vggnet-Resnet）[2].mp4
┣━4-6 Inception-mobile_net（1）[2].mp4
┣━4-1 卷积神经网络进阶（alexnet）[2].mp4
┣━4-3 卷积神经网络进阶（inception-mobile-net）[2].mp4
┣━4-4 VGG-ResNet实战（1）[2].mp4
┣━4-5 VGG-ResNet实战（2）[2].mp4
评论1