个人从网络收集资料，本资料共分为九个部分介绍深度神经网络

本人精翻的《X-VECTORS ROBUST DNN EMBEDDINGS FOR SPEAKER RECOGNITION》

LSTM-DNN进行库存预测 修正LSTM模型的股价预测 它能做什么？ 它可以给出一只股票收盘价的预测值。 它不能预测离现在太远，而它所能做的就是预测明天的价格。 我们需要做的是提供一只股票过去的数据。 评估 我用MAPE（平均绝对百分比误差）评估模型。 通过该模型训练的某些股票的最佳性能可使MAPE达到2％-3％，这意味着精度（1-MAPE）可以达到97％-98％。 训练自己的数据 U首先从互联网上下载股票的csv数据，然后在代码中修改csv路线（在最后一栏中输入收盘价）。 学习性能良好的CPU模型需要花费数小时。 有用吗？ 尽管预测第二天的收盘价表现良好，但无法预测接下来的2,3,4 ...天的价格。 因此这可能会有所帮助，可能没有帮助。 未来 我将把我的股票价格预测系统放在github上，它具有许多新功能，包括预处理数据，训练模型，预测价格，评估模型以及推荐高收益股票。 同时

找了好久，费尽心血才找到

opencv深度学习dnn人脸检测模型之tensorflow模型，真的很难找到

很有用的噪声库，可进行语音信号处理的离线仿真测试等 File: Matlab or WAV formats (compressed) sampling rate: 19.98 KHz A/D: 16 bit pre-filter: anti-aliasing filter pre-emphasis: none filter: none duration: 235 sec length (uncompressed): approx 9 Mb (uncompressed) 白噪声：White noise White Noise acquired by sampling high-quality analog noise generator (Wandel & Goltermann). Exhibits equal energy per Hz. bandwidth. 车内噪声：volvo Volvo 340 noise acquired by recording samples from 1/2" B&K condensor microphone onto digital audio tape (DAT). This recording was made at 120 km/h, in 4th gear, on an asphalt road, in rainy conditions. 军用车辆噪音：Military vehicle noise Leopard 2 noise acquired by recording samples from 1/2" B&K condensor microphone onto digital audio tape (DAT). The Leopard 1 vehicle was moving at a speed of 70 km/h. The sound level during the recording process was 114 dBA. 坦克内部噪声:Tank noise M109 noise acquired by recording samples from 1/2" B&K condensor microphone onto digital audio tape (DAT). The M109 tank was moving at a speed of 30 km/h. The sound level during the recording process was 100 dBA. 餐厅内嘈杂噪声：speech babble Voice Babble acquired by recording samples from 1/2" B&K condensor microphone onto digital audio tape (DAT). The source of this babble is 100 people speaking in a canteen. The room radius is over two meters; therefore, individual voices are slightly audible. The sound level during the recording process was 88 dBA. 高频信道噪声：HF channel noise Recording of noise in an HF radio channel after demodulation 粉红噪声：pink noise Pink Noise acquired by sampling high-quality analog noise generator (Wandel & Goltermann). Exhibits equal energy per 1/3 octave. 机枪噪声：Machine gun noise Machine Gun noise acquired by recording samples from 1/2" B&K condensor microphone onto digital audio tape (DAT). The weapon used was a .50 calibre gun fired repeatedly. 工厂车间噪音1：Factory floor noise 1 Factory noise acquired by recording samples from 1/2" B&K condensor

Deep_Neural_Network_Toolkit_&_Event_Spotting_in_Video_using_DNN_features ABIL N GEORGE MASTER OF TECHNOLOGY

bvlc_googlenet.caffemodel，- bvlc_googlenet.prototxt，synset_words

Dnn_pytorch_titanic KaggleのtitanicコンペをPytorchを使用し，DNNで予测を行いました。 公式ページ 起动方法 公式ページでtitanicコンペに参加 そこで，笔记本を作成する。 作成したNotebookに，.pyのコードをコピーし，ノートに贴り付けて実行 ノートにしっかりtantanicのデータが入っているかを确认する。

opencv4.5.0源码对应的文档，避免外网下载出错