人工智能下载列表第806页

[机器学习] images.rar

说明：演示 findContours 对于亮背景和暗背景处理方式的不一样
<brooknew> 上传 | 大小：18kb

[深度学习] mnist_mxnet.zip

说明：基于MXNet深度学习框架，定义CNN模型，训练手写数字识别数据，得到较高的准确率。这是一个基础的深度学习分类任务，值得借鉴。
<oliver0047> 上传 | 大小：11mb

[深度学习] facenet源码、flw库

说明：facenet源码，facenet无需限制人脸对齐，但是代码中提供了MTCNN的对齐，而且在LFW评分中也发现经过对齐的分数能够提高一个档次。利用提供的代码，在LFW上进行EVAL，发现其精度高达99.2%
<maxinezhou> 上传 | 大小：182mb

[深度学习] vesely_interspeech2013_IS131333.pdf

说明：Sequence-discriminative training of deep neural networks
<vincent1941> 上传 | 大小：132kb

[机器学习] Weighted Finite-State Transducers Important Algorithms

说明：Weighted Finite-State Transducers Important Algorithms University of Tokyomonoid Is an algebr Semirings () structure that supports a sin associative binary operation and identity element. (wikipedia) WFSTs and WfSt-based operations are underpinned b
<vincent1941> 上传 | 大小：9mb

[深度学习] Hybrid LSTM-FSMN Networks for Acoustic Modeling.pdf

说明：Contextual information is key to training acoustic models. Recursive neural networks (RNNs) such as Long short term memory (LSTMs) are context-aware due to their recurrence mechanism, and usually outperform conventional neural networks. Connectioni
<zhang_zhen_yu> 上传 | 大小：265kb

[深度学习] A Survey of the Recent Architectures of Deep Convolutional Neural Networks.pdf

说明：Deep Convolutional Neural Networks (CNNs) are a special type of Neural Networks, which have shown state-of-the-art results on various competitive benchmarks. The powerful learning ability of deep CNN is largely achieved with the use of multiple fea
<zhang_zhen_yu> 上传 | 大小：944kb

[深度学习] coco_ssd_mobilenet_v1_1.0_quant_2018_06_29.zip

说明：tensorflow lite example 中的object_detection资源文件，下载后放到app下的build下的zips中，同时修改download_model.gradle文件，屏蔽task downloadZipFile,并把task downloadAndUnzipFile 中的 from zipTree(downloadZipFile.dest) 修改为 from zipTree(new File(buildDir, 'zips/coco_ssd_mobilenet_v1
<seeyouagen> 上传 | 大小：2mb