206 skills found · Page 1 of 7
fighting41love / FunNLP中英文敏感词、语言检测、中外手机/电话归属地/运营商查询、名字推断性别、手机号抽取、身份证抽取、邮箱抽取、中日文人名库、中文缩写库、拆字词典、词汇情感值、停用词、反动词表、暴恐词表、繁简体转换、英文模拟中文发音、汪峰歌词生成器、职业名称词库、同义词库、反义词库、否定词库、汽车品牌词库、汽车零件词库、连续英文切割、各种中文词向量、公司名字大全、古诗词库、IT词库、财经词库、成语词库、地名词库、历史名人词库、诗词词库、医学词库、饮食词库、法律词库、汽车词库、动物词库、中文聊天语料、中文谣言数据、百度中文问答数据集、句子相似度匹配算法集合、bert资源、文本生成&摘要相关工具、cocoNLP信息抽取工具、国内电话号码正则匹配、清华大学XLORE:中英文跨语言百科知识图谱、清华大学人工智能技术系列报告、自然语言生成、NLU太难了系列、自动对联数据及机器人、用户名黑名单列表、罪名法务名词及分类模型、微信公众号语料、cs224n深度学习自然语言处理课程、中文手写汉字识别、中文自然语言处理 语料/数据集、变量命名神器、分词语料库+代码、任务型对话英文数据集、ASR 语音数据集 + 基于深度学习的中文语音识别系统、笑声检测器、Microsoft多语言数字/单位/如日期时间识别包、中华新华字典数据库及api(包括常用歇后语、成语、词语和汉字)、文档图谱自动生成、SpaCy 中文模型、Common Voice语音识别数据集新版、神经网络关系抽取、基于bert的命名实体识别、关键词(Keyphrase)抽取包pke、基于医疗领域知识图谱的问答系统、基于依存句法与语义角色标注的事件三元组抽取、依存句法分析4万句高质量标注数据、cnocr：用来做中文OCR的Python3包、中文人物关系知识图谱项目、中文nlp竞赛项目及代码汇总、中文字符数据、speech-aligner: 从“人声语音”及其“语言文本”产生音素级别时间对齐标注的工具、AmpliGraph: 知识图谱表示学习(Python)库：知识图谱概念链接预测、Scattertext 文本可视化(python)、语言/知识表示工具：BERT & ERNIE、中文对比英文自然语言处理NLP的区别综述、Synonyms中文近义词工具包、HarvestText领域自适应文本挖掘工具（新词发现-情感分析-实体链接等）、word2word：(Python)方便易用的多语言词-词对集：62种语言/3,564个多语言对、语音识别语料生成工具：从具有音频/字幕的在线视频创建自动语音识别(ASR)语料库、构建医疗实体识别的模型（包含词典和语料标注）、单文档非监督的关键词抽取、Kashgari中使用gpt-2语言模型、开源的金融投资数据提取工具、文本自动摘要库TextTeaser: 仅支持英文、人民日报语料处理工具集、一些关于自然语言的基本模型、基于14W歌曲知识库的问答尝试--功能包括歌词接龙and已知歌词找歌曲以及歌曲歌手歌词三角关系的问答、基于Siamese bilstm模型的相似句子判定模型并提供训练数据集和测试数据集、用Transformer编解码模型实现的根据Hacker News文章标题自动生成评论、用BERT进行序列标记和文本分类的模板代码、LitBank：NLP数据集——支持自然语言处理和计算人文学科任务的100部带标记英文小说语料、百度开源的基准信息抽取系统、虚假新闻数据集、Facebook: LAMA语言模型分析，提供Transformer-XL/BERT/ELMo/GPT预训练语言模型的统一访问接口、CommonsenseQA：面向常识的英文QA挑战、中文知识图谱资料、数据及工具、各大公司内部里大牛分享的技术文档 PDF 或者 PPT、自然语言生成SQL语句（英文）、中文NLP数据增强（EDA）工具、英文NLP数据增强工具 、基于医药知识图谱的智能问答系统、京东商品知识图谱、基于mongodb存储的军事领域知识图谱问答项目、基于远监督的中文关系抽取、语音情感分析、中文ULMFiT-情感分析-文本分类-语料及模型、一个拍照做题程序、世界各国大规模人名库、一个利用有趣中文语料库 qingyun 训练出来的中文聊天机器人、中文聊天机器人seqGAN、省市区镇行政区划数据带拼音标注、教育行业新闻语料库包含自动文摘功能、开放了对话机器人-知识图谱-语义理解-自然语言处理工具及数据、中文知识图谱：基于百度百科中文页面-抽取三元组信息-构建中文知识图谱、masr: 中文语音识别-提供预训练模型-高识别率、Python音频数据增广库、中文全词覆盖BERT及两份阅读理解数据、ConvLab：开源多域端到端对话系统平台、中文自然语言处理数据集、基于最新版本rasa搭建的对话系统、基于TensorFlow和BERT的管道式实体及关系抽取、一个小型的证券知识图谱/知识库、复盘所有NLP比赛的TOP方案、OpenCLaP：多领域开源中文预训练语言模型仓库、UER：基于不同语料+编码器+目标任务的中文预训练模型仓库、中文自然语言处理向量合集、基于金融-司法领域(兼有闲聊性质)的聊天机器人、g2pC：基于上下文的汉语读音自动标记模块、Zincbase 知识图谱构建工具包、诗歌质量评价/细粒度情感诗歌语料库、快速转化「中文数字」和「阿拉伯数字」、百度知道问答语料库、基于知识图谱的问答系统、jieba_fast 加速版的jieba、正则表达式教程、中文阅读理解数据集、基于BERT等最新语言模型的抽取式摘要提取、Python利用深度学习进行文本摘要的综合指南、知识图谱深度学习相关资料整理、维基大规模平行文本语料、StanfordNLP 0.2.0：纯Python版自然语言处理包、NeuralNLP-NeuralClassifier：腾讯开源深度学习文本分类工具、端到端的封闭域对话系统、中文命名实体识别：NeuroNER vs. BertNER、新闻事件线索抽取、2019年百度的三元组抽取比赛：“科学空间队”源码、基于依存句法的开放域文本知识三元组抽取和知识库构建、中文的GPT2训练代码、ML-NLP - 机器学习(Machine Learning)NLP面试中常考到的知识点和代码实现、nlp4han:中文自然语言处理工具集(断句/分词/词性标注/组块/句法分析/语义分析/NER/N元语法/HMM/代词消解/情感分析/拼写检查、XLM：Facebook的跨语言预训练语言模型、用基于BERT的微调和特征提取方法来进行知识图谱百度百科人物词条属性抽取、中文自然语言处理相关的开放任务-数据集-当前最佳结果、CoupletAI - 基于CNN+Bi-LSTM+Attention 的自动对对联系统、抽象知识图谱、MiningZhiDaoQACorpus - 580万百度知道问答数据挖掘项目、brat rapid annotation tool: 序列标注工具、大规模中文知识图谱数据：1.4亿实体、数据增强在机器翻译及其他nlp任务中的应用及效果、allennlp阅读理解:支持多种数据和模型、PDF表格数据提取工具 、 Graphbrain：AI开源软件库和科研工具，目的是促进自动意义提取和文本理解以及知识的探索和推断、简历自动筛选系统、基于命名实体识别的简历自动摘要、中文语言理解测评基准，包括代表性的数据集&基准模型&语料库&排行榜、树洞 OCR 文字识别 、从包含表格的扫描图片中识别表格和文字、语声迁移、Python口语自然语言处理工具集(英文)、 similarity：相似度计算工具包，java编写、海量中文预训练ALBERT模型 、Transformers 2.0 、基于大规模音频数据集Audioset的音频增强 、Poplar：网页版自然语言标注工具、图片文字去除，可用于漫画翻译 、186种语言的数字叫法库、Amazon发布基于知识的人-人开放领域对话数据集 、中文文本纠错模块代码、繁简体转换 、 Python实现的多种文本可读性评价指标、类似于人名/地名/组织机构名的命名体识别数据集 、东南大学《知识图谱》研究生课程(资料)、. 英文拼写检查库 、 wwsearch是企业微信后台自研的全文检索引擎、CHAMELEON：深度学习新闻推荐系统元架构 、 8篇论文梳理BERT相关模型进展与反思、DocSearch：免费文档搜索引擎、 LIDA：轻量交互式对话标注工具 、aili - the fastest in-memory index in the East 东半球最快并发索引 、知识图谱车音工作项目、自然语言生成资源大全 、中日韩分词库mecab的Python接口库、中文文本摘要/关键词提取、汉字字符特征提取器 (featurizer)，提取汉字的特征（发音特征、字形特征）用做深度学习的特征、中文生成任务基准测评 、中文缩写数据集、中文任务基准测评 - 代表性的数据集-基准(预训练)模型-语料库-baseline-工具包-排行榜、PySS3：面向可解释AI的SS3文本分类器机器可视化工具 、中文NLP数据集列表、COPE - 格律诗编辑程序、doccano：基于网页的开源协同多语言文本标注工具 、PreNLP：自然语言预处理库、简单的简历解析器，用来从简历中提取关键信息、用于中文闲聊的GPT2模型：GPT2-chitchat、基于检索聊天机器人多轮响应选择相关资源列表(Leaderboards、Datasets、Papers)、(Colab)抽象文本摘要实现集锦(教程 、词语拼音数据、高效模糊搜索工具、NLP数据增广资源集、微软对话机器人框架 、 GitHub Typo Corpus：大规模GitHub多语言拼写错误/语法错误数据集、TextCluster：短文本聚类预处理模块 Short text cluster、面向语音识别的中文文本规范化、BLINK：最先进的实体链接库、BertPunc：基于BERT的最先进标点修复模型、Tokenizer：快速、可定制的文本词条化库、中文语言理解测评基准，包括代表性的数据集、基准(预训练)模型、语料库、排行榜、spaCy 医学文本挖掘与信息提取 、 NLP任务示例项目代码集、 python拼写检查库、chatbot-list - 行业内关于智能客服、聊天机器人的应用和架构、算法分享和介绍、语音质量评价指标(MOSNet, BSSEval, STOI, PESQ, SRMR)、 用138GB语料训练的法文RoBERTa预训练语言模型 、BERT-NER-Pytorch：三种不同模式的BERT中文NER实验、无道词典 - 有道词典的命令行版本，支持英汉互查和在线查询、2019年NLP亮点回顾、 Chinese medical dialogue data 中文医疗对话数据集 、最好的汉字数字(中文数字)-阿拉伯数字转换工具、 基于百科知识库的中文词语多词义/义项获取与特定句子词语语义消歧、awesome-nlp-sentiment-analysis - 情感分析、情绪原因识别、评价对象和评价词抽取、LineFlow：面向所有深度学习框架的NLP数据高效加载器、中文医学NLP公开资源整理 、MedQuAD：(英文)医学问答数据集、将自然语言数字串解析转换为整数和浮点数、Transfer Learning in Natural Language Processing (NLP) 、面向语音识别的中文/英文发音辞典、Tokenizers：注重性能与多功能性的最先进分词器、CLUENER 细粒度命名实体识别 Fine Grained Named Entity Recognition、 基于BERT的中文命名实体识别、中文谣言数据库、NLP数据集/基准任务大列表、nlp相关的一些论文及代码, 包括主题模型、词向量(Word Embedding)、命名实体识别(NER)、文本分类(Text Classificatin)、文本生成(Text Generation)、文本相似性(Text Similarity)计算等，涉及到各种与nlp相关的算法，基于keras和tensorflow 、Python文本挖掘/NLP实战示例、 Blackstone：面向非结构化法律文本的spaCy pipeline和NLP模型通过同义词替换实现文本“变脸” 、中文 预训练 ELECTREA 模型: 基于对抗学习 pretrain Chinese Model 、albert-chinese-ner - 用预训练语言模型ALBERT做中文NER 、基于GPT2的特定主题文本生成/文本增广、开源预训练语言模型合集、多语言句向量包、编码、标记和实现：一种可控高效的文本生成方法、 英文脏话大列表 、attnvis：GPT2、BERT等transformer语言模型注意力交互可视化、CoVoST：Facebook发布的多语种语音-文本翻译语料库，包括11种语言(法语、德语、荷兰语、俄语、西班牙语、意大利语、土耳其语、波斯语、瑞典语、蒙古语和中文)的语音、文字转录及英文译文、Jiagu自然语言处理工具 - 以BiLSTM等模型为基础，提供知识图谱关系抽取 中文分词 词性标注 命名实体识别 情感分析 新词发现 关键词 文本摘要 文本聚类等功能、用unet实现对文档表格的自动检测，表格重建、NLP事件提取文献资源列表 、 金融领域自然语言处理研究资源大列表、CLUEDatasetSearch - 中英文NLP数据集：搜索所有中文NLP数据集，附常用英文NLP数据集 、medical_NER - 中文医学知识图谱命名实体识别 、(哈佛)讲因果推理的免费书、知识图谱相关学习资料/数据集/工具资源大列表、Forte：灵活强大的自然语言处理pipeline工具集 、Python字符串相似性算法库、PyLaia：面向手写文档分析的深度学习工具包、TextFooler：针对文本分类/推理的对抗文本生成模块、Haystack：灵活、强大的可扩展问答(QA)框架、中文关键短语抽取工具
borisbanushev / StockpredictionaiIn this noteboook I will create a complete process for predicting stock price movements. Follow along and we will achieve some pretty good results. For that purpose we will use a Generative Adversarial Network (GAN) with LSTM, a type of Recurrent Neural Network, as generator, and a Convolutional Neural Network, CNN, as a discriminator. We use LSTM for the obvious reason that we are trying to predict time series data. Why we use GAN and specifically CNN as a discriminator? That is a good question: there are special sections on that later.
ankitaggarwal011 / PyCNNImage Processing with Cellular Neural Networks in Python
btgraham / SparseConvNet ArchivedSpatially-sparse convolutional networks. Allows processing of sparse 2, 3 and 4 dimensional data.Build CNNs on the square/cubic/hypercubic or triangular/tetrahedral/hyper-tetrahedral lattices.
Mycenae / PaperWeeklyPapers for CNN, object detection, keypoint detection, semantic segmentation, medical image processing, SLAM, etc.
yukitsuji / 3D CNN TensorflowKITTI data processing and 3D CNN for Vehicle Detection
1nfinityLoop / Sudoku Solver AII made a real time Sudoku solver using the camera, it looks for the edges of the Sudoku in the frame, extracts it, solves it and overlays the solution on the puzzle itself. For the digit recognition, I used a CNN, trained using Keras with printed characters from the different ubuntu fonts. For the image processing part, I used OpenCV for the edge detection.
molyswu / Hand Detectionusing Neural Networks (SSD) on Tensorflow. This repo documents steps and scripts used to train a hand detector using Tensorflow (Object Detection API). As with any DNN based task, the most expensive (and riskiest) part of the process has to do with finding or creating the right (annotated) dataset. I was interested mainly in detecting hands on a table (egocentric view point). I experimented first with the [Oxford Hands Dataset](http://www.robots.ox.ac.uk/~vgg/data/hands/) (the results were not good). I then tried the [Egohands Dataset](http://vision.soic.indiana.edu/projects/egohands/) which was a much better fit to my requirements. The goal of this repo/post is to demonstrate how neural networks can be applied to the (hard) problem of tracking hands (egocentric and other views). Better still, provide code that can be adapted to other uses cases. If you use this tutorial or models in your research or project, please cite [this](#citing-this-tutorial). Here is the detector in action. <img src="images/hand1.gif" width="33.3%"><img src="images/hand2.gif" width="33.3%"><img src="images/hand3.gif" width="33.3%"> Realtime detection on video stream from a webcam . <img src="images/chess1.gif" width="33.3%"><img src="images/chess2.gif" width="33.3%"><img src="images/chess3.gif" width="33.3%"> Detection on a Youtube video. Both examples above were run on a macbook pro **CPU** (i7, 2.5GHz, 16GB). Some fps numbers are: | FPS | Image Size | Device| Comments| | ------------- | ------------- | ------------- | ------------- | | 21 | 320 * 240 | Macbook pro (i7, 2.5GHz, 16GB) | Run without visualizing results| | 16 | 320 * 240 | Macbook pro (i7, 2.5GHz, 16GB) | Run while visualizing results (image above) | | 11 | 640 * 480 | Macbook pro (i7, 2.5GHz, 16GB) | Run while visualizing results (image above) | > Note: The code in this repo is written and tested with Tensorflow `1.4.0-rc0`. Using a different version may result in [some errors](https://github.com/tensorflow/models/issues/1581). You may need to [generate your own frozen model](https://pythonprogramming.net/testing-custom-object-detector-tensorflow-object-detection-api-tutorial/?completed=/training-custom-objects-tensorflow-object-detection-api-tutorial/) graph using the [model checkpoints](model-checkpoint) in the repo to fit your TF version. **Content of this document** - Motivation - Why Track/Detect hands with Neural Networks - Data preparation and network training in Tensorflow (Dataset, Import, Training) - Training the hand detection Model - Using the Detector to Detect/Track hands - Thoughts on Optimizations. > P.S if you are using or have used the models provided here, feel free to reach out on twitter ([@vykthur](https://twitter.com/vykthur)) and share your work! ## Motivation - Why Track/Detect hands with Neural Networks? There are several existing approaches to tracking hands in the computer vision domain. Incidentally, many of these approaches are rule based (e.g extracting background based on texture and boundary features, distinguishing between hands and background using color histograms and HOG classifiers,) making them not very robust. For example, these algorithms might get confused if the background is unusual or in situations where sharp changes in lighting conditions cause sharp changes in skin color or the tracked object becomes occluded.(see [here for a review](https://www.cse.unr.edu/~bebis/handposerev.pdf) paper on hand pose estimation from the HCI perspective) With sufficiently large datasets, neural networks provide opportunity to train models that perform well and address challenges of existing object tracking/detection algorithms - varied/poor lighting, noisy environments, diverse viewpoints and even occlusion. The main drawbacks to usage for real-time tracking/detection is that they can be complex, are relatively slow compared to tracking-only algorithms and it can be quite expensive to assemble a good dataset. But things are changing with advances in fast neural networks. Furthermore, this entire area of work has been made more approachable by deep learning frameworks (such as the tensorflow object detection api) that simplify the process of training a model for custom object detection. More importantly, the advent of fast neural network models like ssd, faster r-cnn, rfcn (see [here](https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md#coco-trained-models-coco-models) ) etc make neural networks an attractive candidate for real-time detection (and tracking) applications. Hopefully, this repo demonstrates this. > If you are not interested in the process of training the detector, you can skip straight to applying the [pretrained model I provide in detecting hands](#detecting-hands). Training a model is a multi-stage process (assembling dataset, cleaning, splitting into training/test partitions and generating an inference graph). While I lightly touch on the details of these parts, there are a few other tutorials cover training a custom object detector using the tensorflow object detection api in more detail[ see [here](https://pythonprogramming.net/training-custom-objects-tensorflow-object-detection-api-tutorial/) and [here](https://towardsdatascience.com/how-to-train-your-own-object-detector-with-tensorflows-object-detector-api-bec72ecfe1d9) ]. I recommend you walk through those if interested in training a custom object detector from scratch. ## Data preparation and network training in Tensorflow (Dataset, Import, Training) **The Egohands Dataset** The hand detector model is built using data from the [Egohands Dataset](http://vision.soic.indiana.edu/projects/egohands/) dataset. This dataset works well for several reasons. It contains high quality, pixel level annotations (>15000 ground truth labels) where hands are located across 4800 images. All images are captured from an egocentric view (Google glass) across 48 different environments (indoor, outdoor) and activities (playing cards, chess, jenga, solving puzzles etc). <img src="images/egohandstrain.jpg" width="100%"> If you will be using the Egohands dataset, you can cite them as follows: > Bambach, Sven, et al. "Lending a hand: Detecting hands and recognizing activities in complex egocentric interactions." Proceedings of the IEEE International Conference on Computer Vision. 2015. The Egohands dataset (zip file with labelled data) contains 48 folders of locations where video data was collected (100 images per folder). ``` -- LOCATION_X -- frame_1.jpg -- frame_2.jpg ... -- frame_100.jpg -- polygons.mat // contains annotations for all 100 images in current folder -- LOCATION_Y -- frame_1.jpg -- frame_2.jpg ... -- frame_100.jpg -- polygons.mat // contains annotations for all 100 images in current folder ``` **Converting data to Tensorflow Format** Some initial work needs to be done to the Egohands dataset to transform it into the format (`tfrecord`) which Tensorflow needs to train a model. This repo contains `egohands_dataset_clean.py` a script that will help you generate these csv files. - Downloads the egohands datasets - Renames all files to include their directory names to ensure each filename is unique - Splits the dataset into train (80%), test (10%) and eval (10%) folders. - Reads in `polygons.mat` for each folder, generates bounding boxes and visualizes them to ensure correctness (see image above). - Once the script is done running, you should have an images folder containing three folders - train, test and eval. Each of these folders should also contain a csv label document each - `train_labels.csv`, `test_labels.csv` that can be used to generate `tfrecords` Note: While the egohands dataset provides four separate labels for hands (own left, own right, other left, and other right), for my purpose, I am only interested in the general `hand` class and label all training data as `hand`. You can modify the data prep script to generate `tfrecords` that support 4 labels. Next: convert your dataset + csv files to tfrecords. A helpful guide on this can be found [here](https://pythonprogramming.net/creating-tfrecord-files-tensorflow-object-detection-api-tutorial/).For each folder, you should be able to generate `train.record`, `test.record` required in the training process. ## Training the hand detection Model Now that the dataset has been assembled (and your tfrecords), the next task is to train a model based on this. With neural networks, it is possible to use a process called [transfer learning](https://www.tensorflow.org/tutorials/image_retraining) to shorten the amount of time needed to train the entire model. This means we can take an existing model (that has been trained well on a related domain (here image classification) and retrain its final layer(s) to detect hands for us. Sweet!. Given that neural networks sometimes have thousands or millions of parameters that can take weeks or months to train, transfer learning helps shorten training time to possibly hours. Tensorflow does offer a few models (in the tensorflow [model zoo](https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md#coco-trained-models-coco-models)) and I chose to use the `ssd_mobilenet_v1_coco` model as my start point given it is currently (one of) the fastest models (read the SSD research [paper here](https://arxiv.org/pdf/1512.02325.pdf)). The training process can be done locally on your CPU machine which may take a while or better on a (cloud) GPU machine (which is what I did). For reference, training on my macbook pro (tensorflow compiled from source to take advantage of the mac's cpu architecture) the maximum speed I got was 5 seconds per step as opposed to the ~0.5 seconds per step I got with a GPU. For reference it would take about 12 days to run 200k steps on my mac (i7, 2.5GHz, 16GB) compared to ~5hrs on a GPU. > **Training on your own images**: Please use the [guide provided by Harrison from pythonprogramming](https://pythonprogramming.net/training-custom-objects-tensorflow-object-detection-api-tutorial/) on how to generate tfrecords given your label csv files and your images. The guide also covers how to start the training process if training locally. [see [here] (https://pythonprogramming.net/training-custom-objects-tensorflow-object-detection-api-tutorial/)]. If training in the cloud using a service like GCP, see the [guide here](https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/running_on_cloud.md). As the training process progresses, the expectation is that total loss (errors) gets reduced to its possible minimum (about a value of 1 or thereabout). By observing the tensorboard graphs for total loss(see image below), it should be possible to get an idea of when the training process is complete (total loss does not decrease with further iterations/steps). I ran my training job for 200k steps (took about 5 hours) and stopped at a total Loss (errors) value of 2.575.(In retrospect, I could have stopped the training at about 50k steps and gotten a similar total loss value). With tensorflow, you can also run an evaluation concurrently that assesses your model to see how well it performs on the test data. A commonly used metric for performance is mean average precision (mAP) which is single number used to summarize the area under the precision-recall curve. mAP is a measure of how well the model generates a bounding box that has at least a 50% overlap with the ground truth bounding box in our test dataset. For the hand detector trained here, the mAP value was **0.9686@0.5IOU**. mAP values range from 0-1, the higher the better. <img src="images/accuracy.jpg" width="100%"> Once training is completed, the trained inference graph (`frozen_inference_graph.pb`) is then exported (see the earlier referenced guides for how to do this) and saved in the `hand_inference_graph` folder. Now its time to do some interesting detection. ## Using the Detector to Detect/Track hands If you have not done this yet, please following the guide on installing [Tensorflow and the Tensorflow object detection api](https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/installation.md). This will walk you through setting up the tensorflow framework, cloning the tensorflow github repo and a guide on - Load the `frozen_inference_graph.pb` trained on the hands dataset as well as the corresponding label map. In this repo, this is done in the `utils/detector_utils.py` script by the `load_inference_graph` method. ```python detection_graph = tf.Graph() with detection_graph.as_default(): od_graph_def = tf.GraphDef() with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid: serialized_graph = fid.read() od_graph_def.ParseFromString(serialized_graph) tf.import_graph_def(od_graph_def, name='') sess = tf.Session(graph=detection_graph) print("> ====== Hand Inference graph loaded.") ``` - Detect hands. In this repo, this is done in the `utils/detector_utils.py` script by the `detect_objects` method. ```python (boxes, scores, classes, num) = sess.run( [detection_boxes, detection_scores, detection_classes, num_detections], feed_dict={image_tensor: image_np_expanded}) ``` - Visualize detected bounding detection_boxes. In this repo, this is done in the `utils/detector_utils.py` script by the `draw_box_on_image` method. This repo contains two scripts that tie all these steps together. - detect_multi_threaded.py : A threaded implementation for reading camera video input detection and detecting. Takes a set of command line flags to set parameters such as `--display` (visualize detections), image parameters `--width` and `--height`, videe `--source` (0 for camera) etc. - detect_single_threaded.py : Same as above, but single threaded. This script works for video files by setting the video source parameter videe `--source` (path to a video file). ```cmd # load and run detection on video at path "videos/chess.mov" python detect_single_threaded.py --source videos/chess.mov ``` > Update: If you do have errors loading the frozen inference graph in this repo, feel free to generate a new graph that fits your TF version from the model-checkpoint in this repo. Use the [export_inference_graph.py](https://github.com/tensorflow/models/blob/master/research/object_detection/export_inference_graph.py) script provided in the tensorflow object detection api repo. More guidance on this [here](https://pythonprogramming.net/testing-custom-object-detector-tensorflow-object-detection-api-tutorial/?completed=/training-custom-objects-tensorflow-object-detection-api-tutorial/). ## Thoughts on Optimization. A few things that led to noticeable performance increases. - Threading: Turns out that reading images from a webcam is a heavy I/O event and if run on the main application thread can slow down the program. I implemented some good ideas from [Adrian Rosebuck](https://www.pyimagesearch.com/2017/02/06/faster-video-file-fps-with-cv2-videocapture-and-opencv/) on parrallelizing image capture across multiple worker threads. This mostly led to an FPS increase of about 5 points. - For those new to Opencv, images from the `cv2.read()` method return images in [BGR format](https://www.learnopencv.com/why-does-opencv-use-bgr-color-format/). Ensure you convert to RGB before detection (accuracy will be much reduced if you dont). ```python cv2.cvtColor(image_np, cv2.COLOR_BGR2RGB) ``` - Keeping your input image small will increase fps without any significant accuracy drop.(I used about 320 x 240 compared to the 1280 x 720 which my webcam provides). - Model Quantization. Moving from the current 32 bit to 8 bit can achieve up to 4x reduction in memory required to load and store models. One way to further speed up this model is to explore the use of [8-bit fixed point quantization](https://heartbeat.fritz.ai/8-bit-quantization-and-tensorflow-lite-speeding-up-mobile-inference-with-low-precision-a882dfcafbbd). Performance can also be increased by a clever combination of tracking algorithms with the already decent detection and this is something I am still experimenting with. Have ideas for optimizing better, please share! <img src="images/general.jpg" width="100%"> Note: The detector does reflect some limitations associated with the training set. This includes non-egocentric viewpoints, very noisy backgrounds (e.g in a sea of hands) and sometimes skin tone. There is opportunity to improve these with additional data. ## Integrating Multiple DNNs. One way to make things more interesting is to integrate our new knowledge of where "hands" are with other detectors trained to recognize other objects. Unfortunately, while our hand detector can in fact detect hands, it cannot detect other objects (a factor or how it is trained). To create a detector that classifies multiple different objects would mean a long involved process of assembling datasets for each class and a lengthy training process. > Given the above, a potential strategy is to explore structures that allow us **efficiently** interleave output form multiple pretrained models for various object classes and have them detect multiple objects on a single image. An example of this is with my primary use case where I am interested in understanding the position of objects on a table with respect to hands on same table. I am currently doing some work on a threaded application that loads multiple detectors and outputs bounding boxes on a single image. More on this soon.
hungchun-lin / Stock Price Prediction Using GANIn this project, we will compare two algorithms for stock prediction. First, we will utilize the Long Short Term Memory(LSTM) network to do the Stock Market Prediction. LSTM is a powerful method that is capable of learning order dependence in sequence prediction problems. Furthermore, we will utilize Generative Adversarial Network(GAN) to make the prediction. LSTM will be used as a generator, and CNN as a discriminator. In addition, Natural Language Processing(NLP) will also be used in this project to analyze the influence of News on stock prices.
gionanide / Speech Signal Processing And ClassificationFront-end speech processing aims at extracting proper features from short- term segments of a speech utterance, known as frames. It is a pre-requisite step toward any pattern recognition problem employing speech or audio (e.g., music). Here, we are interesting in voice disorder classification. That is, to develop two-class classifiers, which can discriminate between utterances of a subject suffering from say vocal fold paralysis and utterances of a healthy subject.The mathematical modeling of the speech production system in humans suggests that an all-pole system function is justified [1-3]. As a consequence, linear prediction coefficients (LPCs) constitute a first choice for modeling the magnitute of the short-term spectrum of speech. LPC-derived cepstral coefficients are guaranteed to discriminate between the system (e.g., vocal tract) contribution and that of the excitation. Taking into account the characteristics of the human ear, the mel-frequency cepstral coefficients (MFCCs) emerged as descriptive features of the speech spectral envelope. Similarly to MFCCs, the perceptual linear prediction coefficients (PLPs) could also be derived. The aforementioned sort of speaking tradi- tional features will be tested against agnostic-features extracted by convolu- tive neural networks (CNNs) (e.g., auto-encoders) [4]. The pattern recognition step will be based on Gaussian Mixture Model based classifiers,K-nearest neighbor classifiers, Bayes classifiers, as well as Deep Neural Networks. The Massachussets Eye and Ear Infirmary Dataset (MEEI-Dataset) [5] will be exploited. At the application level, a library for feature extraction and classification in Python will be developed. Credible publicly available resources will be 1used toward achieving our goal, such as KALDI. Comparisons will be made against [6-8].
abusufyanvu / 6S191 MIT DeepLearningMIT Introduction to Deep Learning (6.S191) Instructors: Alexander Amini and Ava Soleimany Course Information Summary Prerequisites Schedule Lectures Labs, Final Projects, Grading, and Prizes Software labs Gather.Town lab + Office Hour sessions Final project Paper Review Project Proposal Presentation Project Proposal Grading Rubric Past Project Proposal Ideas Awards + Categories Important Links and Emails Course Information Summary MIT's introductory course on deep learning methods with applications to computer vision, natural language processing, biology, and more! Students will gain foundational knowledge of deep learning algorithms and get practical experience in building neural networks in TensorFlow. Course concludes with a project proposal competition with feedback from staff and a panel of industry sponsors. Prerequisites We expect basic knowledge of calculus (e.g., taking derivatives), linear algebra (e.g., matrix multiplication), and probability (e.g., Bayes theorem) -- we'll try to explain everything else along the way! Experience in Python is helpful but not necessary. This class is taught during MIT's IAP term by current MIT PhD researchers. Listeners are welcome! Schedule Monday Jan 18, 2021 Lecture: Introduction to Deep Learning and NNs Lab: Lab 1A Tensorflow and building NNs from scratch Tuesday Jan 19, 2021 Lecture: Deep Sequence Modelling Lab: Lab 1B Music Generation using RNNs Wednesday Jan 20, 2021 Lecture: Deep Computer Vision Lab: Lab 2A Image classification and detection Thursday Jan 21, 2021 Lecture: Deep Generative Modelling Lab: Lab 2B Debiasing facial recognition systems Friday Jan 22, 2021 Lecture: Deep Reinforcement Learning Lab: Lab 3 pixel-to-control planning Monday Jan 25, 2021 Lecture: Limitations and New Frontiers Lab: Lab 3 continued Tuesday Jan 26, 2021 Lecture (part 1): Evidential Deep Learning Lecture (part 2): Bias and Fairness Lab: Work on final assignments Lab competition entries due at 11:59pm ET on Canvas! Lab 1, Lab 2, and Lab 3 Wednesday Jan 27, 2021 Lecture (part 1): Nigel Duffy, Ernst & Young Lecture (part 2): Kate Saenko, Boston University and MIT-IBM Watson AI Lab Lab: Work on final assignments Assignments due: Sign up for Final Project Competition Thursday Jan 28, 2021 Lecture (part 1): Sanja Fidler, U. Toronto, Vector Institute, and NVIDIA Lecture (part 2): Katherine Chou, Google Lab: Work on final assignments Assignments due: 1 page paper review (if applicable) Friday Jan 29, 2021 Lecture: Student project pitch competition Lab: Awards ceremony and prize giveaway Assignments due: Project proposals (if applicable) Lectures Lectures will be held starting at 1:00pm ET from Jan 18 - Jan 29 2021, Monday through Friday, virtually through Zoom. Current MIT students, faculty, postdocs, researchers, staff, etc. will be able to access the lectures during this two week period, synchronously or asynchronously, via the MIT Canvas course webpage (MIT internal only). Lecture recordings will be uploaded to the Canvas as soon as possible; students are not required to attend any lectures synchronously. Please see the Canvas for details on Zoom links. The public edition of the course will only be made available after completion of the MIT course. Labs, Final Projects, Grading, and Prizes Course will be graded during MIT IAP for 6 units under P/D/F grading. Receiving a passing grade requires completion of each software lab project (through honor code, with submission required to enter lab competitions), a final project proposal/presentation or written review of a deep learning paper (submission required), and attendance/lecture viewing (through honor code). Submission of a written report or presentation of a project proposal will ensure a passing grade. MIT students will be eligible for prizes and awards as part of the class competitions. There will be two parts to the competitions: (1) software labs and (2) final projects. More information is provided below. Winners will be announced on the last day of class, with thousands of dollars of prizes being given away! Software labs There are three TensorFlow software lab exercises for the course, designed as iPython notebooks hosted in Google Colab. Software labs can be found on GitHub: https://github.com/aamini/introtodeeplearning. These are self-paced exercises and are designed to help you gain practical experience implementing neural networks in TensorFlow. For registered MIT students, submission of lab materials is not necessary to get credit for the course or to pass the course. At the end of each software lab there will be task-associated materials to submit (along with instructions) for entry into the competitions, open to MIT students and affiliates during the IAP offering. This includes MIT students/affiliates who are taking the class as listeners -- you are eligible! These instructions are provided at the end of each of the labs. Completing these tasks and submitting your materials to Canvas will enter you into a per-lab competition. MIT students and affiliates will be eligible for prizes during the IAP offering; at the end of the course, prize-winners will be awarded with their prizes. All competition submissions are due on January 26 at 11:59pm ET to Canvas. For the software lab competitions, submissions will be judged on the basis of the following criteria: Strength and quality of final results (lab dependent) Soundness of implementation and approach Thoroughness and quality of provided descriptions and figures Gather.Town lab + Office Hour sessions After each day’s lecture, there will be open Office Hours in the class GatherTown, up until 3pm ET. An MIT email is required to log in and join the GatherTown. During these sessions, there will not be a walk through or dictation of the labs; the labs are designed to be self-paced and to be worked on on your own time. The GatherTown sessions will be hosted by course staff and are held so you can: Ask questions on course lectures, labs, logistics, project, or anything else; Work on the labs in the presence of classmates/TAs/instructors; Meet classmates to find groups for the final project; Group work time for the final project; Bring the class community together. Final project To satisfy the final project requirement for this course, students will have two options: (1) write a 1 page paper review (single-spaced) on a recent deep learning paper of your choice or (2) participate and present in the project proposal pitch competition. The 1 page paper review option is straightforward, we propose some papers within this document to help you get started, and you can satisfy a passing grade with this option -- you will not be eligible for the grand prizes. On the other hand, participation in the project proposal pitch competition will equivalently satisfy your course requirements but additionally make you eligible for the grand prizes. See the section below for more details and requirements for each of these options. Paper Review Students may satisfy the final project requirement by reading and reviewing a recent deep learning paper of their choosing. In the written review, students should provide both: 1) a description of the problem, technical approach, and results of the paper; 2) critical analysis and exposition of the limitations of the work and opportunities for future work. Reviews should be submitted on Canvas by Thursday Jan 28, 2021, 11:59:59pm Eastern Time (ET). Just a few paper options to consider... https://papers.nips.cc/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf https://papers.nips.cc/paper/2018/file/69386f6bb1dfed68692a24c8686939b9-Paper.pdf https://papers.nips.cc/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf https://science.sciencemag.org/content/362/6419/1140 https://papers.nips.cc/paper/2018/file/0e64a7b00c83e3d22ce6b3acf2c582b6-Paper.pdf https://arxiv.org/pdf/1906.11829.pdf https://www.nature.com/articles/s42256-020-00237-3 https://pubmed.ncbi.nlm.nih.gov/32084340/ Project Proposal Presentation Keyword: proposal This is a 2 week course so we do not require results or working implementations! However, to win the top prizes, nice, clear results and implementations will demonstrate feasibility of your proposal which is something we look for! Logistics -- please read! You must sign up to present before 11:59:59pm Eastern Time (ET) on Wednesday Jan 27, 2021 Slides must be in a Google Slide before 11:59:59pm Eastern Time (ET) on Thursday Jan 28, 2021 Project groups can be between 1 and 5 people Listeners welcome To be eligible for a prize you must have at least 1 registered MIT student in your group Each participant will only be allowed to be in one group and present one project pitch Synchronous attendance on 1/29/21 is required to make the project pitch! 3 min presentation on your idea (we will be very strict with the time limits) Prizes! (see below) Sign up to Present here: by 11:59pm ET on Wednesday Jan 27 Once you sign up, make your slide in the following Google Slides; submit by midnight on Thursday Jan 28. Please specify the project group # on your slides!!! Things to Consider This doesn’t have to be a new deep learning method. It can just be an interesting application that you apply some existing deep learning method to. What problem are you solving? Are there use cases/applications? Why do you think deep learning methods might be suited to this task? How have people done it before? Is it a new task? If so, what are similar tasks that people have worked on? In what aspects have they succeeded or failed? What is your method of solving this problem? What type of model + architecture would you use? Why? What is the data for this task? Do you need to make a dataset or is there one publicly available? What are the characteristics of the data? Is it sparse, messy, imbalanced? How would you deal with that? Project Proposal Grading Rubric Project proposals will be evaluated by a panel of judges on the basis of the following three criteria: 1) novelty and impact; 2) technical soundness, feasibility, and organization, including quality of any presented results; 3) clarity and presentation. Each judge will award a score from 1 (lowest) to 5 (highest) for each of the criteria; the average score from each judge across these criteria will then be averaged with that of the other judges to provide the final score. The proposals with the highest final scores will be selected for prizes. Here are the guidelines for the criteria: Novelty and impact: encompasses the potential impact of the project idea, its novelty with respect to existing approaches. Why does the proposed work matter? What problem(s) does it solve? Why are these problems important? Technical soundness, feasibility, and organization: encompasses all technical aspects of the proposal. Do the proposed methodology and architecture make sense? Is the architecture the best suited for the proposed problem? Is deep learning the best approach for the problem? How realistic is it to implement the idea? Was there any implementation of the method? If results and data are presented, we will evaluate the strength of the results/data. Clarity and presentation: encompasses the delivery and quality of the presentation itself. Is the talk well organized? Are the slides aesthetically compelling? Is there a clear, well-delivered narrative? Are the problem and proposed method clearly presented? Past Project Proposal Ideas Recipe Generation with RNNs Can we compress videos with CNN + RNN? Music Generation with RNNs Style Transfer Applied to X GAN’s on a new modality Summarizing text/news articles Combining news articles about similar events Code or spec generation Multimodal speech → handwriting Generate handwriting based on keywords (i.e. cursive, slanted, neat) Predicting stock market trends Show language learners articles or videos at their level Transfer of writing style Chemical Synthesis with Recurrent Neural networks Transfer learning to learn something in a domain for which it’s hard or risky to gather data or do training RNNs to model some type of time series data Computer vision to coach sports players Computer vision system for safety brakes or warnings Use IBM Watson API to get the sentiment of your Facebook newsfeed Deep learning webcam to give wifi-access to friends or improve video chat in some way Domain-specific chatbot to help you perform a specific task Detect whether a signature is fraudulent Awards + Categories Final Project Awards: 1x NVIDIA RTX 3080 4x Google Home Max 3x Display Monitors Software Lab Awards: Bose headphones (Lab 1) Display monitor (Lab 2) Bebop drone (Lab 3) Important Links and Emails Course website: http://introtodeeplearning.com Course staff: introtodeeplearning-staff@mit.edu Piazza forum (MIT only): https://piazza.com/mit/spring2021/6s191 Canvas (MIT only): https://canvas.mit.edu/courses/8291 Software lab repository: https://github.com/aamini/introtodeeplearning Lab/office hour sessions (MIT only): https://gather.town/app/56toTnlBrsKCyFgj/MITDeepLearning
bmartacho / UniPoseWe propose UniPose, a unified framework for human pose estimation, based on our “Waterfall” Atrous Spatial Pooling architecture, that achieves state-of-art-results on several pose estimation metrics. Current pose estimation methods utilizing standard CNN architectures heavily rely on statistical postprocessing or predefined anchor poses for joint localization. UniPose incorporates contextual seg- mentation and joint localization to estimate the human pose in a single stage, with high accuracy, without relying on statistical postprocessing methods. The Waterfall module in UniPose leverages the efficiency of progressive filter- ing in the cascade architecture, while maintaining multi- scale fields-of-view comparable to spatial pyramid config- urations. Additionally, our method is extended to UniPose- LSTM for multi-frame processing and achieves state-of-the- art results for temporal pose estimation in Video. Our re- sults on multiple datasets demonstrate that UniPose, with a ResNet backbone and Waterfall module, is a robust and efficient architecture for pose estimation obtaining state-of- the-art results in single person pose detection for both sin- gle images and videos.
bicepjai / Deep Survey Text ClassificationThe project surveys 16+ Natural Language Processing (NLP) research papers that propose novel Deep Neural Network Models for Text Classification, based on Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). It also implements each of the models using Tensorflow and Keras.
USTCPCS / CVPR2018 AttentionContext Encoding for Semantic Segmentation MegaDepth: Learning Single-View Depth Prediction from Internet Photos LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume On the Robustness of Semantic Segmentation Models to Adversarial Attacks SPLATNet: Sparse Lattice Networks for Point Cloud Processing Left-Right Comparative Recurrent Model for Stereo Matching Enhancing the Spatial Resolution of Stereo Images using a Parallax Prior Unsupervised CCA Discovering Point Lights with Intensity Distance Fields CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation Learning a Discriminative Feature Network for Semantic Segmentation Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation Unsupervised Deep Generative Adversarial Hashing Network Monocular Relative Depth Perception with Web Stereo Data Supervision Single Image Reflection Separation with Perceptual Losses Zoom and Learn: Generalizing Deep Stereo Matching to Novel Domains EPINET: A Fully-Convolutional Neural Network for Light Field Depth Estimation by Using Epipolar Geometry FoldingNet: Interpretable Unsupervised Learning on 3D Point Clouds Decorrelated Batch Normalization Unsupervised Learning of Depth and Egomotion from Monocular Video Using 3D Geometric Constraints PU-Net: Point Cloud Upsampling Network Real-Time Monocular Depth Estimation using Synthetic Data with Domain Adaptation via Image Style Transfer Tell Me Where To Look: Guided Attention Inference Network Residual Dense Network for Image Super-Resolution Reflection Removal for Large-Scale 3D Point Clouds PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image Fully Convolutional Adaptation Networks for Semantic Segmentation CRRN: Multi-Scale Guided Concurrent Reflection Removal Network DenseASPP: Densely Connected Networks for Semantic Segmentation SGAN: An Alternative Training of Generative Adversarial Networks Multi-Agent Diverse Generative Adversarial Networks Robust Depth Estimation from Auto Bracketed Images AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation DeepMVS: Learning Multi-View Stereopsis GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation Single-Image Depth Estimation Based on Fourier Domain Analysis Single View Stereo Matching Pyramid Stereo Matching Network A Unifying Contrast Maximization Framework for Event Cameras, with Applications to Motion, Depth, and Optical Flow Estimation Image Correction via Deep Reciprocating HDR Transformation Occlusion Aware Unsupervised Learning of Optical Flow PAD-Net: Multi-Tasks Guided Prediciton-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing Surface Networks Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation TextureGAN: Controlling Deep Image Synthesis with Texture Patches Aperture Supervision for Monocular Depth Estimation Two-Stream Convolutional Networks for Dynamic Texture Synthesis Unsupervised Learning of Single View Depth Estimation and Visual Odometry with Deep Feature Reconstruction Left/Right Asymmetric Layer Skippable Networks Learning to See in the Dark
himanshub1007 / Alzhimers Disease Prediction Using Deep Learning# AD-Prediction Convolutional Neural Networks for Alzheimer's Disease Prediction Using Brain MRI Image ## Abstract Alzheimers disease (AD) is characterized by severe memory loss and cognitive impairment. It associates with significant brain structure changes, which can be measured by magnetic resonance imaging (MRI) scan. The observable preclinical structure changes provides an opportunity for AD early detection using image classification tools, like convolutional neural network (CNN). However, currently most AD related studies were limited by sample size. Finding an efficient way to train image classifier on limited data is critical. In our project, we explored different transfer-learning methods based on CNN for AD prediction brain structure MRI image. We find that both pretrained 2D AlexNet with 2D-representation method and simple neural network with pretrained 3D autoencoder improved the prediction performance comparing to a deep CNN trained from scratch. The pretrained 2D AlexNet performed even better (**86%**) than the 3D CNN with autoencoder (**77%**). ## Method #### 1. Data In this project, we used public brain MRI data from **Alzheimers Disease Neuroimaging Initiative (ADNI)** Study. ADNI is an ongoing, multicenter cohort study, started from 2004. It focuses on understanding the diagnostic and predictive value of Alzheimers disease specific biomarkers. The ADNI study has three phases: ADNI1, ADNI-GO, and ADNI2. Both ADNI1 and ADNI2 recruited new AD patients and normal control as research participants. Our data included a total of 686 structure MRI scans from both ADNI1 and ADNI2 phases, with 310 AD cases and 376 normal controls. We randomly derived the total sample into training dataset (n = 519), validation dataset (n = 100), and testing dataset (n = 67). #### 2. Image preprocessing Image preprocessing were conducted using Statistical Parametric Mapping (SPM) software, version 12. The original MRI scans were first skull-stripped and segmented using segmentation algorithm based on 6-tissue probability mapping and then normalized to the International Consortium for Brain Mapping template of European brains using affine registration. Other configuration includes: bias, noise, and global intensity normalization. The standard preprocessing process output 3D image files with an uniform size of 121x145x121. Skull-stripping and normalization ensured the comparability between images by transforming the original brain image into a standard image space, so that same brain substructures can be aligned at same image coordinates for different participants. Diluted or enhanced intensity was used to compensate the structure changes. the In our project, we used both whole brain (including both grey matter and white matter) and grey matter only. #### 3. AlexNet and Transfer Learning Convolutional Neural Networks (CNN) are very similar to ordinary Neural Networks. A CNN consists of an input and an output layer, as well as multiple hidden layers. The hidden layers are either convolutional, pooling or fully connected. ConvNet architectures make the explicit assumption that the inputs are images, which allows us to encode certain properties into the architecture. These then make the forward function more efficient to implement and vastly reduce the amount of parameters in the network. #### 3.1. AlexNet The net contains eight layers with weights; the first five are convolutional and the remaining three are fully connected. The overall architecture is shown in Figure 1. The output of the last fully-connected layer is fed to a 1000-way softmax which produces a distribution over the 1000 class labels. AlexNet maximizes the multinomial logistic regression objective, which is equivalent to maximizing the average across training cases of the log-probability of the correct label under the prediction distribution. The kernels of the second, fourth, and fifth convolutional layers are connected only to those kernel maps in the previous layer which reside on the same GPU (as shown in Figure1). The kernels of the third convolutional layer are connected to all kernel maps in the second layer. The neurons in the fully connected layers are connected to all neurons in the previous layer. Response-normalization layers follow the first and second convolutional layers. Max-pooling layers follow both response-normalization layers as well as the fifth convolutional layer. The ReLU non-linearity is applied to the output of every convolutional and fully-connected layer.  The first convolutional layer filters the 224x224x3 input image with 96 kernels of size 11x11x3 with a stride of 4 pixels (this is the distance between the receptive field centers of neighboring neurons in a kernel map). The second convolutional layer takes as input the (response-normalized and pooled) output of the first convolutional layer and filters it with 256 kernels of size 5x5x48. The third, fourth, and fifth convolutional layers are connected to one another without any intervening pooling or normalization layers. The third convolutional layer has 384 kernels of size 3x3x256 connected to the (normalized, pooled) outputs of the second convolutional layer. The fourth convolutional layer has 384 kernels of size 3x3x192 , and the fifth convolutional layer has 256 kernels of size 3x3x192. The fully-connected layers have 4096 neurons each. #### 3.2. Transfer Learning Training an entire Convolutional Network from scratch (with random initialization) is impractical[14] because it is relatively rare to have a dataset of sufficient size. An alternative is to pretrain a Conv-Net on a very large dataset (e.g. ImageNet), and then use the ConvNet either as an initialization or a fixed feature extractor for the task of interest. Typically, there are three major transfer learning scenarios: **ConvNet as fixed feature extractor:** We can take a ConvNet pretrained on ImageNet, and remove the last fully-connected layer, then treat the rest structure as a fixed feature extractor for the target dataset. In AlexNet, this would be a 4096-D vector. Usually, we call these features as CNN codes. Once we get these features, we can train a linear classifier (e.g. linear SVM or Softmax classifier) for our target dataset. **Fine-tuning the ConvNet:** Another idea is not only replace the last fully-connected layer in the classifier, but to also fine-tune the parameters of the pretrained network. Due to overfitting concerns, we can only fine-tune some higher-level part of the network. This suggestion is motivated by the observation that earlier features in a ConvNet contains more generic features (e.g. edge detectors or color blob detectors) that can be useful for many kind of tasks. But the later layer of the network becomes progressively more specific to the details of the classes contained in the original dataset. **Pretrained models:** The released pretrained model is usually the final ConvNet checkpoint. So it is common to see people use the network for fine-tuning. #### 4. 3D Autoencoder and Convolutional Neural Network We take a two-stage approach where we first train a 3D sparse autoencoder to learn filters for convolution operations, and then build a convolutional neural network whose first layer uses the filters learned with the autoencoder.  #### 4.1. Sparse Autoencoder An autoencoder is a 3-layer neural network that is used to extract features from an input such as an image. Sparse representations can provide a simple interpretation of the input data in terms of a small number of \parts by extracting the structure hidden in the data. The autoencoder has an input layer, a hidden layer and an output layer, and the input and output layers have same number of units, while the hidden layer contains more units for a sparse and overcomplete representation. The encoder function maps input x to representation h, and the decoder function maps the representation h to the output x. In our problem, we extract 3D patches from scans as the input to the network. The decoder function aims to reconstruct the input form the hidden representation h. #### 4.2. 3D Convolutional Neural Network Training the 3D convolutional neural network(CNN) is the second stage. The CNN we use in this project has one convolutional layer, one pooling layer, two linear layers, and finally a log softmax layer. After training the sparse autoencoder, we take the weights and biases of the encoder from trained model, and use them a 3D filter of a 3D convolutional layer of the 1-layer convolutional neural network. Figure 2 shows the architecture of the network. #### 5. Tools In this project, we used Nibabel for MRI image processing and PyTorch Neural Networks implementation.
singaxiong / SignalGraphMatlab-based deep learning toolkit that supports arbitrary directed acyclic graphs (DAG). Support DNN, LSTM, CNN layers and many signal processing layers. Include recipes/examples of using the tool for various tasks.
jimmy-ren / Vcnn Double BladedVectorized implementation of convolutional neural networks (CNN) in Matlab for both visual recognition and image processing.
omerbsezer / CNN TAAlgorithmic Financial Trading with Deep Convolutional Neural Networks: Time Series to Image Conversion Approach: A novel algorithmic trading model CNN-TA using a 2-D convolutional neural network based on image processing properties.
NadavIs56 / Skin Disease AIA Python-based computer vision and AI system for skin disease recognition and diagnosis. Led end-to-end project pipeline, including data gathering, preprocessing, and training models. Utilized Keras, TensorFlow, OpenCV, and other libraries for image processing and CNN models, showcasing expertise in deep learning and machine learning techniques.
sidmulajkar / Sentiment Predictor For Stress DetectionVoice stress analysis (VSA) aims to differentiate between stressed and non-stressed outputs in response to stimuli (e.g., questions posed), with high stress seen as an indication of deception. In this work, we propose a deep learning-based psychological stress detection model using speech signals. With increasing demands for communication between humans and intelligent systems, automatic stress detection is becoming an interesting research topic. Stress can be reliably detected by measuring the level of specific hormones (e.g., cortisol), but this is not a convenient method for the detection of stress in human- machine interactions. The proposed algorithm first extracts Mel- filter bank coefficients using pre-processed speech data and then predicts the status of stress output using a binary decision criterion (i.e., stressed or unstressed) using CNN (Convolutional Neural Network) and dense fully connected layer networks.
