使用更快的RCNN实现了汽车和牌照的分割，准确率为97%，并使用PyTesseract模型对n...，
Car and Licence Plate Segmentation using Faster RCNN was achieved with 97% accuracy and PyTesseract Model was used to perform OCR on the number plate. (2019-09-19, Python, 0KB, 下载0次)
来自[https: github.com huggingface transformers的学习](https: github.com huggingface transformers%E7%9A%84%E5%AD%A6%E4%B9%A0),
From [https: github.com huggingface transformers] (https: github.com huggingface transformers% E7% 9A% 84% E5% AD% A6% E4% B9% A0), (2023-10-19, Python, 0KB, 下载0次)
交通标志识别由高级分类器CNN（卷积神经网络）组成，精度为97%，
traffic sign recognition consist of advance classifier CNN(convolutional neural network) with 97% accuracy, (2023-10-01, Python, 0KB, 下载0次)
交通标志识别由高级分类器CNN（卷积神经网络）组成，精度为97%，
traffic sign recognition consist of advance classifier CNN(convolutional neural network) with 97% accuracy, (2023-08-23, Python, 0KB, 下载0次)
whale是kaggle比赛[鲸鱼图像]([https: www.kaggle.com c humpback-whale- identification )识别的简化版,本文是对Top3大神pudae算法复现](https: www.kaggle.com c humpback- whale- identification \)%E8%AF%86%E5%88%AB%E7%9A%84%E7%AE%80%E5%8C%96%E7%89%88%EF%BC%8C%E6%9C%AC%E6%96%87%E6%98%AF%E5%AF%B9Top3%E5%A4%A7%E7%A5%9Epudae%E7%AE%97%E6%B3%95%E5%A4%8D%E7%8E%B0),
Whale is a simplified version of the recognition of the Kaggle contest [Whale Image] ([https: www.kaggle.com c humpback whale - identification). This article is a reproduction of the Top3 god putae algorithm] (https: www.kaggle.com c humpback whale - identification )% E8% AF% 86% E5% 88% AB% E7% 9A% 84% E7% AE% 80% E5% 8C% 96% E7% 89% 88% EF% BC% 8C% E6% 9C% AC% E6% 96% 87% E6% 98% AF% E5% AF% B9Top3% E5% A4% A7% E7% A5% 9Epudae% E7% AE% 97% E6% B3% 95% E5% A4% 8D% E7% 8E% B0), (2023-06-17, Python, 0KB, 下载0次)
根据这个[https: github.com matterport Mask_RCNN修改的FPN](https: github.com matterport Mask_RCNN%E4%BF%AE%E6%94%B9%E7%9A%84FPN)
According to this [https: github.com matterport Mask_RCNN modified FPN] (https: github.com matterport Mask_RCNN% E4% BF% AE% E6% 94% B9% E7% 9A% 84FPN) (2018-03-02, Python, 50KB, 下载0次)
EC601 BU的VQA团队
VQA team in BU for EC601 (2022-11-30, Python, 3335KB, 下载0次)
基于深度视觉、图像处理和机器视觉的4种步态识别算法的研究、设计和实现...
Research, design and implementation of 4 Gait Recognition algorithms using depth vision, image processing and machine learning to identify individuals based on their gait. Additionally, a system with a GUI was created for ease of use. Algorithms created, yielded up to 97% precision. Tools: Python (Spyder), Intel RealSense D435 (2019-06-30, Python, 40571KB, 下载0次)
基于python- opencv的车牌识别demo(参考:[https: blog.csdn.net weixin_41695564 article details 79712393进行了修改](https: blog.csdn.net weixin_41695564 article details 79712393%E8%BF%9B%E8%A1%8C%E4%BA%86%E4%BF%AE%E6%94%B9))
Demo for license plate recognition based on Python opencv (reference: [https: blog.csdn.net weixin_41695564 article details 79712393 modified] (https: blog.csdn.net weixin_41695564 article details 79712393% E8% BF% 9B% E8% A1% 8C% E4% BA% 86% E4% BF% AE% E6% 94% B9) (2021-11-25, Python, 122837KB, 下载0次)
基于Bloom滤波器和虹膜编码的虹膜BTP方案
Iris BTP scheme based on Bloom filters and iris-codes (2017-11-14, Python, 413KB, 下载0次)
基于Bloom滤波器和LGBPHS特征的人脸BTP方案
Face BTP scheme based on Bloom filters and LGBPHS features (2017-11-14, Python, 448KB, 下载0次)
基于Bloom滤波器的多生物特征BTP方案
Multi-biometric BTP scheme based on Bloom filters (2017-11-14, Python, 410KB, 下载0次)
源程序来自于:[https: github.com sgrvinod a-PyTorch-Tutorial-to-Object- Detection。但是原作者的环境是:](https: github.com sgrvinod a-PyTorch-Tutorial-to- Object- Detection%E3%80%82%E4%BD%86%E6%98%AF%E5%8E%9F%E4%BD%9C%E8%80%85%E7%9A%84%E7%8E%AF%E5%A2%83%E6%98%AF%EF%BC%9A) `PyTorch 0.4` in `Python 3.6`。在用...
The source program comes from: [https: github.com sgrVinod a-PyTorch Tutorial to Object - Detection. However, the original author s environment is:] (https: github.com sgrVinod a-PyTorch Tutorial to Object - Detection% E3% 80% 82% E4% BD% 86% E6% 98% AF% E5% 8E% 9F% E4% BD% 9C% E8% 80% 85% E7% 9A% 84% E7% 8E% AF% E5% A2% 83% E6% 98% AF% EF% BC% 9A) PyTorch 0.4 in Python 3.6 . In use (2020-08-02, Python, 20645KB, 下载0次)
开发了一个5层序列卷积神经网络，使用Keras和Tensorflow后端进行数字识别...
Developed a 5-layer Sequential Convolutional Neural Network using Keras with Tensorflow backend for digit recognition trained on MNIST dataset. Adjusted parameters such as kernel size, activation function and optimizer properties to compute the best fit. Obtained an accuracy of 97.12%. Performed Data Augmentation such as image scaling, image (2018-04-20, Python, 5KB, 下载0次)
带激光雷达的Pi人脸考勤系统，基于人脸识别的考勤系统，可部署在带Movidius NCS2的Raspberry Pi上。RPLIDAR A1集成用于...
Face Recognition-based Attendance system deployable on Raspberry Pi with Movidius NCS2. RPLIDAR A1 is integrated for depth sensing to enable Door Access Control simulated with Pimoroni Blinkt! (2021-09-24, Python, 11970KB, 下载0次)
说话人识别、使用GMM和MFCC进行语音特征提取的说话人识别。此应用程序识别具有...的注册扬声器...
Speaker Recognition using GMM and MFCC for feature extraction of voice. This app recognizes a registered speaker with an accuracy of 97%. (2021-04-23, Python, 23367KB, 下载0次)
mvo,A visual odometry project reference: [http: www.fengbing.net 2015 08 15 一步步实现单目视觉里程计3——初始位置确定 ](http: www.fengbing.net 2015 08 15 %E4%B8%80%E6%AD%A5%E6%AD%A5%E5%AE%9E%E7%8E%B0%E5%8D%95%E7%9B%AE%E8%A7%86%E8%A7%89%E9%87%8C%E7%A8%8B%E8%AE%A13%E2%80%94%E2%80%94%E5%88%9D%E5%A7%8B%E4%BD%8D%E7%BD%AE%E7%A1%AE%E5%AE%9A )
Mvo, A visual odometry project reference: [http: www.fengbing.net 2015 08 15 Step by Step Implementation of Monocular Visual Odometer 3- Initial Position Determination] (http: www.fengbing.net 2015 08 15% E4% B8% 80% E6% AD% A5% E6% AD% A5% E5% AE% 9E% E7% 8E% B0% E5% 8D% 95% E7% 9B% AE% E8% A7% 86% E8% A7% 89% E9% 87% 8C% E7% A8% 8B% E8% AE% A13% E2% 80% 94% E2% 80% 94% E5% 88% 9D% E5% A7% 8B% E4% BD% 8D% E7% BD% AE% E7% A1% AE% E5% AE% 9A) (2019-08-31, Python, 202KB, 下载0次)
deepspeech2_tensorflow,基于baidu 2016年开源语音识别项目修改后端为tensorflow,rnn层为 双向GRU,ctc损失计算调用tensorflow内置模块实现中文语音识别,在清华开源数据上的测试准确率0.97.
deepspeech2_ Tensorflow, based on Baidu s 2016 open-source speech recognition project, modified the backend to Tensorflow, the RNN layer to bidirectional GRU, and the ctc loss calculation calls the Tensorflow built-in module to achieve Chinese speech recognition. The test accuracy on Tsinghua open-source data is 0.97 (2019-06-25, Python, 40KB, 下载0次)