The study uses a deep learning model called YOLO-v6 to classify three distinct seagrass object types and determine their dimensions. The results suggest that the proposed model is highly effective, with an average recall of 97.5%, an average precision of 83.7%, and an average F1 score of 90.1%. (2024-05-17, Jupyter Notebook, 0KB, 下载0次)
http://www.pudn.com/Download/item/id/1715927295663892.html
利用Callbacks建立图像分类模型（Rock-Paper Scissors），训练和验证准确率达到97%以上。基于分词类引入的项目数据科学机器学习
Making image classification model (Rock Paper Scissors) with Callbacks achieved more than 97% training and validation accuracy. Project based on Dicoding Class Introduction Datascience Machine Learning (2024-03-24, Jupyter Notebook, 0KB, 下载0次)
该报告包含一个使用HOG和SVM对CIFAR-10数据集中的图像进行分类的项目。它使用TensorFlow、scikit image、scikit-learn、matplotlib和joblib库。它还演示了预处理、流水线、并行计算以及模型保存和加载技术。在试验数据上达到了62.97%的精度。
This repo contains a project that classifies images from the CIFAR-10 dataset using HOG and SVM. It uses TensorFlow, scikit-image, scikit-learn, matplotlib, and joblib libraries. It also demonstrates preprocessing, pipelining, parallel computing, and model saving and loading techniques. It achieves an accuracy of 62.97% on the test data. (2024-03-10, Jupyter Notebook, 0KB, 下载0次)
这是一个使用97名高危受试者和88名低危受试者的眼球追踪数据来检测阅读障碍的模型。我们试图通过无监督学习算法来解决这个问题，并进行聚类分析
This is a model to detect dyslexia using eye-tracking data from 97 high-risk subjects and 88 low-risk subjects. We try to approach this issue through Unsupervised Learning Algorithm and conduct cluster analysis (2024-01-31, Jupyter Notebook, 0KB, 下载0次)
CV A1边缘检测
CV A1 Edge Detection (2024-01-27, Jupyter Notebook, 0KB, 下载0次)
A1-使用特征脸和fisher脸的人脸识别，
A1 - Face recognition using eigen faces and fisher faces, (2023-10-23, Jupyter Notebook, 0KB, 下载0次)
计算机视觉使用DeepFace预处理模型，准确率为97.35%，检测快乐、悲伤、惊讶、愤怒......等情绪...，
Computer vision using DeepFace pretrained model with an accuracy of 97.35 % to detect emotions ranging from happy, sad, surprised，angry, fear,neutral, digust (2023-10-13, Jupyter Notebook, 0KB, 下载0次)
我使用了Mnist数字分类数据集。利用RNN对28*28的60000幅图像进行训练。模型精度为97.39，其中...，
I have used Mnist digit classification dataset. The model is trained on 60,000 images of 28*28 using RNN. The model accuracy is 97.39 with a loss of 0.099 (2023-09-11, Jupyter Notebook, 0KB, 下载0次)
通过Fellowship.ai使用Resnet50和Fast.ai识别102朵花的图像分类应用程序，准确率为97%。查看：Dep...，
An Image Classification app identifying 102 flowers with 97% accuracy using Resnet50 and Fast.ai through Fellowship.AI. Check it out: Deployed on Hugging Face: https://lnkd.in/dEE5eszX Leveraged Fast.AI s power to streamline training, achieving remarkable results. (2023-08-21, Jupyter Notebook, 0KB, 下载0次)
使用从web收集的图像训练二值图像分类器，
Train a binary image classifier with images gathered from the web, (2023-08-19, Jupyter Notebook, 0KB, 下载0次)
基于源滤波模式的信号合成，
Signal Synthesis Based on Source Filter Mode, (2023-08-16, Jupyter Notebook, 0KB, 下载0次)
本项目旨在从植物叶片图像中检测植物病害。为了实现这个目标，我们使用...
This project aims to detect plant diseases from plant leaf images. To achieve this goal we preprocessed images using the grabcut algorithm and trained a CNN model using the plant disease dataset from kaggle. Our model successfully classifies 38 different types of disease with an accuracy up to 97%. (2020-05-07, Jupyter Notebook, 5430KB, 下载0次)
我们使用CNN和转移学习将胸部X光图像分为冠心病、正常和肺炎。考虑到小数据...
We classify chest X-ray images with Covid, normal and pneumonia using CNN and transfer learning. Given the small dataset, we use k-fold cross validation for training the model, reaching accuracies of ~97%. on the test data. We also construct a confusion matrix and P-R curve (2021-09-17, Jupyter Notebook, 250792KB, 下载0次)
在这个项目中，我开发了一个web应用程序，可以使用Javascript和...
In this project, I ve developed web app which can be used to verify online signatures efficiently using Javascript and Flask, a python framework, as a backend. This project is hosted on Heroku for easy access. I ve used Tensorflow 2.0 to develop the deep learning model. This model detects signature forgery with 97% accuracy . (2020-05-01, Jupyter Notebook, 30194KB, 下载0次)
在Kaggle 2013猫狗数据集上使用了CNN、ANN、数据增强和迁移学习的概念，并实现了...
Used concepts of CNN, ANN, Data Augmentation and Transfer Learning on Kaggle 2013 Cats and Dogs Dataset and achieved an accuracy of 97.2%. (2023-01-02, Jupyter Notebook, 120KB, 下载0次)
COVID-19的风险分析-来自计算机断层扫描-使用深度学习，。。。算法的性能最好，准确率为97.3%...
This study aimed to describe the prediction of COVID-19 using chest CT images by using GAN for resampling depending on deep transfer learning models and machine learning (ML) algorithms and risk analysis of patients based on traditional machine learning. The dataset consisted of 8129 samples in two classes, including 5927 CT chest images of (2022-07-07, Jupyter Notebook, 5950KB, 下载0次)
RCNN-A-Better-Model-for-Biological-Object-Recognition，这里我使用了具有自下而上（B）、横向（L）和自上而下（T）连接的RCNN。结合这三种类型的连接...
Here I have used RCNN with Bottom-up(B), Lateral(L), and top-down(T) connections. Combining these three types of connections yield four architectures( B, BT, BL, BLT) and two extra BF and BK models also tested and evaluated. We hypothesize that Recurrent dynamics improve the recognition performance in challenging conditions. (2020-05-28, Jupyter Notebook, 296KB, 下载0次)
猫狗分类烧瓶应用程序，我们通过实现卷积神经网络（CNN）来对狗进行分类，成功地建立了一个深度神经网络模型...
We successfully built a deep neural network model by implementing Convolutional Neural Network (CNN) to classify dog and cat images with very high accuracy 97.32 %. In addition, we also built a Flask application so user can upload their images and classify easily. (2021-03-25, Jupyter Notebook, 12567KB, 下载0次)
Computer-Vision-Lip-Reading-2.0，一种使用3D细胞神经网络的语音识别系统。最终模型的训练精度达到97.4%，测试精度达到99.2%...
A speech recognition system using 3D CNNs. The final model achieves 97.4% training accuracy and a 99.2% testing accuracy and the system can accurately recognize spoken words from a set of pre-defined words in real-time. (2023-04-13, Jupyter Notebook, 1105649KB, 下载0次)
疟疾检测，在FastAI图书馆的帮助下，构建一个准确率为97%的疟疾分类器
Malaria_detection,With the help of FastAI libraries building an malaria classifier with an 97% accuracy (2019-07-30, Jupyter Notebook, 798KB, 下载0次)