 Kaggle-Google-Landmark-2019
 Kaggle-Google-Landmark-2019 
 Image recognition system
 A machine learning project to recognize landmarks from images using a deep neural network architecture.
https://www.kaggle.com/c/landmark-recognition-2019
3 stars
 1 watching
 0 forks
 
Language: Python 
last commit: over 6 years ago  Related projects:
| Repository | Description | Stars | 
|---|---|---|
|  | A deep learning project based on the Quick Draw! Doodle Recognition Challenge, aimed at training and testing a neural network for drawing recognition. | 11 | 
|  | An approach to image classification using a combination of pre-trained models and fine-tuning on two separate datasets | 40 | 
|  | A Python-based deep learning project for medical image analysis, specifically focused on detecting RSNA intracranial hemorrhage. | 41 | 
|  | A framework for robust facial landmark detection in motion-blurred videos using structure consistency and geometry priors. | 99 | 
|  | A solution to a computer vision task involving image segmentation | 19 | 
|  | Pre-trained models and code for fine-tuning image recognition tasks using deep learning frameworks | 1,516 | 
|  | A Python implementation of a machine learning solution for classifying images as dogs or cats from the Kaggle competition. | 66 | 
|  | An effort to predict accelerometer biometric data from recorded sensor readings | 15 | 
|  | A Python implementation of an exotic image classifier architecture inspired by Google's evolution of image classifiers | 53 | 
|  | A Matlab-based system designed to predict epileptic seizures from EEG data using machine learning algorithms. | 104 | 
|  | A deep neural network architecture optimized for image classification on the CIFAR-10 dataset | 246 | 
|  | This is an implementation of a blindness detection model using deep learning and regression techniques. | 68 | 
|  | Code for training and predicting on the CIFAR-10 image classification dataset using CUDA-convnet architecture. | 44 | 
|  | An image classification project that uses a U-Net network to detect features in satellite imagery | 207 | 
|  | A generative model with tractable likelihood and easy sampling, allowing for efficient data generation. | 1,921 |