Pinned Repositories
acm-challenge-workbook
《挑战程序设计竞赛》习题册攻略
AutonomousDrivingCookbook
Scenarios, tutorials and demos for Autonomous Driving
cddfm3d
Cross-Domain and Disentangled Face Manipulation with 3D Guidance
Char-RNN-TensorFlow
Multi-language Char RNN for TensorFlow >= 1.2.
Deep-Learning-PointNet-Project
Classification and Segmentation of the MNIST dataset given as a point set input. Classification: the program classifies hand written digits, given as a sample of 100 points in a 2 dimensional field. the architecture is based on a Stanford article of a PointNet which is especially efficient for 3D image classification. the PointNet classification accuracy is 92.86% Segmentation: this is an extension to the classification net which can later define segments within the pointset. the program receives an input of a handwritten digit, given as a sample of 200 points in a 2 dimensional field, where 100 of the points are a sample of the digit itself, and the rest of the points are "background" points which are not part of the digit. the program classifies each point into one of the 2 segments and returns if it is part of the digit or part of the background. the PointNet segmentation accuracy is 97.65%
DeepLearning-500-questions
深度学习500问,以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述,以帮助自己及有需要的读者。 全书分为18个章节,50余万字。由于水平有限,书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作,联系scutjy2015@163.com 版权所有,违权必究 Tan 2018.06
densenet-tensorflow
DenseNet Implementation in Tensorflow
faiss
A library for efficient similarity search and clustering of dense vectors.
MachineLearningAlgorithms
pytorch-tutorial
PyTorch Tutorial for Deep Learning Researchers
sonny180's Repositories
sonny180/Char-RNN-TensorFlow
Multi-language Char RNN for TensorFlow >= 1.2.
sonny180/kaggle-nips2017-adversarial_attack
kaggle nips2017 Adversarial Attack
sonny180/Deep-Learning-PointNet-Project
Classification and Segmentation of the MNIST dataset given as a point set input. Classification: the program classifies hand written digits, given as a sample of 100 points in a 2 dimensional field. the architecture is based on a Stanford article of a PointNet which is especially efficient for 3D image classification. the PointNet classification accuracy is 92.86% Segmentation: this is an extension to the classification net which can later define segments within the pointset. the program receives an input of a handwritten digit, given as a sample of 200 points in a 2 dimensional field, where 100 of the points are a sample of the digit itself, and the rest of the points are "background" points which are not part of the digit. the program classifies each point into one of the 2 segments and returns if it is part of the digit or part of the background. the PointNet segmentation accuracy is 97.65%
sonny180/SVM-ipython-tutorial
ipython notebook examples for SVM
sonny180/statistical-analysis-python-tutorial
Statistical Data Analysis in Python