SVM-CNN-master
所属分类：其他
开发工具：Python
文件大小：12518KB
下载次数：70
上传日期：2017-11-22 00:28:14
上 传 者：
冬冬冬冬冬冬
说明： 实现卷积神经网络与支持向量机的联合调试使用
(Joint debugging and implementation of convolutional neural network and support vector machine)
文件列表:
LICENSE (11357, 2016-06-19)
MNIST_data (0, 2017-10-01)
MNIST_data\t10k-images-idx3-ubyte.gz (1648877, 2017-06-07)
MNIST_data\t10k-labels-idx1-ubyte.gz (4542, 2017-06-07)
MNIST_data\train-images-idx3-ubyte.gz (9912422, 2017-06-07)
MNIST_data\train-labels-idx1-ubyte.gz (28881, 2017-06-07)
__pycache__ (0, 2017-10-01)
__pycache__\elm.cpython-35.pyc (20258, 2017-06-07)
__pycache__\random_layer.cpython-35.pyc (17582, 2017-06-07)
elm.py (20319, 2016-06-19)
main.py (11381, 2016-06-19)
random_layer.py (18874, 2016-06-19)
results.log (83411, 2016-06-19)
svm-cnn-article.pdf (105518, 2016-06-19)
svm-cnn-presentation.pdf (1170910, 2016-06-19)
# SVM-CNN
It is my project based on Python 3, Tensorflow ans Scikit-learn to the course Hybrid Systems of Center of Informatics of UFPE (2016.1). This course is related with my Master Degree in Deep Learning. The idea is to extract features from MNIST dataset and then use SVM to classify. We show that improves the accuracy when compared with the regular CNN and is faster than ELM of worst accuracy.
To run it, you shoult type:
python main.py
近期下载者：
相关文件：
收藏者：