![](https://img-blog.csdnimg.cn/20201014180756738.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
python
youknowzjz
这个作者很懒,什么都没留下…
展开
-
pybrain 的安装及报错 ImportError:No module named structure的解决方案
最近想用python来做机器学习,发现python下有个开源的神经网络工具包--pybrain可供我们使用。pybrain的安装:我是ubuntu的系统,所以使用命令行安装。sudo pip3 install git+https://github.com/pybrain/pybrain.git安装后使用报错但是再三检查没有问题,安装也正确,随后r原创 2016-04-03 13:33:51 · 5744 阅读 · 0 评论 -
[CS231n@Stanford] Assignment1-Q1 (python) KNN实现
最近在学习斯坦福的深度学习课程CS231n: Convolutional Neural Networks for Visual Recognition. 课程视频及笔记链接: https://zhuanlan.zhihu.com/p/21930884作业网址:http://cs231n.github.io/assignment1/k_nearest_neighbor.pyi原创 2016-09-05 11:24:08 · 2037 阅读 · 0 评论 -
[CS231n@Stanford] Assignment1-Q2 (python) SVM实现
linear_svm.pyimport numpy as npfrom random import shuffledef svm_loss_naive(W, X, y, reg): """ Structured SVM loss function, naive implementation (with loops). Inputs have dimension D, the原创 2016-09-07 10:36:49 · 2646 阅读 · 1 评论 -
[CS231n@Stanford] Assignment1-Q3 (python) Softmax实现
softmax.pyimport numpy as npfrom random import shuffledef softmax_loss_naive(W, X, y, reg): """ Softmax loss function, naive implementation (with loops) Inputs have dimension D, there are原创 2016-09-07 13:09:59 · 2593 阅读 · 1 评论 -
[CS231n@Stanford] Assignment2-Q1 (python) Fully-connected Neural Network实现
layer.pyimport numpy as npdef affine_forward(x, w, b): """ Computes the forward pass for an affine (fully-connected) layer. The input x has shape (N, d_1, ..., d_k) and contains a minibatc原创 2016-09-20 14:22:13 · 4726 阅读 · 1 评论 -
[CS231n@Stanford] Assignment1-Q4 (python) Two layer neural network实现
neural_net.pyimport numpy as npimport matplotlib.pyplot as pltclass TwoLayerNet(object): """ A two-layer fully-connected neural network. The net has an input dimension of N, a hidden lay原创 2016-09-07 18:48:43 · 3017 阅读 · 0 评论 -
[CS231n@Stanford] Assignment1-Q5 (python) features实现
features.ipynbfrom linear_classifier import LinearSVMlearning_rates = [1e-9, 1e-8, 1e-7]regularization_strengths = [1e5, 1e6, 1e7]results = {}best_val = -1best_svm = Nonepass############原创 2016-09-07 21:05:01 · 1898 阅读 · 0 评论 -
[CS231n@Stanford] Assignment2-Q2 (python) Batch Normalization 实现 和Q3(python)Dropout 实现
layers.pydef batchnorm_forward(x, gamma, beta, bn_param): """ Forward pass for batch normalization. During training the sample mean and (uncorrected) sample variance are computed from min原创 2016-09-27 13:07:12 · 3788 阅读 · 0 评论