youknowzjz的博客

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

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

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

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

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

features.ipynbfrom linear_classifier import LinearSVMlearning_rates = [1e-9, 1e-8, 1e-7]regularization_strengths = [1e5, 1e6, 1e7]results = {}best_val = -1best_svm = Nonepass############

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