leaeason的博客

前言首先来一波地址：happynear大神的第三方caffe：http://blog.youkuaiyun.com/happynear/article/details/45372231Neil Z大神的第三方caffe：https://initialneil.wordpress.com/2015/01/11/build-caffe-in-windows-with-visual-studio-201

Coursera-Deep Learning Specialization 课程之（二）：Improving Deep Neural Networks: -weak2编程作业Optimization Methods1 - Gradient Descentdef update_parameters_with_gd(parameters, grads, learning_rate): """

Coursera-Deep Learning Specialization 课程之（二）：Improving Deep Neural Networks: -weak1编程作业Initializationimport numpy as npimport matplotlib.pyplot as pltimport sklearnimport sklearn.datasetsfrom init_

自动驾驶中的车辆检测Autonomous driving - Car detectionimport argparseimport osimport matplotlib.pyplot as pltfrom matplotlib.pyplot import imshowimport scipy.ioimport scipy.miscimport numpy as npimport pa

人脸识别Face Recognition for the Happy Housefrom keras.models import Sequentialfrom keras.layers import Conv2D, ZeroPadding2D, Activation, Input, concatenatefrom keras.models import Modelfrom keras.laye

Operations on word vectors - v2import numpy as npfrom w2v_utils import *words, word_to_vec_map = read_glove_vecs('data/glove.6B.50d.txt')1 - Cosine similarity# GRADED FUNCTION: cosine_s...

Emojify!1 - Baseline model: Emojifier-V11.3 - Implementing Emojifier-V1# GRADED FUNCTION: sentence_to_avgdef sentence_to_avg(sentence, word_to_vec_map): """ Converts a sentence (...

Building your Recurrent Neural Network - Step by Step1 - Forward propagation for the basic Recurrent Neural Network1.1 - RNN cell# GRADED FUNCTION: rnn_cell_forwarddef rnn_cell_forward(xt,...

Dinosaurus Island – Character level language model final - v31 - Problem Statement1.1 - Dataset and Preprocessingdata = open('dinos.txt', 'r').read()data= data.lower()chars = list(set(data...

Coursera-Deep Learning Specialization 课程之（二）：Improving Deep Neural Networks: -weak3编程作业TensorFlow Tutorial1 - Exploring the Tensorflow Library1.1 - Linear function# GRADED FUNCTION: linear_functiondef

一 Python Basics with numpy (optional)学习目标： ①使用logistic regression ②学习如何最小化代价函数cost function ③理解通过代价函数的导数来更新参数**1 - Building basic functions with numpy1.1 - sigmoid function,

Planar data classification with a hidden layer1 - Packages# Package importsimport numpy as npimport matplotlib.pyplot as pltfrom testCases_v2 import *import sklearnimport sklearn.datasetsimport s

Building your Deep Neural Network: Step by Step1 - Packagesimport numpy as npimport h5pyimport matplotlib.pyplot as pltfrom testCases_v3 import *from dnn_utils_v2 import sigmoid, sigmoid_backward,

Neural Networks and Deep Learning

weak2目录: Logistic Regression as a Neural Network Python and Vectorization 编程作业： 1. Python Basics with numpy (optional) 2. Logistic Regression with a Neural Network mindset学习目标：

Convolutional Neural Networks: Step by Step3 - Convolutional Neural Networks3.1 - Zero-Paddingdef zero_pad(X, pad): """ Pad with zeros all images of the dataset X. The padding is applied to the

Residual Networks1 - The problem of very deep neural networks2 - Building a Residual Network2.1 - The identity blockdef identity_block(X, f, filters, stage, block): """ Implementation of the id

Improvise a Jazz Solo with an LSTM Networkfrom __future__ import print_functionimport IPythonimport sysfrom music21 import *import numpy as npfrom grammar import *from qa import *from prepr...