這是我在做大學(xué)教授期間推薦給我學(xué)生的一本書，非常好，適合入門學(xué)習(xí)。《python深度學(xué)習(xí)》由Keras之父、現(xiàn)任Google人工智能研究員的弗朗索瓦?肖萊（Franc?ois Chollet）執(zhí)筆，詳盡介紹了用Python和Keras進(jìn)行深度學(xué)習(xí)的探索實(shí)踐，包括計(jì)算機(jī)視覺、自然語言處理、產(chǎn)生式模型等應(yīng)用。書中包含30多個代碼示例，步驟講解詳細(xì)透徹。作者在github公布了代碼，代碼幾乎囊括了本書所有知識點(diǎn)。在學(xué)習(xí)完本書后，讀者將具備搭建自己的深度學(xué)習(xí)環(huán)境、建立圖像識別模型、生成圖像和文字等能力。但是有一個小小的遺憾：代碼的解釋和注釋是全英文的，即使英文水平較好的朋友看起來也很吃力。本人認(rèn)為，這本書和代碼是初學(xué)者入門深度學(xué)習(xí)及Keras最好的工具。作者在github公布了代碼，本人參照書本，對全部代碼做了中文解釋和注釋，并下載了代碼所需要的一些數(shù)據(jù)集（尤其是“貓狗大戰(zhàn)”數(shù)據(jù)集），并對其中一些圖像進(jìn)行了本地化，代碼全部測試通過。（請按照文件順序運(yùn)行，代碼前后有部分關(guān)聯(lián)）。以下代碼包含了全書約80%左右的知識點(diǎn)，代碼目錄：2.1: A first look at a neural network（ 初識神經(jīng)網(wǎng)絡(luò)）3.5: Classifying movie reviews（電影評論分類：二分類問題）3.6: Classifying newswires（新聞分類：多分類問題 ）3.7: Predicting house prices（預(yù)測房價(jià)：回歸問題）4.4: Underfitting and overfitting（ 過擬合與欠擬合）5.1: Introduction to convnets（卷積神經(jīng)網(wǎng)絡(luò)簡介）5.2: Using convnets with small datasets（在小型數(shù)據(jù)集上從頭開始訓(xùn)練一個卷積網(wǎng)絡(luò)）5.3: Using a pre-trained convnet（使用預(yù)訓(xùn)練的卷積神經(jīng)網(wǎng)絡(luò)）5.4: Visualizing What convnets learn（卷積神經(jīng)網(wǎng)絡(luò)的可視化）
標(biāo)簽： python 深度學(xué)習(xí)
上傳時間： 2022-01-30
上傳用戶：
因此，您想編寫一個內(nèi)核模塊。您知道C，您已經(jīng)編寫了一些可以作為進(jìn)程運(yùn)行的常規(guī)程序，現(xiàn)在您想知道真正的動作在哪里，一個通配指針可以擦掉文件系統(tǒng)，核心轉(zhuǎn)儲意味著重新啟動。內(nèi)核模塊到底是什么？模塊是可以根據(jù)需要加載和卸載的代碼段。它們擴(kuò)展了內(nèi)核的功能，而無需重新引導(dǎo)系統(tǒng)。例如。模塊驅(qū)動程序的一種類型是設(shè)備驅(qū)動程序，它允許內(nèi)核訪問沒有模塊的系統(tǒng)硬件，我們將不得不構(gòu)建單片內(nèi)核并將新功能直接添加到內(nèi)核映像中，除了具有更大的內(nèi)核之外，這還具有缺點(diǎn)每次我們想要新功能時都要求我們重建并重新啟動內(nèi)核的過程So, you want to write a kernel module. You know C, you, ve written a few normal programs to run as processes, and now you want to get to where the real action is, to where a single wild pointer can wipe out your file system and a core dump means a reboot.What exactly is a kernel module? Modules are pieces of code that can be loaded and unloaded into th upon demand. They extend the functionality of the kernel without the need to reboot the system. For example.one type of module is the device driver, which allows the kernel to access hardware connected to the syste without modules, we would have to build monolithic kernels and add new functionality directly into the em ernel image, Besides having larger kernels
標(biāo)簽： linux
上傳時間： 2022-03-30
上傳用戶：
In this presentation, we will look at What the Serial Peripheral Interface, otherwise known as the SPI, is. and how it is used to communicate data to and from the PICmicro microcontroller.SPl is frequently used when few 1/O lines are available, but communication between two or more devices must be fast and easy to implement.In this presentation, we will discuss the following topics: We will first cover an Overview of SPI This section of the tutorial will introduce you to SPI and its concepts.Next, we will examine the use of SPI on the PICmicro MCU.The details of how SPI is implemented on a PICmicro device will be examined.Then, a Code Walkthrough will be given.The walkthough will explore code for both an SPI Master and SPI Slave. The example will have the Master generate data for sending to the slave.Finally, there will be a few resources given at the end of the presentation. These resources will allow you to explore in more detail the SPI interface
標(biāo)簽： spi協(xié)議
上傳時間： 2022-06-20
上傳用戶：
German universities and scientists have repeatedly set the intermational standard in drive technology. Identification and active compensation of natural frequencies in oscillatory mechanics, status controls with monitoring structures incorporating acceleration sensors, adaptive compensation of measurement system deficiencies, self-adjusting detent torque compensation… everything invented with only a single aim in mind: to continue improv-ing the motion control, dynamics, precision and processing speed of your machines. For the industrial applicabability of this technology scientific publications in proceedings and laboratory test rigs are not enough. These features consequenty need to be converted into cost-efficient and easily manageable products. That 's exactly What we have done.So in future, if you should need more than today ' smarket can offer you, now everything isgoing to be alright. With our new high-performance ServoOne drive series you will experi-ence
標(biāo)簽： servoone
上傳時間： 2022-06-24
上傳用戶：kingwide
近來發(fā)現(xiàn)有些問題很多人都很感興趣。所以在這里希望能盡自己能力跟大家討論一些力所能及的算法。現(xiàn)在先討論一下卡爾曼濾波器，如果時間和能力允許，我還希望能夠?qū)憣懫渌乃惴ǎ邕z傳算法，傅立葉變換，數(shù)字濾波，神經(jīng)網(wǎng)絡(luò)，圖像處理等等。因?yàn)檫@里不能寫復(fù)雜的數(shù)學(xué)公式，所以也只能形象的描述。希望如果哪位是這方面的專家，歡迎討論更正。卡爾曼濾波器-Kalman Filter什么是卡爾曼濾波器（What is the Kalman Filter？）在學(xué)習(xí)卡爾曼濾波器之前，首先看看為什么叫“卡爾曼”。跟其他著名的理論（例如傅立葉變換，泰勒級數(shù)等等）一樣，卡爾曼也是一個人的名字，而跟他們不同的是，他是個現(xiàn)代人！
上傳時間： 2022-07-05
上傳用戶：zhaiyawei
? VL53L1X OverView? VL53L1X Software Package? Default and FAST mode? Ultra light driver.? VL53L1X GUI? VL53L1X Multi sensor design? STM32 FW: Import, Compile, Run, Debug…? What is Xtalk?? Cover Window and ID design? How about Human and object reflectance at 940 nm ?
上傳時間： 2022-07-17
上傳用戶：bluedrops
Simulation can provide a lot of information about What the system is doing. We canadd the effect of different element, like Encoder resolution, ADC sampling rate, etc and understand how does it affect the system. Another benefit is the possibility to slow down the process, to gain insight on What happens of fast systems or, vice versa, speed up slow process.Because National Instruments is a unique company in the fact the we provide a fullhardware solution couple with a full development platform, we can use this tools in very particular ways For example, it is possible to combine the LabVIEW Control Design and Simulation Module along with the FPGA module to quickly prototype a controller. One of the main benefits of this approach is that there is no need to compile the FPGA code, which allows for a quick algorithm design turnaround and debugging.
標(biāo)簽： pid控制
上傳時間： 2022-07-20
上傳用戶：
近來發(fā)現(xiàn)有些問題很多人都很感興趣。所以在這里希望能盡自己能力跟大家討論一些力所能及的算法。現(xiàn)在先討論一下卡爾曼濾波器，如果時間和能力允許，我還希望能夠?qū)憣懫渌乃惴ǎ邕z傳算法，傅立葉變換，數(shù)字濾波，神經(jīng)網(wǎng)絡(luò)，圖像處理等等。 因?yàn)檫@里不能寫復(fù)雜的數(shù)學(xué)公式，所以也只能形象的描述。希望如果哪位是這方面的專家，歡迎討論更正。 卡爾曼濾波器 – Kalman Filter 1． 什么是卡爾曼濾波器 （What is the Kalman Filter?） 在學(xué)習(xí)卡爾曼濾波器之前，首先看看為什么叫“卡爾曼”。跟其他著名的理論（例如傅立葉變換，泰勒級數(shù)等等）一樣，卡爾曼也是一個人的名字，而跟他們不同的是，他是個現(xiàn)代人！ 卡爾曼全名Rudolf Emil Kalman，匈牙利數(shù)學(xué)家，1930年出生于匈牙利首都布達(dá)佩斯。1953，1954年于麻省理工學(xué)院分別獲得電機(jī)工程學(xué)士及碩士學(xué)位。1957年于哥倫比亞大學(xué)獲得博士學(xué)位。我們現(xiàn)在要學(xué)習(xí)的卡爾曼濾波器，正是源于他的博士論文和1960年發(fā)表的論文《A New Approach to Linear Filtering and Prediction Problems》（線性濾波與預(yù)測問題的新方法）。如果對這編論文有興趣
上傳時間： 2022-07-23
上傳用戶：qdxqdxqdxqdx
蟲蟲下載站版權(quán)所有 京ICP備2021023401號-1
