Chapter 7 - Automation "There's a lot of automation that can happen that isn't a replacement of humans but of mind-numbing behavior." - Stewart Butterfield, Founder (Slack) We have talked about a variety tensorflow.keras import layers, optimizers train_ds, val_ds, test_ds = tfds.load( 'oxford_flowers102', split=['train', 'validation', 'test'], as_supervised=True, read_config=tfds.ReadConfig(try_autocache=False) return image, label train_ds = train_ds.map(resize_image) val_ds = val_ds.map(resize_image) test_ds = test_ds.map(resize_image) Note that the create_model() function here has two additional parameters:

Train-Val-Test划分 主讲人：龙良曲 Recap How to detect Splitting Train Set Test Set For example 60K 10K test while train train test trade-off Overfitt ing For others judge ▪ Kaggle Train Set Test Set Set Val Set Unavailable train-val-test K-fold cross-validation Train Set Test Set Val Set k-fold cross validation ▪ merge train/val sets ▪ randomly sample 1/k as val set 下一课时 减轻Overfitting Thank

also introduce core areas of efficiency techniques (compression techniques, learning techniques, automation, efficient models & layers, infrastructure). Our hope is that even if you just read this chapter case). For example, if you are deploying a model on devices where inference is constrained (such as mobile and embedded devices), or expensive (cloud servers), it might be worth paying attention to inference liable for data breaches. The law went into effect in 2018. Figure 1-5: Growth in the number of mobile and IoT devices over time. The lighter blue bars represent forecasts. (Data Source: 1, 2) In this

goals. High quality models have an additional benefit in footprint constrained environments like mobile and edge devices where they provide the flexibility to trade off some quality for smaller footprints others’. Let’s understand it with an example. Assume that we are working on a model for a home-automation device. Figure 3-4 shows the high level workflow of such a device. The model continuously classifies indicates the absence of an acceptable keyword in the input signal. Figure 3-4: Workflow of a home-automation device which detects three spoken words: hello weather and time. The output is none when none

even whole channels. Libraries like XNNPACK3,4 can help accelerate networks on a variety of web, mobile, and embedded devices, provided the user can design networks that match their constraints. One might val_loss: 0.5619 - val_accuracy: 0.8460 # Evaluate the pruned model on the test set. model_for_pruning_acc = model_for_pruning.evaluate(test_prep_ds.batch(256))[1] print('Accuracy: ', model_for_pruning_acc) Accuracy: 0.8471 Recall that the regular model performed with a 85.11% accuracy on the test set. Our pruned model performed with an accuracy of 84.71%. It's a slight drop in performance. Let's go ahead

5项主要比赛中 的3项世界冠军 软银孙正义收购Google旗下的 机器人公司Boston Dynamics 和Schaft 通用 10亿美元 收购无人驾驶技 术初创公司Cruise Automation 首次中国公司在ImageNet竞赛 夺冠，视频分析技术登顶 人脸识别大幅提高精度，商汤科 技首次突破人类肉眼识别准确率 ，领先于Facebook Google5000万美元招入 为什么用Go - 比起C++，更易于实践各种并发模式 - 比起Java，更加简洁，更易于与C/C++交互 - 比起脚本语言，类型和内存安全，保证重构效率与产品质量 - 完善的配套工具，如go test, gofmt, go lint, race-detector Go语言在高性能系统中的实践经验 • Go在开发高性能应用上也有一些不足， 对比C++： - 无法直接控制操作系统线程，CUDA

L.P. All rights reserved. Qcon Beijing April 21, 2018 Biye Li Team Manager, Data Technologies Automation Xiangqian Yu Team Lead, Derivatives Data From Keyboards to Neural Networks 从键盘到神经网络 © 2018 Bloomberg decision- making. 4 © 2018 Bloomberg Finance L.P. All rights reserved. What is Data Technologies Automation? Challenges – Scale of Financial Information Companies Market Types Speed To Market Problematic reserved. Final Notes Deep Learning can achieve superhuman accuracy for the right problems Automation is the only way to keep up with the exponential growth of data © 2018 Bloomberg Finance L.P.

them to transform large and complex models into smaller and efficient models capable of running on mobile and edge devices. We have also set up a couple of programming projects for a hands-on model optimization the structure is as follows. dbpedia_csv/ dbpedia_csv/train.csv dbpedia_csv/readme.txt dbpedia_csv/test.csv dbpedia_csv/classes.txt Let's explore the dataset! First, let's see what classes we have. import " Let's find the number of train and test examples. !wc -l dbpedia_csv/train.csv !wc -l dbpedia_csv/test.csv 560000 dbpedia_csv/train.csv 70000 dbpedia_csv/test.csv It all looks good! Now, it’s time

Such a model is useful if we want to deploy a model in a space constrained environment like a mobile device. To summarize, compression techniques help to achieve an efficient representation of a layer the storage space or the transmission bandwidth is expensive like deep learning models on mobile devices. Mobile devices are resource constrained. Hence, quantization can help to deploy models which would can be deployed in resource constrained environments like the mobile devices. Quantization has enabled a whole lot of models to run on mobile devices and IoTs which otherwise wouldn’t be possible. We have

D轮融资 估值70亿美元 7 旷视科技 计算机视觉技术等 安防 中国 2011年 D轮融资 估值40亿美元 8 科大讯飞 智能语音技术 综合 中国 1999年 上市 市值108亿美元 9 Automation Anywhere 自然语言处理技术、非结构化数据认知 企业管理 美国 2003年 B轮融资 估值68亿美元 10 IBM Watson（IBM沃森） 深度学习、智适应学习技术 计算机 美国