TensorFlow Developer Certificate考試相關資源蒐集
3 min readSep 11, 2020
#2020/10/05更新：
已完成考試報名，最後考試日期為4月5日。希望能在今年以前完成考試
Your exam attempt for the TensorFlow Developer will expire on Mon, 05 Apr 2021 00:24:13 -0500TensorFlow考試相關資源蒐集：
100美金報名費
5小時解題(使用PyCharm)
3年後過期
台灣目前只有4個人通過考試的樣子先學會在使用PyCharm的環境下重建所有TensorFlow in Practice Specialization的程式碼
https://www.youtube.com/playlist?list=PLQY2H8rRoyvwLbzbnKJ59NkZvQAW9wLbx學習資源:
Hands-on Machine Learning with Scikit-Learn, Keras and TensorFlow 2nd Edition
Chapter 10: Introduction to Artificial Neural Networks with Keras
Chapter 11: Training Deep Neural Networks
Chapter 12: Custom Models and Training with TensorFlow
Chapter 13: Loading and Preprocessing Data with TensorFlow
Chapter 14: Deep Computer Vision Using Convolutional Neural Networks
Chapter 15: Processing Sequences Using RNNs and CNNs
Chapter 16: Natural Language Processing with RNNs and Attention[2020/09/12完成]
Introduction to Deep Learning by MIT
The first 3 lectures, deep learning (in general), Convolutional Neural Networks (usually used for computer vision) and Recurrent Neural Networks (usually used for text processing) are the most relevant to the exam.
https://github.com/aamini/introtodeeplearning/
http://introtodeeplearning.com/Getting started with PyCharm
https://www.jetbrains.com/pycharm/learning-center/官方考試指南
https://www.tensorflow.org/site-assets/downloads/marketing/cert/Setting_Up_TF_Developer_Certificate_Exam.pdfhttps://www.tensorflow.org/site-assets/downloads/marketing/cert/TF_Certificate_Candidate_Handbook.pdfTensorFlow in Practice
https://www.coursera.org/specializations/tensorflow-in-practicedataset的載入、資料預處理相當重要
https://www.tensorflow.org/api_docs/python/tf/data/Dataset
建議使用GPU進行Model訓練(用Colab或aiForge)(5小時時間限制)，最後將模型傳回考試資料夾即可
需要訓練CNN、LSTM或GRU模型
有遇到錯誤要參考[https://towardsdatascience.com/how-i-passed-the-tensorflow-developer-certification-exam-f5672a1eb641]
My broken Python interpreter
A concept I’d read in the book would get cemented by code examples in the Coursera specialization and eventually summarised by the MIT video.Basic/Simple model
Model from learning dataset
Convolutional Neural Network with real-world image dataset
NLP Text Classification with real-world text dataset
Sequence Model with real-world numeric datasetIt’s an open book test. But you need to score 90% or more to pass. If you don’t pass, you must wait 14 days before taking it a second time, two months for the third attempt, and one year for the 4th exam.Five models that you will have to code, increasing in difficulty. You don’t start from scratch. There’s the question (as comments) on top of the Python file, and prompts where needed (for example, to load the data, or to build the model itself). It is clearly marked where you have to add some magic by ‘#Add your code here’ comments.you get the 5/5. You can submit a model as many times as you need, with no penalization.upgraded both, tensorflow and tensorflow-estimator to the latest version. PyCharm lets you choose which version you want installed, so I thought I could always downgrade them if that broke the exam… But it did not! And I have to say that my accuracy went up an incredible 5% only by doing the upgrade.Add more epochs to the training and let it converge more. The result, a 5/5 score! On to the next question.
So trying a couple of times to send the model is my last tip for you.I submitted the exam (remember, you must have run and ‘submit and test’ each question at least once)… and immediately got an email with the news. There is no score on it (the candidate handbook says you need a 90% to pass, and not all the questions have the same weight).Make sure your PyCharm with the most updated version is working, your GPU is working, and all the packages version meets the exam requirements.please don’t struggle to improve 5% accuracy for more than 20 minutes.use tf.keras.callbacks.ModelCheckpoint() to save your model during training to avoid unnecessarily retraining tasks. Believe me, it could frustrate you so much during the exam, especially when you solve NLP questions.Google Developer Certificate plugin in PyCharm, it’s because you have PyCharm version 2019.3 and the plugin doesn’t support this version. Just simply update PyCharm to version 2020.1.