TensorFlow Developer Certificate, Exercises of Computer Vision

Download TensorFlow Developer Certificate and more Exercises Computer Vision in PDF only on Docsity!

TensorFlow Developer Ceicate

Candidate Handbook

Please review this handbook in its entirety prior to registering and taking the exam. Last Updated: August 12, 2021

Contents

Exam details

Criteria Skills checklist Exam environment Exam time limit Exam URL

Candidate identication and authentication

Resources allowed during exam

Eligibility

Registration

Fees and payment

Taking the exam

Results

Retaking the exam

Length of validity of the ceicate

Statement of non-discrimination

Contact Email: [email protected] Web: www.tensorflow.org/certificate

❏ Build and train models for binary classication. ❏ Build and train models for multi-class categorization. ❏ Plot loss and accuracy of a trained model. ❏ Identify strategies to prevent oveiing, including augmentation and dropout. ❏ Use pretrained models (transfer learning). ❏ Extract features from pre-trained models. ❏ Ensure that inputs to a model are in the correct shape. ❏ Ensure that you can match test data to the input shape of a neural network. ❏ Ensure you can match output data of a neural network to specied input shape for test data. ❏ Understand batch loading of data. ❏ Use callbacks to trigger the end of training cycles. ❏ Use datasets from dierent sources. ❏ Use datasets in dierent formats, including json and csv. ❏ Use datasets from .data.datasets. (3) Image classication You need to understand how to build image recognition and object detection models with deep neural networks and convolutional neural networks using TensorFlow 2.x. You need to know how to: ❏ Dene Convolutional neural networks with Conv2D and pooling layers. ❏ Build and train models to process real-world image datasets. ❏ Understand how to use convolutions to improve your neural network. ❏ Use real-world images in dierent shapes and sizes.. ❏ Use image augmentation to prevent oveiing. ❏ Use ImageDataGenerator. ❏ Understand how ImageDataGenerator labels images based on the directory structure. (4) Natural language processing (NLP) You need to understand how to use neural networks to solve natural language processing problems using TensorFlow. You need to know how to: ❏ Build natural language processing systems using TensorFlow. ❏ Prepare text to use in TensorFlow models. ❏ Build models that identify the category of a piece of text using binary categorization ❏ Build models that identify the category of a piece of text using multi-class categorization

❏ Use word embeddings in your TensorFlow model. ❏ Use LSTMs in your model to classify text for either binary or multi-class categorization. ❏ Add RNN and GRU layers to your model. ❏ Use RNNS, LSTMs, GRUs and CNNs in models that work with text. ❏ Train LSTMs on existing text to generate text (such as songs and poetry) (5) Time series, sequences and predictions You need to understand how to solve time series and forecasting problems in TensorFlow. You need to know how to: ❏ Train, tune and use time series, sequence and prediction models. ❏ Train models to predict values for both univariate and multivariate time series. ❏ Prepare data for time series learning. ❏ Understand Mean Absolute Error (MAE) and how it can be used to evaluate accuracy of sequence models. ❏ Use RNNs and CNNs for time series, sequence and forecasting models. ❏ Identify when to use trailing versus centred windows. ❏ Use TensorFlow for forecasting. ❏ Prepare features and labels. ❏ Identify and compensate for sequence bias. ❏ Adjust the learning rate dynamically in time series, sequence and prediction models. Note Our website, tensorflow.org/certificate recommends courses for learning the skills that are tested in this exam. However, the exam does not test the syllabus of any particular course. The exam may include questions not specifically addressed in any of the suggested courses. All knowledge tested in the exam is adequately covered in the guides and tutorials on tensorflow.org.

Primary ID (non-expired and including photograph and signature) Secondary ID (non-expired and including signature with Candidate name in Latin characters) Passport Government-issued driver’s license/permit Government-Issued local language ID (plastic card with photo and signature) National Identity card State or province-issued identity card Health Insurance Card U.S. Social Security Card Exams may be administered to citizens of a sanctioned country listed below PROVIDED the citizens are tested OUTSIDE the sanctioned country and their exam registration and current ID show an address OUTSIDE the sanctioned country. ● Cuba ● Iran ● Syria ● Sudan ● North Korea ● Crimea Region of Ukraine Resources allowed during exam You may use whatever learning resources you would normally use during your ML development work.

Eligibility You must test as an individual. The certificate is only available for natural persons, not corporations or other legal entities. Registration You must be registered to be eligible to take the exam. To register for the exam, go here. To complete the checkout, you will be prompted to enter payment information, and read and accept the Terms and Conditions for Exam Registration. The exam may be taken at your convenience. You are not required to take the exam at the time of registration and payment. Fees and payment The exam cost is $100 USD, which includes one exam attempt. You have 6 months from the date of purchasing the exam to take the exam before your purchase expires. Please note that we are offering a limited number of stipends to partially cover the cost of taking the TensorFlow certificate to help ensure this opportunity is accessible for everyone. More details can be found on our website. Taking the exam After you download the plugin and sign in, your exam will be provided to you. You will have a maximum of five hours to complete the exam. If you have not completed the exam after five hours it will be auto-submitted for you. Results After you submit your exam, it will be graded and your score will be posted to your Candidate

Portal. If you pass the exam, your name and email will be sent to a third party company who will