Creating Multi Task Models With Keras
65 個評分

3,413 人已註冊
Creating multi-task models with Keras
Training multi-task models with Keras
在面試中展現此實踐經驗
65 個評分
3,413 人已註冊
Creating multi-task models with Keras
Training multi-task models with Keras
在面試中展現此實踐經驗
In this 1 hour long guided project, you will learn to create and train multi-task, multi-output models with Keras. You will learn to use Keras' functional API to create a multi output model which will be trained to learn two different labels given the same input example. The model will have one input but two outputs. A few of the shallow layers will be shared between the two outputs, you will also use a ResNet style skip connection in the model. If you are familiar with Keras, you have probably come across examples of models that are trained to perform multiple tasks. For example, an object detection model where a CNN is trained to find all class instances in the input images as well as give a regression output to localize the detected class instances in the input. Being able to use Keras' functional API is a first step towards building complex, multi-output models like object detection models. We will be using TensorFlow as our machine learning framework. The project uses the Google Colab environment. You will need prior programming experience in Python. You will also need prior experience with Keras. Consider this to be an intermediate level Keras project. This is a practical, hands on guided project for learners who already have theoretical understanding of Neural Networks, Convolutional Neural Networks, and optimization algorithms like gradient descent but want to understand how to use use Keras to write custom, more complex models than just plain sequential neural networks. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.
Prior programming experience in Python. Conceptual understanding of Neural Networks. Prior experience with TensorFlow and Keras is recommended.
Deep Learning
Machine Learning
Tensorflow
Computer Vision
keras
在與您的工作區一起在分屏中播放的視頻中,您的授課教師將指導您完成每個步驟:
Introduction
Create Dataset
Dataset Generator
Create Model
Train the Model
Final Predictions
您的工作空間就是瀏覽器中的雲桌面,無需下載
在分屏視頻中,您的授課教師會為您提供分步指導
由 GP 提供
2021年6月30日This course is pretty good, that I learned many concepts in one hour. The instructor too very good that his way of explanation made me to understand it quickly.
由 MS 提供
2021年5月14日Amit is awesome. You are one the best instructors/teachers , I have ever seen in my life.
由 SK 提供
2021年2月22日The project was simple yet provided the core idea of going for multitask model with an interesting use-case.
由 CM 提供
2022年2月5日An useful practice and review of keras functional api.
由於您的工作空間包含適合筆記本電腦或台式計算機使用的雲桌面,因此指導項目不在移動設備上提供。
指導項目授課教師是特定領域的專家,他們在項目的技能、工具或領域方面經驗豐富,並且熱衷於分享自己的知識以影響全球數百萬的學生。
您可以從指導項目中下載並保留您創建的任何文件。為此,您可以在訪問云桌面時使用‘文件瀏覽器’功能。
您可在頁面頂部點按此指導項目的經驗級別,查看任何知識先決條件。對於指導項目的每個級別,您的授課教師會逐步為您提供指導。
是,您可以在瀏覽器的雲桌面中獲得完成指導項目所需的一切。
您可以直接在瀏覽器中於分屏環境下完成任務,以此從做中學。在屏幕的左側,您將在工作空間中完成任務。在屏幕的右側,您將看到有授課教師逐步指導您完成項目。
還有其他問題嗎?請訪問 學生幫助中心。