學生對 Coursera Project Network 提供的 TensorFlow for CNNs: Transfer Learning 的評價和反饋
This guided project course is part of the "Tensorflow for Convolutional Neural Networks" series, and this series presents material that builds on the second course of DeepLearning.AI TensorFlow Developer Professional Certificate, which will help learners reinforce their skills and build more projects with Tensorflow.
In this 1.5-hour long project-based course, you will learn how to apply transfer learning to fine-tune a pre-trained model for your own image classes, and you will train your model with Tensorflow using real-world images. By the end of this project, you will have applied transfer learning on a pre-trained model to train your own image classification model with TensorFlow.
This class is for learners who want to learn how to apply transfer learning to re-use pre-trained models to create a new model, work with convolutional neural networks and use Python for building convolutional neural networks with TensorFlow, and for learners who are currently taking a basic deep learning course or have already finished a deep learning course and are searching for a practical deep learning project with TensorFlow project. Also, this project provides learners with further knowledge about creating and training convolutional neural networks and improves their skills in Tensorflow which helps them in fulfilling their career goals by adding this project to their portfolios....
1 - TensorFlow for CNNs: Transfer Learning 的 2 個評論（共 2 個）
創建者 Priscila A B
創建者 Diego F B H
The explanation is interesting, still, I have the doubt if we can initialize the weights and retain all layer 🤔