Classification with Transfer Learning in Keras
In this 1.5 hour long project-based course, you will learn to create and train a Convolutional Neural Network (CNN) with an existing CNN model architecture, and its pre-trained weights. We will use the MobileNet model architecture along with its weights trained on the popular ImageNet dataset. By using a model with pre-trained weights, and then training just the last layers on a new dataset, we can drastically reduce the training time required to fit the model to the new data . The pre-trained model has already learned to recognize thousands on simple and complex image features, and we are using its output as the input to the last layers that we are training. In order to be successful in this project, you should be familiar with Python, Neural Networks, and CNNs. 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.
Convolutional Neural Network
由 RR 提供Jul 13, 2020
More detailed explanation could be given about functions used, parameters
由 MS 提供May 7, 2020
Its first time I went to the Keras and TensorFlow they are super easy to implement.
由 AS 提供Jun 20, 2020
How else would I have learned this? What a great fast way to apply a concept in real code.
由 TH 提供Sep 10, 2020
good presentation, but It will be better more details explanations of about for training model parameters and predict accuracy.