课程: Apache Spark Deep Learning Essential Training
今天就学习课程吧!
今天就开通帐号,24,100 门业界名师课程任您挑!
Transfer learning in action - Spark DataFrames教程
课程: Apache Spark Deep Learning Essential Training
Transfer learning in action
- [Instructor] So, we're going to do transfer learning using the ResNet50 model. Now, the ResNet50 model has been trained on the ImageNet data set, which has 1,000 classes. So, we've got a couple of varieties of flowers in the flower data set that we'll use. We've got daisies, dandelions, roses, sunflowers, and tulips. Now, it so happens that daisies are one of the 1,000 categories in ImageNet, so we won't pick them. Instead we'll use transfer learning to distinguish between two classes of flowers, tulips and sunflowers. So, let's head over to the notebook, so I select Workspace, I select the down arrow, I select Import, Browse, I select the notebook 04_03_begin. I select Import, so we'll do our usual checks, confirm that we've got the correct libraries installed. I select Attach and Run to attach this notebook to the cluster. And then what you're going to do is to download the flower data set. Enter and unzip it, go into the flower photos and just confirm that we've got the different…
随堂练习,边学边练
下载课堂讲义。学练结合,紧跟进度,轻松巩固知识。