3 -3-تعلم الالة-Lesson 3 Deep Learning 2019 Data blocks Multi label classification Segmentation

114- 3 -3-تعلم الالة-Lesson 3 Deep Learning 2019 Data blocks Multi label classification Segmentation
https://youtu.be/GoGcMqASLas

113- 3 -2-تعلم الالة-Lesson 3 Deep Learning 2019 Data blocks Multi label classification Segmentation
https://youtu.be/B8fSI5OJoyo
112- 3 -1-تعلم الالة-Lesson 3 Deep Learning 2019 Data blocks Multi label classification Segmentation
https://youtu.be/WjjXCI8-4kc

101 - تعلم الالة- Lesson 2 - 2 Deep Learning 2019 Image classification
https://youtu.be/kykqSDsKAqw

100 - تعلم الالة- Lesson 2 -1 Deep Learning 2019 Image classification
https://youtu.be/tES-AOVKSuM

99 - تعلم الالة- Lesson 1 - 2 Deep Learning 2019 Image classification
https://youtu.be/TPzGj5UuSe0

98 - تعلم الالة- Lesson 1 - 1 Deep Learning 2019 Image classification
https://youtu.be/6AkEAXsN8Ng

تابعونا على ليصلكم كل جديد

يوتيوب

https://www.youtube.com/channel/UC9-a4I9rw-ulKxSEuUqYmSg…

فيس بوك

https://www.facebook.com/groups/Smartfamily2020/?ref=bookmarks

https://www.facebook.com/Maintenanceoflaptopcomputers/?eid=ARCh8WpdjOH0Jskr0c-hC0P6MKlZdhvozX4u9kU-0gR2GWhHWW8yJPRK71EaNKYzQpktI7fi_2LKRR5x

تلكرام

https://t.me/Aymenz_chenal

تويتر
https://twitter.com/Ayman32969179



We start lesson 3 looking at an interesting dataset: Planet's Understanding the Amazon from Space. In order to get this data into the shape we need it for modelling, we'll use one of fastai's most powerful (and unique!) tools: the data block API (https://docs.fast.ai/data_block.html). We'll be coming back to this API many times over the coming lessons, and mastery of it will make you a real fastai superstar! Once you've finished this lesson, if you're ready to learn more about the data block API, have a look at this great article: https://blog.usejournal.com/finding-d...

One important feature of the Planet dataset is that it is a *multi-label* dataset. That is: each satellite image can contain *multiple* labels, whereas previous datasets we've looked at have had exactly one label per image. We'll look at what changes we need to make to work with multi-label datasets.

Next, we will look at *image segmentation*, which is the process of labelling every pixel in an image with a category that shows what kind of object is portrayed by that pixel. We will use similar techniques to the earlier image classification models, with a few tweaks. fastai makes image segmentation modelling and interpretation just as easy as image classification, so there won't be too many tweaks required.

We will be using the popular Camvid dataset for this part of the lesson. In future lessons, we will come back to it and show a few extra tricks. Our final Camvid model will have dramatically lower error than a model we've been able to find in the academic literature!

What if your dependent variable is a continuous value, instead of a category? We answer that question next, looking at a keypoint dataset, and building a model that predicts face keypoints with high accuracy.