Chevron Left
Вернуться к Convolutional Neural Networks in TensorFlow

Отзывы учащихся о курсе Convolutional Neural Networks in TensorFlow от партнера deeplearning.ai

4.7
звезд
Оценки: 7,157
Рецензии: 1,116

О курсе

If you are a software developer who wants to build scalable AI-powered algorithms, you need to understand how to use the tools to build them. This course is part of the upcoming Machine Learning in Tensorflow Specialization and will teach you best practices for using TensorFlow, a popular open-source framework for machine learning. In Course 2 of the deeplearning.ai TensorFlow Specialization, you will learn advanced techniques to improve the computer vision model you built in Course 1. You will explore how to work with real-world images in different shapes and sizes, visualize the journey of an image through convolutions to understand how a computer “sees” information, plot loss and accuracy, and explore strategies to prevent overfitting, including augmentation and dropout. Finally, Course 2 will introduce you to transfer learning and how learned features can be extracted from models. The Machine Learning course and Deep Learning Specialization from Andrew Ng teach the most important and foundational principles of Machine Learning and Deep Learning. This new deeplearning.ai TensorFlow Specialization teaches you how to use TensorFlow to implement those principles so that you can start building and applying scalable models to real-world problems. To develop a deeper understanding of how neural networks work, we recommend that you take the Deep Learning Specialization....

Лучшие рецензии

RB
14 мар. 2020 г.

Nice experience taking this course. Precise and to the point introduction of topics and a really nice head start into practical aspects of Computer Vision and using the amazing tensorflow framework..

MS
12 нояб. 2020 г.

A really good course that builds up the knowledge over the concepts covered in Course 1. All the ideas are applicable in real world scenario and this is what makes the course that much more valuable!

Фильтр по:

726–750 из 1,116 отзывов о курсе Convolutional Neural Networks in TensorFlow

автор: Mochammad G R M

2 апр. 2021 г.

Thanks

автор: Jeff D

5 нояб. 2020 г.

Thanks

автор: Josef N

19 июня 2020 г.

great!

автор: Sarath S

16 сент. 2021 г.

great

автор: Ben B

6 мая 2020 г.

Great

автор: Aji S

3 мая 2020 г.

great

автор: Muhammad N

10 авг. 2021 г.

nice

автор: Ken T

8 авг. 2021 г.

good

автор: Suci A S

19 июня 2021 г.

good

автор: Alivia Z

25 апр. 2021 г.

wowo

автор: Roberto

16 апр. 2021 г.

good

автор: Ahmad H N

26 мар. 2021 г.

Good

автор: Indah D S

19 мар. 2021 г.

cool

автор: tg l

17 янв. 2021 г.

good

автор: Johnnie W

22 сент. 2020 г.

good

автор: RAGHUVEER S D

25 июля 2020 г.

good

автор: Rifat R

7 июня 2020 г.

Good

автор: PANG M Q

29 мая 2020 г.

good

автор: Amit K

13 мая 2020 г.

Good

автор: Nho N

17 мар. 2020 г.

good

автор: zhenzhen w

18 нояб. 2019 г.

nice

автор: Jurassic

6 сент. 2019 г.

good

автор: 林韋銘

20 авг. 2019 г.

gj

автор: Islam U

24 янв. 2021 г.

The course definitely teaches interesting techniques (Dropout, Transfer Learning) and tools (use of ImageDataGenerator). What i think would be an improment point is further tips on how to actually achieve a state of art (or really high quality) models. For example for full Cats and Dogs dataset from Kaggle, there was an optional ungraded work that asked to achieve over 99.9% accuracy on both training/validated datasets. It would be great if some tips on how to achieve this would be given. Maybe some discussion of network architectures that can achieve this, as this subject is not always covered, while it plays probably a dominant role whether you make it or break it. Otherwise, i liked the course and thanks for wonderfull explanations.

P.s. week 4 final graded task is structured suboptimally, so maybe it can be reviewed, as many people struggling with many sorts of errors.

автор: Xiaolong L

20 февр. 2021 г.

In general a very good course. But it seems that the instructor could have put more work into the weekly projects. For example, the weekly project for the 3rd week is almost the same as that of week 2. Also, one of the week boasted that the project involves training on the full dogs vs cats dataset but it is actually still just a subset. I was able to run on the full data set by downloading and loading them manually. I can see that the platform has concerns on the computational resources usage, but it should at least be accurate on in the project descriptions.