Chevron Left
返回到 Classification with Transfer Learning in Keras

學生對 Coursera Project Network 提供的 Classification with Transfer Learning in Keras 的評價和反饋

4.5
149 個評分
19 條評論

課程概述

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....

熱門審閱

AS
2020年6月20日

How else would I have learned this? What a great fast way to apply a concept in real code.

SK
2020年5月28日

Everything was as per description! Need more advanced tasks. Thanks, Amit Sir!

篩選依據:

1 - Classification with Transfer Learning in Keras 的 19 個評論(共 19 個)

創建者 Mudit D

2020年7月1日

A little more in-depth explanation would be better, but if you're approaching this project, chances are you have enough knowledge and momentum to research and learn and figure things out yourself. If you're a hobbyist or need to learn these skills for your job, this is a superb fast-track to getting something that works ready for use. As with Data Science things, for true mastery, more study will be required, but this is a great start. For DL noobs like myself, I recommend reading a few articles on CNN, Image Classification and what Keras is. Perhaps just spend an hour reading whatever you come across (without fussing too much over details) and then dive in. Do not be intimidated by the 'Intermediate' rating of this Guided Project, and then dive right in. It is really quite great and unintimidating.

創建者 Harshad L

2020年6月7日

Great tutorial with hands on. But want more explanation about MobileNet Layers structure. And its little more features based customisation. At-least provide some documents for more reading & development. Overall good platform to start with..!!!

創建者 Alex S

2020年6月20日

How else would I have learned this? What a great fast way to apply a concept in real code.

創建者 Sarah K

2020年5月29日

Everything was as per description! Need more advanced tasks. Thanks, Amit Sir!

創建者 M V

2020年6月3日

Great course, surely learnt a lot.

創建者 EDWIN J

2020年6月15日

wonderful and simple project

創建者 Kamlesh C

2020年6月20日

thank you

創建者 Gaikwad N

2020年7月23日

Good

創建者 p s

2020年6月25日

Good

創建者 tale p

2020年6月23日

good

創建者 Patil B

2020年5月2日

nice

創建者 Ali E

2020年3月22日

Good course, but still misses a key step: how to save and reuse the modified model without having to rebuild it from scratch? Literature about this topic is at best ambiguous if not flat out lacking. You should include the method for saving and reloading customized models with custom layers and/or standard layers that have been added to the pre-trained models.

創建者 Yubesny V

2020年11月13日

La interfaz en la plataforma de la nube fue un poco lenta, así que me alcanzó el tiempo suficiente para terminar la programación, sin embargo, no me quedó tiempo para volver a repasar el código para reforzar lo aprendido.

創建者 Utkarsh R

2020年3月24日

Learning a topic using Hands on project is way better than passive learning in my opinion. Explanation could've been much better. They can use slides and animation to explain the core functioning of objects.

創建者 Thanda H

2020年9月11日

good presentation, but It will be better more details explanations of about for training model parameters and predict accuracy.

創建者 Mr. M K S E

2020年5月8日

Its first time I went to the Keras and TensorFlow they are super easy to implement.

創建者 Raj v

2020年7月14日

More detailed explanation could be given about functions used, parameters

創建者 Rathi.R

2020年6月11日

good

創建者 Jorge G

2021年2月25日

I do not recommend taking this type of course, take one and pass it, however after a few days I have tried to review the material, and my surprise is that it asks me to pay again to be able to review the material. Of course coursera gives me a small discount for having already paid it previously.