This course describes different types of computer vision use cases and then highlights different machine learning strategies for solving these use cases. The strategies vary from experimenting with pre-built ML models through pre-built ML APIs and AutoML Vision to building custom image classifiers using linear models, deep neural network (DNN) models or convolutional neural network (CNN) models. The course shows how to improve a model's accuracy with augmentation, feature extraction, and fine-tuning hyperparameters while trying to avoid overfitting the data. The course also looks at practical issues that arise, for example, when one doesn't have enough data and how to incorporate the latest research findings into different models. Learners will get hands-on practice building and optimizing their own image classification models on a variety of public datasets in the labs they will work on.
Really interesting labs in this course!.Thank you!
I would like to work with TPUs in one laboratory. Also, I would like to see how the pattern of image was formed throught the convolutional neural network in a lab.
Great course, great team, First week is as it was expected but second is week is outstanding. The Neural Architecture search(NAS) is outstanding. Super job.
Very good course on CNNs. The labs were cool. Thank you!
Some of the content could not be completed/needs to be updated. I ran into a few bugs/errors, but still wanted to learn the content/gain the certificate.
Everything is good except Lab of Transfer learning was missing.
End to End learning image undestanding from the scratch manual code to fully automated from Google Cloud Platform services
Fairly basic course and would have liked more guidance on setting up jobs for processing including sample JSON requests etc. However was interesting but definitely not challenging.
It was great! Not just a tutorial for Google Cloud tools, but a lot of theory and hands-on in machine learning code!
Great and detailed class! Although would be better experience if the GCP instance creation will be smoother.
The course is good however for 2020 it seems out of date as it uses TensorFlow v1 which is way more complex as compared to the last east v2.
Amazing course! Definitely recommend the course for learning Google's way to handle images! ;)
Showing: 20 of 63
Subscribing to this course only gives you option to run assignments on Qwik labs, and they're very poor for these kinds of assignments. You won't get any feedback on assignments anyway since there is no grader.
If you want to check out the material it's better to just clone training-data-analyst from github and do these assignments on GCP free tier.
思路很清晰，每一个课程讲解的都很明白，本觉得课程内容有些少，对于很多概念讲解的很浅显，但是想一下和门课主要是讲TensorFlow的，也就不这么苛刻了，老师语速适中，不十分推荐新手，尤其是英语不是特别棒的新手观看，少许有一些图像相关的了解看起来会快一些，还有就是觉得实验方面不是很好，主要还是感觉这种形式的实验其实自己在电脑上就可以做了，没必要很复杂的在GoogleCloud上费时间，希望改进一下Lab吧
a real eye opener education, it gave me lots of answers to the questions i had in this area. it is just amazing that ML can differ between roses and tulips !
Several quicklabs issues
TPU quicklabs does not work. Always getting access error. I added manually the rights, but then I have an error about import apache-beam.
AutoML Vision quicklabs needs to mention to enable per object ACL or you cannot set the ACL.
Datalab is very very slow to start, very painful.
Decent course. One of the labs does not seem to be really about transfer learning. Some of the screenshots in the lab instructions are outdated and incorrect. Unresponsive discussion forum. I wouldn't have paid for this course, had I known the issues in advance.
information not updated
Most labs don't work or are pointless
The labs don't work, I've been in contact with the support team for more than a month, still not able to use the labs which are the whole point of taking this course. So much of my time has been wasted in this process.
Can't able to access any of the labs.
Was worried this would be just another CNN course but it was so much more. Showing out to use existing models etc. The details on CNN is a little lite but that can be found elsewhere. What was really good was the batch normalization and using pre-trained models but just changing the dense layers to provide classification,
Great course, great team, First week is as it was expected but second is week is outstanding. The Neural Architecture search(NAS) is outstanding. Super job.
End to End learning image undestanding from the scratch manual code to fully automated from Google Cloud Platform services
It was great! Not just a tutorial for Google Cloud tools, but a lot of theory and hands-on in machine learning code!
Excelente recorrido por los conceptos básicos de RNN - CNN y su aplicación a problemas de visión por computador.
Great and detailed class! Although would be better experience if the GCP instance creation will be smoother.
this Courser teach a ongoing technique in GCP, and the world
The AUTOML is fascinated technique for learning
Definitely amazing course, the way that they've shown to us was brilliant. Thanks Google for this.
Amazing course! Definitely recommend the course for learning Google's way to handle images! ;)
A very good course, with cutting edge research about Deep Learning, Go google :-) !
It was One of the great course having labs which was really fun