MS
Nov 12, 2020
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!
RB
Mar 14, 2020
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..
By Zain A
•Mar 19, 2023
noice
By Sarath S
•Sep 16, 2021
great
By Ben B
•May 6, 2020
Great
By Wira A S
•May 3, 2020
great
By Dini P U
•Nov 2, 2023
good
By SRIKANTH K
•Jun 28, 2022
good
By Muhammad N
•Aug 10, 2021
nice
By Ken T
•Aug 8, 2021
good
By Suci A S
•Jun 19, 2021
good
By Alivia Z
•Apr 25, 2021
wowo
By Roberto
•Apr 16, 2021
good
By Ahmad H N
•Mar 26, 2021
Good
By Indah D S
•Mar 19, 2021
cool
By tg l
•Jan 17, 2021
good
By Johnnie W
•Sep 22, 2020
good
By RAGHUVEER S D
•Jul 25, 2020
good
By Rifat R
•Jun 7, 2020
Good
By PANG M Q
•May 29, 2020
good
By Amit K
•May 13, 2020
Good
By Nho N
•Mar 17, 2020
good
By zhenzhen w
•Nov 18, 2019
nice
By Jurassic
•Sep 6, 2019
good
By Ming G
•Aug 20, 2019
gj
By Islam U
•Jan 24, 2021
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.
By Uriel S
•Mar 6, 2023
The course itself was good, but the assignments were worse than in the first course. You are basically forced to either use google colab during some of the tests and during some of the practices. I dislike this, specially because my machine can train the models faster, without using colab's resources which i might need for something else. I also find it a bit annoying considering that in the previous course they provided a virtual env you could use.
Additionally some of the assignments weren't quite solvable with the content shown during the course. It wouldn't be a big deal, but since training the model was done on colab when you had to try new things, for example to reach a higher accuracy, it was slow and time consuming specially with big datasets.