Sign in
Categories
Migration Mapping Assistant Your Saved List Partners Sell in AWS Marketplace Amazon Web Services Home Help

Reviews from AWS Marketplace

0 AWS reviews
  • 5 star
    0
  • 4 star
    0
  • 3 star
    0
  • 2 star
    0
  • 1 star
    0

External reviews

43 reviews
from G2

External reviews are not included in the AWS star rating for the product.


    Computer Software

I used TensorFlow for my some of course projects

  • September 01, 2020
  • Review provided by G2

What do you like best?
It is open-source and can use for different platforms. There are lots of tutorials available that can make help students when that stuck in some part. Also, I really like the visualization tools of that through TensorBoar.
What do you dislike?
I have a windows machine and there is no support for Windows
What problems are you solving with the product? What benefits have you realized?
I used for my text analysis class and machine learning class to solve the class project on time series and CNN
Recommendations to others considering the product:
The best way to use it is through python because there are lots of tutorials for that. Also, using Keras through TensorFlow is also fabulous


    Higher Education

Using Deep Neurals Nets with a few lines of code

  • August 11, 2020
  • Review provided by G2

What do you like best?
The Keras API: it makes building, training, working with DNNs, CNNs very easy. It requires only a very small knowlegde of (python) coding. Line by line one can add layers to the network to construct it, and the built-in optimizers do the training. No need to go through the pain if implementing backprop or optimizations steps on your own.
Also nice: the support for GPUs which really speeds up all computions.
What do you dislike?
The (remants of) older TF versions using weird and sometimes incomprehensible stuff like placeholder, logits, etc.
What problems are you solving with the product? What benefits have you realized?
As of now, used TF mainly as coding environent to actually learn ML, DNNs etc. The nice Keras API really helped me a lot to start my own ML exercise projects.


    Chemicals

Neural network at your hands

  • August 08, 2020
  • Review verified by G2

What do you like best?
Neural network application has become so easy. User now no need to focus on the development and optimising the models, and rather could stay more focused with the application part of it.
What do you dislike?
Required Memory and ram size could be optimized.
What problems are you solving with the product? What benefits have you realized?
Manufacturing requirements lated challenges. Modeling the frameworks using tensor flow is now easy and handy.
Recommendations to others considering the product:
Using tensor flow the user gets the space to focus more towards the application perspective rather than spending time on its development.


    Aravind S.

Best way to jump start ML development

  • August 08, 2020
  • Review verified by G2

What do you like best?
The Keras interface is super cool for beginners. Once you get comfortable, there are ample option to customize the data access during training and export the model.
What do you dislike?
Its lerning curve is a little steep once you cross the beginners threshold. But can say its the worst :).
What problems are you solving with the product? What benefits have you realized?
I worked on using ML in solving classification of signal events from background events in data from Particle Physics experiments. I was able to make a new classifier that had 90%+ purity compared to the existing benchmark of 70%. The model deployment was also pretty quick with GPU back-end available. I am now working on porting things to FPGA based accelerator and the framework I am using supports TF too.. The wide documentation and user support forums are plus points too.


    Research

Essential Toolkit for Machine Learning and Deep Learning Research and Development Projects

  • August 07, 2020
  • Review provided by G2

What do you like best?
Useful in all stages of development and production as well as most types of research work. It also gathers extensive pre-built and pre-trained systems and allows high level and low level access to most if not all components of the model.
What do you dislike?
The team behind tensorflow is doing a great job and there is very little to dislike about it. Of course like every library, first comers will take a bit of time to get acquainted to it but it is getting easier to use with every version update.For new comers, watch out of the big shifts between some versions, which might require a bit of more work for compatibility.
What problems are you solving with the product? What benefits have you realized?
I am solving research problems and production level applications in the domain of human-agent interactions (using several different modalities of the human expressions: speech, vision and motion capture mainly). Tensorflow facilitates both quick prototyping and implementation of production level systems .
Recommendations to others considering the product:
1-Usually the team takes care of compatibility problems but the users must be aware that they exist.
2-Conda's installation facilitate the installation of dependency libraries such as CUDA for the GPU version.


    Research

Mechanical engineering PhD student who used TensorFlow in his research.

  • August 05, 2020
  • Review provided by G2

What do you like best?
Rapid prototyping. Especially in building a neural network.
What do you dislike?
The documentation some times don't have plenty of examples for different scenarios
What problems are you solving with the product? What benefits have you realized?
Chemical reactions in materials.


    Telecommunications

Tensorflow Deep learning framework

  • January 02, 2020
  • Review provided by G2

What do you like best?
Tensorflow is the package available in python for creating neural network. Best part of tensor flow is we can create the complex machine learning model in just few lines of code.
What do you dislike?
Sometimes i feel as complexity of the data increases, speed is the concern. it takes more time.
What problems are you solving with the product? What benefits have you realized?
I use to create complex machine learning model and creating deep neural networks for my some tasks.
Recommendations to others considering the product:
It is one of the best way to train test and develope your neural network in few line of codes.


    Computer Software

building a CNN for my Data

  • November 20, 2019
  • Review provided by G2

What do you like best?
lots of my peers and university use this so lots of examples
What do you dislike?
It should have code expansions for some funtions to keep cleaner code
What problems are you solving with the product? What benefits have you realized?
developing a ML model for my data, wrote a CNN for my Data
Recommendations to others considering the product:
It's necessary in my profession


    Computer Software

Using it on daily basis

  • October 02, 2019
  • Review provided by G2

What do you like best?
I like it's new version 2.0 because they include keras workflow with TF and distributed computing.
What do you dislike?
I dislike the most it that it low level API, we have to define placeholders, session.
What problems are you solving with the product? What benefits have you realized?
Deep Learning can't be easy without Tensorflow and keras.


    Financial Services

If you do machine learning...

  • August 08, 2019
  • Review provided by G2

What do you like best?
Pretty much won the battle of what library to use for machine learning problems. Has everything you need for foundational building blocks of large scale calculations
What do you dislike?
Not much in the way of cons as everyone is using tensorflow. A little difficult to set up with a gpu
What problems are you solving with the product? What benefits have you realized?
Machine learning problems
Recommendations to others considering the product:
Use it for any machine learning problems!