Reviews from AWS Marketplace
0 AWS reviews
-
5 star0
-
4 star0
-
3 star0
-
2 star0
-
1 star0
External reviews
External reviews are not included in the AWS star rating for the product.
Mechanical engineering PhD student who used TensorFlow in his research.
What do you like best about the product?
Rapid prototyping. Especially in building a neural network.
What do you dislike about the product?
The documentation some times don't have plenty of examples for different scenarios
What problems is the product solving and how is that benefiting you?
Chemical reactions in materials.
- Leave a Comment |
- Mark review as helpful
Tensorflow Deep learning framework
What do you like best about the product?
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 about the product?
Sometimes i feel as complexity of the data increases, speed is the concern. it takes more time.
What problems is the product solving and how is that benefiting you?
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.
building a CNN for my Data
What do you like best about the product?
lots of my peers and university use this so lots of examples
What do you dislike about the product?
It should have code expansions for some funtions to keep cleaner code
What problems is the product solving and how is that benefiting you?
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
Using it on daily basis
What do you like best about the product?
I like it's new version 2.0 because they include keras workflow with TF and distributed computing.
What do you dislike about the product?
I dislike the most it that it low level API, we have to define placeholders, session.
What problems is the product solving and how is that benefiting you?
Deep Learning can't be easy without Tensorflow and keras.
If you do machine learning...
What do you like best about the product?
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 about the product?
Not much in the way of cons as everyone is using tensorflow. A little difficult to set up with a gpu
What problems is the product solving and how is that benefiting you?
Machine learning problems
Recommendations to others considering the product:
Use it for any machine learning problems!
Most powerful machine learning framework to train model.
What do you like best about the product?
Three different crowds use Tensorflow : Researcher , data scientist and developer. Ideally they there were no so such which can collaborate three of them and provide better efficiency. Tensorflow was the solution they created to solve this problem. The library was to scale, it was made to run on multiple CPU's or GPU's and even mobile OS and it has several wrappers. From installation to deployment Tensorflow is the easiest among all the other platform which provide cross cross-platform deployment. Tensorflow provide decent event handling, graph management, image management and best feature is tensorboard.
What do you dislike about the product?
Tensorflow is powerful in terms of performance but with less area to work with. It will restrict you from as tweaking of algorithms in it is quite a complex task. Since the release of Tensorflow 2.0, tensorflow has gain leverage over other framework but its community is still growing and sometime its very hard to find answers when you are stuck in your work.
What problems is the product solving and how is that benefiting you?
For model training and mostly we have used tensorflow as it provide multiple platform deployment.
An awesome human readable machine learning framework
What do you like best about the product?
Tensorflow is free, it's easy to install and get running and also light weight. Best of all Tensorflow is human readable, Unlike most of the other deep learning frameworks out there that make life difficult. Tensorflow is built by Google and integrates seamlessly into all of their existing products making deployments very easy. It's also very fast and efficient backend for models.
What do you dislike about the product?
Like all deep learning frameworks, it requires lots of data to train a network built using it but this is hardly surprising
What problems is the product solving and how is that benefiting you?
I've been able to rapidly develop and deploy several machine learning and deep learning models. Tensorflow also allowed me to accomplish AI related tasks that were previously out of my reach due to the cost of other deep learning frameworks
Recommendations to others considering the product:
With Tensorflow, you can quickly build your machine learning frameworks. It's properly documented and is very easy to use
TensorFlow Review
What do you like best about the product?
- It is easy to use (for adept users)
- It is more often used for research, this gives TensorFlow regular support and updates.
- It is the back-end for one of the easiest frameworks (Keras)
- It is more often used for research, this gives TensorFlow regular support and updates.
- It is the back-end for one of the easiest frameworks (Keras)
What do you dislike about the product?
- It is hard to learn (for beginners in AI)
What problems is the product solving and how is that benefiting you?
I use TensorFlow to build deep learning models for object detection and image classification.
Tensorflow 2.0
What do you like best about the product?
Tensorflow transformed to the best deep learning framework since tensorflow 2.0 it's faster new functionalities and it uses both a dynamic and static flow graph which makes it good for both production and testing
What do you dislike about the product?
I don't really see what I dislike about tensorflow 2.0 it's got everything ready except that it's not so easy to learn
What problems is the product solving and how is that benefiting you?
I used tensorflow in most of my machine learning competitions to create machine learning models mostly image classification models
Recommendations to others considering the product:
I recommend tensor flow to companies that are into machine learning and artificial intelligence it's a good API for these things
Too messy
What do you like best about the product?
The static computational graph is a very good concept. The API usually has implementations available for almost everything you would need.
What do you dislike about the product?
The documentation is not very good. The API is too messed up - there are several functions that do the same thing with minor differences and little documentation about the differences. Boilerplate code is also usually long. The API is cumbersome to use overall.
What problems is the product solving and how is that benefiting you?
I have used tensorflow for several projects related to text classification.
showing 31 - 40