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.
Awesome framework for use of image processing solutions
What do you like best about the product?
Easy to train images and create models which you can use in multiple plateforms like Windows, embedded devices and Mobile applications.
What do you dislike about the product?
Sometime it is hang on medium config system otherwise it is ok.
What problems is the product solving and how is that benefiting you?
Trains and use model for image processing solutions.
- Leave a Comment |
- Mark review as helpful
Perfect for neural networks
What do you like best about the product?
It works wonders when processing image, text and audio data. The documentation is very good and easy to use. With Keras, you can do your deep learning work simply and quickly. Open source. The best software library on the market for deep learning. It's reassuring to have Google behind it. Documentation is being updated. Functional.
What do you dislike about the product?
It's forcing the video card. Detecting and resolving errors is sometimes difficult.
What problems is the product solving and how is that benefiting you?
I can easily process my data with the models I have prepared.
Framework for solving Machine Learning Problem
What do you like best about the product?
The main important thing I like about Tensorflow is, it is Open Source. Anyone can use it and can create multiple Machine Learning applications. I can also visualize my machine learning model in TensorFlow by using Tensorboard. Tensorflow also supports Keras, so we can easily create ML and CNN models using it. Tensorflow is compatible with many programming languages like Java, Python, C++, Ruby etc.
What do you dislike about the product?
One thing I don't like about Tensorflow is, it gives updates regularly. So it becomes a little bit difficult to install new versions. Because sometimes, whatever application I developed may not be supported on a more recent version of Tensorflow.
What problems is the product solving and how is that benefiting you?
I am using Tensorflow for creating Machine Learning and Deep Learning Applications.
Recommendations to others considering the product:
I recommend to the ones who want to develop applications quickly and beginner-friendly.
Best for Neural Network Modelling and Other ML Project
What do you like best about the product?
This is having will defined and organized Classes for NN
What do you dislike about the product?
Sometimes dependencies give error during run time
What problems is the product solving and how is that benefiting you?
I am doing a project that is based on Deep NN and Reinforcement learning
Great framework for production grade model development and deployment
What do you like best about the product?
Tensorflow is a mature framework that offers many valuable features such as Keras, Tensorboard, data processing modules, easy-to-implement multiprocessing, integration with HDFS, and more. Tensorflow has a strong community and very robust documentation. Tensorflow has many time-saving features, such as easily integrated pre-trained model layers. The TensorFlow model hub is one of the best I have seen in terms of ease of finding and using pre-trained models. There are many demos and example notebooks that demonstrate how to use complex and straightforward concepts.
What do you dislike about the product?
Tensorflow has gone through many iterations over the past years, so code maintenance has been an issue. In my opinion, eager execution is a preferred method of developing and debugging networks; however, experience with legacy TensorFlow makes the switch more challenging. Since the deep learning research community favors PyTorch over TensorFlow, researchers generally find state-of-art models and new methodologies implemented in PyTorch.
What problems is the product solving and how is that benefiting you?
We have developed custom models using the Keras API. We have used pre-trained (EfficientNet) models to solve various batch and real-time modeling needs in tabular and image processing learning paradigms. We are also looking into the TensorFlow decision forest package to keep all model development consistent. We use TensorFlow as both an experimental as well as a real-time production platform.
Recommendations to others considering the product:
Start by looking at examples provided by the developers.
Use TensorBoard
Use TensorBoard
I used TensorFlow for my some of course projects
What do you like best about the product?
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 about the product?
I have a windows machine and there is no support for Windows
What problems is the product solving and how is that benefiting you?
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
Using Deep Neurals Nets with a few lines of code
What do you like best about the product?
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.
Also nice: the support for GPUs which really speeds up all computions.
What do you dislike about the product?
The (remants of) older TF versions using weird and sometimes incomprehensible stuff like placeholder, logits, etc.
What problems is the product solving and how is that benefiting you?
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.
Neural network at your hands
What do you like best about the product?
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 about the product?
Required Memory and ram size could be optimized.
What problems is the product solving and how is that benefiting you?
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.
Best way to jump start ML development
What do you like best about the product?
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 about the product?
Its lerning curve is a little steep once you cross the beginners threshold. But can say its the worst :).
What problems is the product solving and how is that benefiting you?
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.
Essential Toolkit for Machine Learning and Deep Learning Research and Development Projects
What do you like best about the product?
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 about the product?
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 is the product solving and how is that benefiting you?
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.
2-Conda's installation facilitate the installation of dependency libraries such as CUDA for the GPU version.
showing 21 - 30