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.
Reviewing Tensorflow
What do you like best about the product?
It's easy to integrate pre-trained models for building up the starter projects and tensorflow.js helped me out for integrating it directly into the browser.
What do you dislike about the product?
There were compatibility issues between different versions, to convert code from Tensorflow 1.0 to Tensorflow 2.0. Although change was good but it need now some changes to be made in order to make it compatible.
What problems is the product solving and how is that benefiting you?
I have used Tensorflow in building crop disease identification using lightweignt Convolutional Neural Network model. Building own Convolutional block seemed pretty easy using Tensorflow.
- Leave a Comment |
- Mark review as helpful
Tensorflow the deep learning tool
What do you like best about the product?
The libraries available in that library ,the convince it provides for creating Neural network model .
What do you dislike about the product?
No dislikes ,it's the best tool for Deep Learning
What problems is the product solving and how is that benefiting you?
By providing the essential tools and libraries for building or crafting deep learning models .
What an amazing library
What do you like best about the product?
The way it handles the data and the community support it has is a god sent. Developing and maintaining the code base is really easy with tensorflow. And with v2 it's just amazing.
What do you dislike about the product?
I think for a person just entering the industry it's somewhat difficult to understand. Sometimes the documentation is really confusing and you have to search if someone has explained it for you to understand it better.
What problems is the product solving and how is that benefiting you?
I am a machine learning engineer and hardly a day goes by when I don't have to use tensorflow because all our algorithms are written with tensorflow because of it's amazing community support.
Tensorflow is the key to AI
What do you like best about the product?
Tensorflow is the best library to work with neural networks and building model architecture. The functional API along with other functionalities makes it easy to define any model from easy to complex and train with ease.
What do you dislike about the product?
Tensorflow needs to add some development in context of memory. In order to deploy any model it takes around 400mb memory for just tensorflow lib. This is the only part which holds me back sometimes.
What problems is the product solving and how is that benefiting you?
It allows us to build model architecture in AI from easy to complex with simplicity. It really helps to perform EDA through the TFX library and build AI models with minimal code.
Worked with computer vision project using tensorflow
What do you like best about the product?
In tensorflow there have lots of methods for many purpose. And in tf you can do anything about deep learning.
What do you dislike about the product?
Tensorflow can build own UI for managing models and all.
What problems is the product solving and how is that benefiting you?
I am using tensorflow for training for deep neural nets for medical diseases detection and it quite perform well because I did lots of things by using tf thats why
Train complex Machine learning model with ease by using tensorflow !
What do you like best about the product?
TensorFlow is flexible. It provides a platform for building and deploying machine learning models across a wide range of devices and media, and Tensorflow is really scalable, running on a single device to distributed systems with thousands of GPUs
What do you dislike about the product?
A few things I dislike about TensorFlow are it is resource intensive; TensorFlow is really resource intensive. It requires high computational power and a powerful GPU. the second thing is the learning curve TensorFlow can have a steep learning curve for beginners due to its complexity
What problems is the product solving and how is that benefiting you?
We were using TensorFlow to build a machine learning modal which can recognise potholes on roads using artificial intelligence and machine learning; we created it using python.
a gpu based deep learning library by Google for python,c++ and java programmer.
What do you like best about the product?
It provides all the recent algorithms that can run on a Convolutional neural network model. It provides training algorithms, metrics and optimizers for the deep learning algorithm.
What do you dislike about the product?
Python version of TensorFlow runs only on GPU-based processors.
What problems is the product solving and how is that benefiting you?
It is a python, java and C++-based deep learning library that can help us solve data science and machine learning problems.
Excellent Machine Learning Library
What do you like best about the product?
Tensorflow has several intuitive methods for implementing machine learning algorithms. I personally like to use the image classification section to understand how to detect patterns in supervised data.
What do you dislike about the product?
I think there is still some room for improvement in terms of readability. In particular, it feels like many of TensorFlow's commands don't follow a "pythonic" pattern.
What problems is the product solving and how is that benefiting you?
Tensorflow is trying to make machine learning easier to implement for anybody who is just learning and understanding. Tensorflow is also allowing seasoned veterans to implement ML algorithms with ease.
A solid framework for deep neural networks
What do you like best about the product?
One of the best features of Tensorflow is its ability to perform multicore training of models. Unlike the old frameworks, TF doesn't rely on single CPU training rather it allows distributed training of models which drastically decreases the training time we have several GBs of images to be trained for diffusion models.
What do you dislike about the product?
When developers are using Windows for development there are certain issues with the Python pip packages that are part of TF. There is no native support for Decision forests which is one of the most popular packages that is supported by other frameworks. I train la
What problems is the product solving and how is that benefiting you?
I train large amounts of data for classification and the old frameworks that run on single-core training consume several hours to just train a couple of GBs of images whereas when I train it on tensorflow it reduces the time by almost 50% with distributed training.
TensorFlow: Beginner friendly and Production Ready
What do you like best about the product?
Easy to get started with. The TensorFlow ecosystem provides support tools to load data efficiently (TF Dataloaders) , build models (Keras), Optimize it (TF Lite), and Deploy and monitor (TFX) and it is production-ready.
What do you dislike about the product?
One concern I have is inconsistent APIs and functions. Confusion with TF 1 and TF 2. Lots of duplicate and redundant methods. Code customization for research purposes.
What problems is the product solving and how is that benefiting you?
I am a Deep Learning Engineer and Educator. TF helps to build Neural Network models with less code using Keras API. Since Google is backing TensorFlow is robust for production level applications.
showing 1 - 10