Overview
What is TensorFlow?
TensorFlow is an open-source machine learning software library for numerical computation using data flow graphs. It was originally developed by Google.
TrustRadius Insights
My review on Tensorflow
Tensorflow is built for deep-divers
Get Flowing with TensorFlow
1. Recommendations: selecting the best …
TensorFlow, what else?
TensorFlow: The best library with optimized implementation for deep learning
Predict with confidence : Tensorflow
Tensorflow - a feature rich & easy to use distributed open source ML framework
Tensor Flow Reviews
A must have thing for deep learning
Most advanced deep learning library
Best deep learning tool
My perception of the first year with TensorFlow
A must for deep learning
Best deep learning library which comes with lots of prebuilt features and visualisation tools
Reviewer Pros & Cons
Pricing
What is TensorFlow?
TensorFlow is an open-source machine learning software library for numerical computation using data flow graphs. It was originally developed by Google.
Entry-level set up fee?
- No setup fee
Offerings
- Free Trial
- Free/Freemium Version
- Premium Consulting/Integration Services
Would you like us to let the vendor know that you want pricing?
26 people also want pricing
Alternatives Pricing
What is Qlik Sense?
Qlik Sense® is a self-service BI platform for data discovery and visualization. It supports a full range of analytics use cases—data governance, pixel-perfect reporting, and collaboration. Its Associative Engine indexes and connects relationships between data points for creating actionable insights.
What is Dataiku?
Dataiku is a French startup and its product, DSS, is a challenger to market incumbents and features some visual tools to assist in building workflows.
Product Details
- About
- Tech Details
What is TensorFlow?
TensorFlow Video
TensorFlow Technical Details
Operating Systems | Unspecified |
---|---|
Mobile Application | No |
Comparisons
Compare with
Reviews and Ratings
(52)Community Insights
- Business Problems Solved
- Pros
- Cons
- Recommendations
TensorFlow has proven to be a versatile tool for solving a wide range of problems across various industries. In the healthcare sector, users have utilized TensorFlow for patient monitoring, appointment cancellation, scheduling, and registration, leading to improved efficiency and better patient care. It has also been adopted by multiple departments within organizations to address user-facing business challenges.
Another key use case of TensorFlow is in building complex neural networks, particularly when dealing with large training datasets consisting of millions of data points. This capability makes it invaluable for tasks such as predictive analysis and recommendation engines, enabling more accurate predictions and significant cost savings for businesses.
The application of TensorFlow extends beyond traditional domains as well. For instance, it has been employed for time series analysis in the equity market, allowing traders to make informed decisions based on reliable predictions. Moreover, TensorFlow's powerful deep learning algorithms have facilitated image and video classification tasks, enhancing capabilities in areas like computer vision and object recognition.
In addition to these specific use cases, TensorFlow has found practical applications in diverse scenarios such as developing chatbots that answer queries related to trained documents, predicting product categories from images in e-commerce settings, automating tasks for merchants, and building recommendation systems. Its flexibility is especially evident when traditional models fall short or generate complex solutions.
Furthermore, researchers have leveraged TensorFlow's strengths in natural language processing, image processing, and predictive modeling exercises. The tool's visualization capabilities are highly regarded by users who require efficient model training and tuning with large datasets.
Finally, TensorFlow plays a crucial role in real-time inference products by supporting state-of-the-art machine learning and deep learning models. This allows businesses to deploy cutting-edge solutions that deliver fast and accurate results.
Overall, TensorFlow's wide range of use cases demonstrates its effectiveness in various industries and problem-solving scenarios. Its ability to handle large datasets and develop complex models makes it a valuable asset for those seeking advanced machine learning solutions.
Clear Documentation: Many users have found the documentation for multi-GPU support in TensorFlow to be simple and clear. This has been helpful for users who are new to working with multiple GPUs, as it allows them to easily understand and implement this feature.
Powerful Visualization Tools: Reviewers appreciate the ability to visualize the graph using TensorBoard, as it helps them understand and navigate through complex models. The interactive nature of TensorBoard also allows users to log events and monitor output over time, providing a convenient way to perform quick sanity checks.
Active Community Support: Users highly value the active community surrounding TensorFlow, which has helped them learn faster and overcome obstacles in their development work. The availability of readily available answers and top-notch documentation from the community has been instrumental in ensuring a smooth experience while working with TensorFlow.
Lack of User-Friendliness: Users have expressed that TensorFlow has a steep learning curve and is not as simple as other popular Python libraries. Some users find it difficult to understand concepts like Tensor Graph, which takes a lot of time. Additionally, the implementation of a whole neural network can be time-consuming, leading users to suggest the provision of a wrapper library to simplify the process.
Confusing Error Messages: Error messages from TensorFlow can be difficult to understand and debug, especially for beginners. Some users have found certain error messages hard to decipher, resulting in confusion during troubleshooting.
Complexity in Implementing Models: Users feel that implementing complex architectures can be challenging in TensorFlow. Certain actions require too many lines of code and are not intuitive for non-programming engineers. Users suggest creating more high-level APIs like Keras and providing better support for Keras to address these concerns.
Users commonly recommend the following when using Tensorflow:
-
Start with the provided examples: Users suggest looking at the examples provided by the developers to get started with Tensorflow. This allows users to understand how the framework works and provides a solid foundation for further exploration.
-
Use TensorBoard for visualization: Users recommend utilizing TensorBoard, a built-in tool in Tensorflow, for visualizing and monitoring the training process. It helps users gain insights into the performance of their models and facilitates debugging.
-
Consider using Keras with Tensorflow: Many users find it beneficial to use Keras, a high-level neural networks API, in conjunction with Tensorflow. They suggest using Keras for prototyping before diving into Tensorflow, as it simplifies network building and automates certain processes.
These recommendations highlight the importance of starting with examples, leveraging visualization tools like TensorBoard, and exploring the integration of Keras with Tensorflow for enhanced productivity and efficiency.
Attribute Ratings
Reviews
(1-15 of 15)The big advantage of TensorFlow is also the serving, with TensorFlow serving it is quite easy to deploy the model (literally a matters of minutes with reasonable performance), however performance wise it is not always the best, I often get better throughput with ONNX conversion of the model then deployment with TensorRT at then expense of more intermediary steps (tradeoff depending on the load expected for the model).
I think TensorFlow got a bad wrap in the community due to the handling of the transition from version 1 to version 2 that was a bit chaotic, similarly when Google dropt the support of TensorFlow-Swift fears of "yet another project that Google will kill" intensified, but TensorFlow 2 can still be a good choice for a lot of models especially BERT based (NER, QA, etc.)
Less well suited: - Small project due to the complexity/less resource to learn - New model tends to use Pytorch
My review on Tensorflow
- Model saving and prediction.
- Training is faster.
- It's well documented.
- Create more high level APIs like keras.
- Provide better support for keras.
- Try to decrease model size.
Tensorflow is built for deep-divers
- Integrating with Keras.
- Working on CPU/GPU/TPU neutrally.
- Exporting to TFLite for browsers or edge computing.
- The massive changes between v1 and v2 can be confusing when looking at examples online.
- TensorFlow is losing market ground to PyTorch and JAX.
Get Flowing with TensorFlow
1. Recommendations: selecting the best templates to recommend to users via email in the various countries the company has a market in, over 100 languages supported,
2. User feedback classification: when users provide feedback, natural language processing algorithms implemented in TensorFlow and Keras are used to classify issues so that stakeholders can identify the major issues with a product/product release,
3. Learning-to-rank for search: there is some development on improving search results by switching to deep learning algorithms from a gradient boosting one, and TensorFlow provides that capability, and
4. Computer vision: some experimentation performed on object detection and image classification.
- TensorFlow is fairly easy to use, with adequate tutorials to get any user started quickly.
- Tooling around TensorFlow, such as TensorBoard, is a gold standard: it has made the training and debugging process so much easier compared to most other deep learning platforms.
- Community support for TensorFlow is very good. If there is a problem, there usually is an answer by just a little Googling. Also the documentation for TensorFlow is often top notch.
- Prior to TensorFlow 2.0, setting up data ingestion for TensorFlow can be a huge pain. So much so that TensorFlow Lite and alternatives such as Keras make it more palatable. Things are changing with TensorFlow 2.0 though.
- Some error messages from TensorFlow can be quite difficult to understand. For instance, a recent error using the dot product layer in TensorFlow 2.0 made it seem like there was a problem with data ingestion, but by downgrading to TensorFlow 1.14.0, the problem disappears.
- Tooling with Bazel (our choice for a build tool) in our monorepo is a bit of a nightmare, partly because Bazel has poor Python support. However, we were able to integrate PyTorch easily with Bazel, but not TensorFlow.
- Would love to have better bindings with the JVM, rather than just Python, considering that many companies have a JVM-based stack, making it easier to integrate.
1. Computer vision: image classification, object detection and image generation via generative adversarial networks
2. Natural language processing: text classification and generation.
The good community support often means that a lot of off-the-shelf models can be used to prove a concept or test an idea quickly. That, and Google's promotion of Colab means that ideas can be shared quite freely. Training, visualizing and debugging models is very easy in TensorFlow, compared to other platforms (especially the good old Caffe days).
In terms of productionizing, it's a bit of a mixed bag. In our case, most of our feature building is performed via Apache Spark. This means having to convert Parquet (columnar optimized) files to a TensorFlow friendly format i.e., protobufs. The lack of good JVM bindings mean that our projects end up being a mix of Python and Scala. This makes it hard to reuse some of the tooling and support we wrote in Scala. This is where MXNet shines better (though its Scala API could do with more work).
TensorFlow, what else?
- Data pipeline implementation is quite good, loading large amounts of data and pre-process it in an efficient way is no more issue for us
- It supports all major DL algorithms and network layouts such as ConvNets, RNN, LSTMs, Word2Vec, and even the latest transformer architecture
- The abstraction for the device is perfectly done and its support seamlessly for multiple GPU and even TPU will bring a lot of performance gain for enterprise scoped solution while still keep the flexibility
- The TensorBoard is amazing. I haven't seen a similar thing in other frameworks on the market. It allows us to quickly understand and debug the model with the info visualization which makes understanding much better
- A very supportive community, which is the key for sharing the ideas and find the quick and best solutions
- TensorFlow has its own model and terminology, which is not quite the same as the normal Python styled other frameworks, so in order to master it, the learning curve is a little bit steep, and as a by-product of the fast iteration and release, sometimes the documentation is not quite catching up
- TensoFlow is based on Design Model Then Run Model concept, which means the model itself is static. Maybe it could also borrow some ideas from PyTorch, which is more intuitive and supports dynamic model building
- Detailed and more functional implementation of various algorithms.
- Great visualization under TensorFlow board for training models.
- Multiple GPU support and availability of TPU to train large models.
- Regular updates.
- Large user community.
- Performance issues on a low scale system.
- Complex to debug for multi GPU training of a large model.
- It is not easy to use for new developers compared to other libraries.
- Implementation for complex architecture is difficult.
Predict with confidence : Tensorflow
We also use it for time series analysis to make predictions in the equity market. TensorFlow has been a powerful and easy to deploy tool for various algorithms.
- Support for many libraries and programming languages.
- Ability to use GPU and TPU - hence faster execution.
- Low effort in getting started in development, hence ease of learning.
- Graphic interface to create layers can help beginners.
- Detailed tutorials on what goes behind the scenes in each layer. Currently, the tutorials don't focus on that.
- Better support to integrate with files on the cloud.
It can be avoided when your development stack is Microsoft, as using Azure may provide better integration. Also, if the work requires detailed customization of the algorithm, it may be easier to work directly with Python code and TensorFlow may not help.
- A vast library of functions for all kinds of tasks - Text, Images, Tabular, Video etc.
- Amazing community helps developers obtain knowledge faster and get unblocked in this active development space.
- Integration of high-level libraries like Keras and Estimators make it really simple for a beginner to get started with neural network based models.
- Profiling the TensorFlow (TF) graph for performance optimizations is still a challenge due to lack of proper documentation.
- In our experiments with using TF-GPU on Kubernetes, we see constant memory issues causing nodes to crash.
- There is still a significant learning curve and it's not as simple as other popular Python libraries. Having said that, the TF team and community are actively working on this problem.
- Whenever the problem has the demand for a neural networks based solution, Tensorflow (TF) is a great fit.
- The tf.dataset API makes it really simple to create complex data pipelines in a few lines of code.
- tf.estimators API abstracts all the complex computation graph creation logic making it very simple to get started.
- Eager execution makes it simple to develop a TF graph as debugging the code would be like any other imperative Python program.
- TF abstracts all the complexities of scaling it to multiple machines. It has various code and data distribution algorithms ready to use.
- Projects like TensorBoard make monitoring the training process really easy. It also gives the ability to view embeddings without any extra code. Their What-If is extremely useful for poking and understanding a black box model. It also has tools to visualize data to quickly check for anomalies.
- TF Autograph aims to covert any normal Python code into a distributed program which is quite handy to scale an existing code base.
Tensor Flow Reviews
- Multi-GPU support. It works; the documentation is simple and clear. You’ll still need to figure out how to divide and conquer your problem, but isn’t that part of the fun?
- Training across distributed resources (i.e., cloud). As of v0.8, distributed training is supported.
- Queues for putting operations like data loading and preprocessing on the graph.
- Visualize the graph itself using TensorBoard. When building and debugging new models, it is easy to get lost in the weeds. For me, holding mental context for a new framework and model I’m building to solve a hard problem is already pretty taxing, so it can be really helpful to inspect a totally different representation of a model; the TensorBoard graph visualization is great for this.
- Logging events interactively with TensorBoard. In UNIX/Linux, I like to use tail -f to monitor the output of tasks at the command line and do quick sanity checks. Logging events in TensorFlow allows me to do the same thing, by emitting events and summaries from the graph and then monitoring output over time via TensorBoard (e.g., learning rate, loss values, train/test accuracy).
- Model checkpointing. Train a model for a while. Stop to evaluate it. Reload from checkpoint, keep training.
- Performance and GPU memory usage are similar to Theano and everything else that uses CUDNN. Most of the performance complaints in the earlier releases appear to have been due to using CUDNNv2, so TensorFlow v0.8 (using CUDNNv4) is much improved in this regard.
It's improving imaging analytics and pathology. Machine learning can supplement the skills of human radiologists by identifying subtler changes in imaging scans more quickly, potentially leading to earlier and more accurate diagnoses.
A must have thing for deep learning
- TensorFlow is the best when you are doing some work around deep learning
- You can also use this for natural language processing as it has lot of inbuilt functionality for this.
- It also can be used to clean up the data and for data processing, as it provides lots of functionality for that too.
- It would be much better if they could provide good documentation and easy ways to understand concepts.
- It is difficult to understand the concept behind for example, Tensor Graph, which takes a lot of time.
- As you have to write everything, it is time consuming to write the implementation of whole neural network. It would be better if they can provide some wrapper library to make things easier.
Most advanced deep learning library
- Fast to implement deep learning algorithm
- Fast to train the big model, and easy to deploy on GPU as well
- Provides a lot of inbuilt functionality which helps your development move faster
- You can see dynamic graph, tensor graph, etc. which is helpful
- Long learning curve—it takes a lot of time to learn its basics
- Everything is not easy in this product. It takes a lot of time to develop algorithms, and it's difficult too.
Best deep learning tool
- TensorFlow is very powerful to build the neural networks, it gives you the power to write your own implementation with full customisation.
- It has inbuilt methods which helps a lot when it comes to writing your own implementation of neural networks
- It has lots of inbuilt methods to do the data processing like reading data from a directory as classes using an image data generator etc.
- First and biggest con is that it has a very tense learning curve. Understanding the concept of a tensor, a dynamic graph is difficult and takes a lot of time to learn
- As compared to Keras, TensorFlow takes a lot of time to build and implement a neural network. You have to write everything by yourself.
My perception of the first year with TensorFlow
- Modeling for complex problems with large amounts of data
- Modeling when the client is not interested in building the model patiently in levels
- Guiding what we are doing wrong with other models
- Too many lines of code for some actions
- Not very intuitive for non-programming engineers
A must for deep learning
- Visualizing learning
- Ease of use
- Good documentation
- Simplify distributed learning examples in the Github repo
- Provide more tutorials on distributed training
Best deep learning library which comes with lots of prebuilt features and visualisation tools
- First of all, it is fast. This machine library is faster as compared to other machine learning libraries like Theano.
- It has lots of prebuilt tools in it for data processing, neural network layers like convolution layer, pooling layer etc. It also hase great prebuilt tools for data visualization.
- Easy to deploy its model on GPU. We can train the model created by tensor flow on GPU.
- It can be easily used with wrapper library like Keras which makes it easier to write a machine learning model.
- Initially understanding this library is bit difficult. It has a steep learning curve.
- Sometime the error messages are difficult to understand and debug. So that should be made clear such that even a beginner can solve the issue quickly.
- Writing models with TensorFlow only is a bit difficult. So, it's easier to use this with a wrapper library like Keras.