#tensorflow

[ follow ]
fromInfoWorld
11 hours ago

Google's cheaper, faster TPUs are here, while users of other AI processors face a supply crunch

That doesn't mean it will be all plain sailing for Google and its TPU customers, though: Myron Xie, a research analyst at SemiAnalysis, warned that Google might also face constraints in terms of chip manufacturing capacity at Taiwan Semiconductor Manufacturing Company (TSMC), which is facing bottlenecks around limited capacity for advanced chip packaging. Designed for TensorFlow Ironwood is the seventh generation of Google's TPU platform, and
Artificial intelligence
Software development
fromHackernoon
5 months ago

How TensorFlow Handles Backward Compatibility Across Versions | HackerNoon

Semantic Versioning 2.0 is followed for TensorFlow, indicating compatibility levels defined by MAJOR, MINOR, and PATCH changes.
fromwww.tensorflow.org
2 months ago

Why Your tf.function Isn't Working the Way You Think (and How to Fix It)

The outputs of a tf.function must be return values, and side effects may behave unexpectedly, executing only for the first call with a set of inputs.
Python
#keras
fromHackernoon
2 years ago

The HackerNoon Newsletter: The Tech Behind War Robots' First Sword-Wielding Mech (7/24/2025) | HackerNoon

Peter Thiel's 'Zero to One' has become a cornerstone of startup lore, but it can actively harm innovation by promoting monopolistic tendencies in the tech industry.
Tech industry
Miscellaneous
fromHackernoon
5 months ago

How to Save and Load TensorFlow Models | HackerNoon

Checkpoints save parameter values, while the SavedModel format includes model computation descriptions for deployment.
fromhackernoon.com
3 months ago

TensorFlow's Experimental NumPy Interface Brings Familiarity to Deep Learning

TensorFlow implements a subset of the NumPy API, allowing the execution of NumPy code with acceleration from TensorFlow, providing access to all TensorFlow’s APIs.
Python
#type-promotion
fromHackernoon
1 year ago
Web frameworks

Your One-Stop Guide to All the Type Promotion Changes in TensorFlow 2.15 | HackerNoon

fromHackernoon
1 year ago
Web frameworks

Your One-Stop Guide to All the Type Promotion Changes in TensorFlow 2.15 | HackerNoon

fromHackernoon
5 months ago

Optimizing Machine Learning Models with Precise Gradient Management in TensorFlow | HackerNoon

Controlling gradient recording in TensorFlow enables users to specify which variables are monitored by the GradientTape, enhancing efficiency during complex operations.
Python
Scala
fromhackernoon.com
4 months ago

tf.distribute 101: Training Keras on Multiple Devices and Machines

The article focuses on synchronous data parallelism techniques for training models efficiently across multiple devices using minimal code changes.
#machine-learning
Women in technology
fromHackernoon
1 year ago

The HackerNoon Newsletter: The Double Life of a TensorFlow Function (6/4/2025) | HackerNoon

AI companions are a multi-billion dollar industry, transforming from fantasy to reality.
Reinforcement Learning shapes technology and innovation through its simple yet impactful concept.
Python
fromHackernoon
5 months ago

Loops, Conditionals & AutoGraph: Writing Graph-Friendly TensorFlow Code | HackerNoon

AutoGraph simplifies Python code for TensorFlow, enabling easier control flow.
Scala
fromHackernoon
5 months ago

If TensorFlow Had a Brain, It Would Be Made of Graphs | HackerNoon

Graph execution in TensorFlow improves model performance and supports portability by using tf.Graph, optimizing computations, and enabling execution outside of Python.
Marketing tech
fromHackernoon
2 years ago

The HackerNoon Newsletter: There's No TensorFlow Without Tensors (5/19/2025) | HackerNoon

Twitter is throttling links to Patreon and WhatsApp, impacting traffic.
A new AI model, Chameleon, enhances the integration of text and images, surpassing existing models.
TensorFlow fundamentals are essential for understanding modern AI applications.
Java
fromHackernoon
1 year ago

There's No TensorFlow Without Tensors | HackerNoon

Tensors are immutable multi-dimensional arrays of uniform types.
[ Load more ]