HackerNoon<p>Speed up your TensorFlow training by optimizing input pipelines with tf.data. Learn how prefetching, caching, and vectorization make a difference. <a href="https://hackernoon.com/youre-wasting-gpu-powerfix-your-tensorflow-input-pipeline-today" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">hackernoon.com/youre-wasting-g</span><span class="invisible">pu-powerfix-your-tensorflow-input-pipeline-today</span></a> <a href="https://mas.to/tags/tensorflow" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tensorflow</span></a></p>
Recent searches
Search options
#tensorflow
0 posts0 participants0 posts today
Learn how to use TensorFlow’s RaggedTensor for indexing, broadcasting, and handling uneven shapes in deep learning workflows. https://hackernoon.com/the-shape-of-data-broadcasting-indexing-and-encoding-with-raggedtensors #tensorflow
hackernoon.comThe Shape of Data: Broadcasting, Indexing, and Encoding with RaggedTensors | HackerNoonLearn how to use TensorFlow’s RaggedTensor for indexing, broadcasting, and handling uneven shapes in deep learning workflows.
Learn how to save, restore, and inspect TensorFlow models using checkpoints and tf.train.Checkpoint for robust training and deployment. https://hackernoon.com/how-to-save-and-load-tensorflow-models #tensorflow
hackernoon.comHow to Save and Load TensorFlow Models | HackerNoonLearn how to save, restore, and inspect TensorFlow models using checkpoints and tf.train.Checkpoint for robust training and deployment.
Master randomness in TensorFlow with tf.random.Generator and stateless RNGs. Learn best practices for reproducibility, distribution, and saving states. https://hackernoon.com/randomness-as-defined-by-machine-learnings-most-popular-language #tensorflow
hackernoon.comRandomness As Defined by Machine Learning’s Most Popular Language | HackerNoonMaster randomness in TensorFlow with tf.random.Generator and stateless RNGs. Learn best practices for reproducibility, distribution, and saving states.
Learn to build and use custom C++ operations in TensorFlow, from kernel creation to Python integration—covering CPU, GPU, and Bazel builds. https://hackernoon.com/why-and-how-developers-extend-tensorflow-with-custom-kernels #tensorflow
hackernoon.comWhy and How Developers Extend TensorFlow With Custom Kernels | HackerNoonLearn to build and use custom C++ operations in TensorFlow, from kernel creation to Python integration—covering CPU, GPU, and Bazel builds.
Explore TensorFlow NumPy: seamless interoperability, fast gradients, tf.function boosts, device control, and performance gains over classic NumPy. https://hackernoon.com/why-tensorflow-numpy-might-be-the-future-of-differentiable-programming #tensorflow
hackernoon.comWhy TensorFlow NumPy Might Be the Future of Differentiable Programming | HackerNoonExplore TensorFlow NumPy: seamless interoperability, fast gradients, tf.function boosts, device control, and performance gains over classic NumPy.
tf.keras.layers.RandomRotation specifies the rotation as a fraction of 2*pi radians. Is this the work of a subversive tauist?
#Mozilla stellt #DeepSpeech ein.
DeepSpeech ist eine quelloffene, lokale #Sprache-zu-Text-Engine, die mit #Machine #Learning unter Verwendung des #TensorFlow-Frameworks erstellt wurde. Es ist in Verbindung mit der ebenfalls von #Mozilla zusammengestellten Stimmdatenbank Common Voice Corpus bereits auf einem Raspberry Pi 4 in Echtzeit lauffähig.
LinuxNews.de · Mozilla stellt DeepSpeech ein
More from 
LinuxNews.de
) Anyone smart enough to understand this error?
This is #Python with #Keras / #Tensorflow running in #Anaconda PowerShell. I have too little expert knowledge to quite understand this error.
"indices[14,6] = -2147483648 is not in [0, 21)" hints that somewhere there's an integer overflow, maybe? Idk what this sentence means
![[screenshot of codeblock]
# 31-mer coding
def coding(mers):
# amino acid dictionaries
dic = {'A':0, 'C':1, 'D':2, 'E':3, 'F':4, 'G':5, 'H':6, 'I':7, 'K':8,
'L':9, 'M':10, 'N':11, 'P':12, 'Q':13, 'R':14, 'S':15, 'T':16,
'V':17, 'W':18, 'Y':19, 'Z':20}
# coding
vectors = []
for mer in mers:
coded_mer = [dic.get(aa) for aa in mer]
vectors += [coded_mer]
return vectors](https://cdn.masto.host/fribygdano/media_attachments/files/114/748/938/039/526/795/original/221af11b41cb9bfa.png "[screenshot of codeblock]
# 31-mer coding
def coding(mers):
# amino acid dictionaries
dic = {'A':0, 'C':1, 'D':2, 'E':3, 'F':4, 'G':5, 'H':6, 'I':7, 'K':8,
'L':9, 'M':10, 'N':11, 'P':12, 'Q':13, 'R':14, 'S':15, 'T':16,
'V':17, 'W':18, 'Y':19, 'Z':20}
# coding
vectors = []
for mer in mers:
coded_mer = [dic.get(aa) for aa in mer]
vectors += [coded_mer]
return vectors")
![[screenshot of codeblock]
# extract all the 31-mers
mers = []
for line in data:
seqs = re.split('[\t,]', line[1])[1:]
mers += [mer for mer in seqs if len(mer) > 1] # mer != '' or '*'
print("There are %s candidate cleavage sites." % len(mers))
# predicting probabilities of all the sites
x_mers = np.array(coding(mers))
mers_pred = loaded_model.predict(x_mers)](https://cdn.masto.host/fribygdano/media_attachments/files/114/748/940/467/656/240/original/87c4120301033586.png "[screenshot of codeblock]
# extract all the 31-mers
mers = []
for line in data:
seqs = re.split('[\t,]', line[1])[1:]
mers += [mer for mer in seqs if len(mer) > 1] # mer != '' or '*'
print(\"There are %s candidate cleavage sites.\" % len(mers))
# predicting probabilities of all the sites
x_mers = np.array(coding(mers))
mers_pred = loaded_model.predict(x_mers)")
Keynote announcement for Plone Conference 2025 and PyCon Finland 2025: "Muuttolintujen Kevät - Automatic Bird Sound Classifier" by Patrik Lauha from Helsinki University! 
Discover how an innovative convolutional neural network, trained in Python with TensorFlow, identifies vocalizations from 263 Finnish bird species.
https://2025.ploneconf.org/news/keynote-muuttolintujen-kevat-automatic-bird-sound-classifier
Keynote announcement for Plone Conference 2025 and PyCon Finland 2025: "Muuttolintujen Kevät - Automatic Bird Sound Classifier" by Patrik Lauha from Helsinki University!
Discover how an innovative convolutional neural network, trained in Python with TensorFlow, identifies vocalizations from 263 Finnish bird species.
https://2025.ploneconf.org/news/keynote-muuttolintujen-kevat-automatic-bird-sound-classifier
Finally found time to continue work on the Rockchip NPU. Plan to give this a strong push in the next few months:
https://blog.tomeuvizoso.net/2025/05/rockchip-npu-update-5-progress-on.html
blog.tomeuvizoso.netRockchip NPU update 5: Progress on the kernel driver It has been almost a year since my last update on the Rockchip NPU, and though I'm a bit sad that I haven't had more time to work on it, I...
Setting up TensorFlow Lite for Raspberry Pi High Quality Camera and compiling rpicam-detect was surprisingly complicated. Installing a .deb and manually writing the .pc file worked in the end.
These links are helpful:
https://lindevs.com/install-precompiled-tensorflow-lite-on-raspberry-pi/
https://github.com/raspberrypi/rpicam-apps/issues/622
lindevs.com · Install Precompiled TensorFlow Lite 2.19 on Raspberry Pi…
NEW Paper: #Modelling #NeuralNetwork Models + generators for #TensorFlow and #PyTorch
https://modeling-languages.com/modelling-neural-network-models/
Part of the latest BESSER release https://github.com/BESSER-PEARL/BESSER/releases
PyCharm thinks I have TensorFlow 2.19 installed, but the official TensorFlow site thinks the most recent version is 2.17.
MCP, Agentic Knowledge Graphs & AI Models: Solving Conversational Analytics
In this free webinar led by ex-Snowflake, Cloudera, and Amazon leaders, we'll unveil how cutting-edge LLMs (GPT 4.5, Sonnet 3.7, Deepseek V3/R1, Gemini 2.5, etc.) are revolutionizing data products.
#python #machinelearning #deeplearning #ai #developer #dev #devsecops #devops #mlops #learn #learning #study #git #github #codeberg #tensorflow #pytorch #jax #huggingface #linux #ubuntu #popos #llm
EventbriteMCP, Agentic Knowledge Graphs & AI Models: Solving Conversational AnalyticsCo-hosted by Gunther Hagleitner and Wangda Tan, former engineering and product leaders at Snowflake, Cloudera, & Cribl. Founders of Waii.ai.
𖤐AlderForrest 𖤐 Heitetääs nopia pallo tänne: onko olemassa #EU vastinetta AI-tunnistusmalleille objektien tunnistamiseen mallia #YOLO tai #tensorflow?
A message you do not want to see when loading "just data" in your AI / ML framework. Beware!
Description in comments.
Continued thread
Here's my presentation where I explored #tensorflow to make a neural network spatial curve based on an autoencoder.
https://www.youtube.com/watch?v=S_8_trOCVjI
You can follow along with my code diffs. https://github.com/RangerMauve/neural-spatial-curves/commits/default/
I've been using generative #AI for over two years now –a few months before, I was struggling to understand the Python #TensorFlow #neuralNetwork library, without much success 
– and I'm increasingly convinced that the exponentially incredible increase in AI capabilities is leading us to a wild socioeconomic shift in a very short time, especially in the field of #work 
; and let's not even talk about Public Administration, where we're stuck with labor models and future aspirations that will be completely inconsequential and insignificant in no time 
–our foresight is truly laughable 
.
Neural networks learn 
, they aren't programmed; the generation of knowledge beyond the original training data is already becoming a reality 
; completely autonomous and intelligent #robotics is right here 
. In short, we need to get our act together and stop thinking it's not a big deal... It's a huge deal
! In the West, work as we know it is going to end –unless there's a nuclear cataclysm first 
– and we better start fighting for our piece of the pie 
."
-
Llevo usando #IA generativa desde hace más de dos años –ya unos meses antes me peleaba por entender un poco la librería de #redesNeuronales TensorFlow de Python, sin conseguirlo demasiado – y cada vez estoy más convencido de que el aumento de capacidades de las IAs, que es increiblemente exponencial 
, nos dirige a un cambio socioeconómico salvaje en muy poco tiempo, especialmente en el campo del #trabajo 
; y no digamos en la Administración Pública, que estamos con modelos laborales y con pretensiones de futuro que serán completamente intrascendentes e insignificantes en nada de tiempo –desde luego nuestra capacidad de prospectiva es de llorar 
.
Las redes neuronales aprenden , no se programan; la generación de conocimiento alejada de los datos de entrenamiento originales 
empieza a ser ya real; la #robótica 
completamente autónoma e inteligente está ahí al lado. En fin, que ya nos podemos poner las pilas y dejar de pensar que no es para tanto... ¡Es para más! 
. En occidente se va a acabar el trabajo tal y como lo conocemos –si no hay un cataclismo nuclear antes 
– y ya podemos ir peleando para que nos toque un trozo del pastel 
.
