StoneAge Waterblast Tools’ Post

Check out this tutorial on "OMVS Commands from ISPF 3.17 (UDList)" by Lionel Dyck https://lnkd.in/eWUZP8Qv

so working with a blank yolo model quantized to int8 was a bad idea.The edge hardware I'm using meant I took some shortcuts as training was taking to long.Anyway I ended up downloading a pre trained model and running conversion to int8 tflite model as I usually just add a class I must say tensorflow just works now on Windows every time I've had to download the tensorflow library I've always resorted to docker. I was going to run onnx but I've had issues in the path going onnx then int8 with models but man tensorflow names are weird so it makes a few flavours you'd say some partial int8 one full int8 the model called yoloint8.tflite isn't the full int8 no no no it's the yolo11_full_interger_quant.tflite. That makes perfect sense why would I stupidly think the model called int8 would be the actual int8 model. But now tensorflow is back again just working on Windows (with some downloaded dependencies onnx,c++) I think it's back to being usefull again for me as it can be packaged and shipped without sending someone to location to get running.

"You Only Look Once: The Mind-Blowing Secrets Behind VoloV8's Unstoppable Performance!" Thanks to its powerful processing capabilities, the cutting-edge object identification algorithm YOLO has almost become the industry standard for object detection in computer vision applications. In the past, object detection methods included sliding windows, RCNN, fast RCNN, and faster RCNN. Explore our #blog here https://lnkd.in/g_6Hy8mg to know about yoloV8 with its improved architecture and state-of-the-art features, its deep learning model allows for extremely accurate object detection in a variety of applications #yoloV8 #objectdetection #machinelearning #computervision #nocodedevelopment

Our NPU optimized 💡, on-device 💻 SLM PhiSilica 🧠 is used by C2D which is now in Windows WIP 🪟 ! Here is some technical background 🔬 on how we accelerated Phi on NPUs: https://lnkd.in/efx6T96z Vivek Pradeep explains how it all works.

Quantization with DirectML helps you scale further on Windows : Activation-Aware Quantization (AWQ) is a technique to identify the top 1% of salient weights that are needed for maintaining model accuracy and then quantize the remaining 99% of weights. This leads to much less accuracy loss with AWQ compared to other techniques.

On our blog check out our second APS Viewer Performance Update: OPFS Cache to improve model loading times. You will be experiencing much faster loading times if you’re using SVF2 as a viewing format. Learn more: https://bit.ly/3ITXB5J

Day - 11 -> project-1 : implementing DL paper [main quest-3] > stared with rnn > read colah's blog on rnn. > wrote a scrapper to get text data. project-2 : Building a computer from scratch [side quest] >read the memory chapter from book.(The Elements of Computing Systems). >tmwr will get into code.

Always the repetitive task and doing same work multiple times is very tough . Copying and pasting from one to another . So having something which shares files between host and virtual machine . Sharing information for different computers. Read my article for some depth info!!! Balemarthy Vamsi Krishna

For SDETs wanting to 1-up their Pytest game, this website provides the best documentation I've seen on both beginner and advanced topics such as Hook manipulation, Async testing, CPU usage profiling fixes, ML project testing, and more!

At the simplest level, memory can be viewed as a 3-step process – encoding, storage, and retrieval. But you’ll see the story gets a lot more complex, and a secret hidden player is doing all the heavy lifting from the shadows. And you can leverage that player’s input, literally, to develop expert-level memory. https://lnkd.in/dwp-7P_p