Mahaaveer 🚁🛸🚀🛩️✈️

Aerospace amateur, The roger federer, Arsenal, Space fascinates me so much, photography enthusiast. Wish i was a tennis player.

[Mahaaveer 🚁🛸🚀🛩️✈️ @Mahaaveer]

@NVIDIAGeForce If I had a 5090, i would be using it to develop computer vision applications #RTXPowersplay

[Mahaaveer 🚁🛸🚀🛩️✈️ @Mahaaveer]

@imo_slot_114514 Is L1 good enough with 3-4 days of growth ? I currently have L3 superslant which is too much for me.

[Mahaaveer 🚁🛸🚀🛩️✈️ @Mahaaveer]

@Crazymoments01 AI dogs.

[Pratyush Kumar @pratykumar]

📢 Open-sourcing the Sarvam 30B and 105B models! Trained from scratch with all data, model research and inference optimisation done in-house, these models punch above their weight in most global benchmarks plus excel in Indian languages.

Get the weights at Hugging Face and AIKosh. Thanks to the good folks at SGLang for day 0 support, vLLM support coming soon. Links, benchmark scores, examples, and more in our blog - https://t.co/DcCG3zlN8p

[Mahaaveer 🚁🛸🚀🛩️✈️ @Mahaaveer]

@details_with_ai Yt

[Mahaaveer 🚁🛸🚀🛩️✈️ @Mahaaveer]

@TheAhmadOsman How do you buy 4090s and 3090s ? Where can I buy it safe ?

[Grummz @Grummz]

AMD Ryzen chief teases they are bringing back Zen 3 because of the DDR5 shortage.

This is on the heels of nVidia rumored to be bringing back the 3060.

We going backwards like it’s 2020. 😭

[Mahaaveer 🚁🛸🚀🛩️✈️ @Mahaaveer]

@aiwithjainam AI.

[Mahaaveer 🚁🛸🚀🛩️✈️ @Mahaaveer]

Shoutout to @langvalmall 's Starline Cinemas for their unmatched hospitality

[Mahaaveer 🚁🛸🚀🛩️✈️ @Mahaaveer]

I have never learnt C++ but I'm using it now.

[Rezi @rqobela]

I am very surprised , how many people learn c++ and never use it again.

What is the reason?

[Mahaaveer 🚁🛸🚀🛩️✈️ @Mahaaveer]

@goodreads Hardcover, whenever possible

[Mahaaveer 🚁🛸🚀🛩️✈️ @Mahaaveer]

Long books with a good story and pacing.

[Goodreads @goodreads]

Do you prefer short books or long books?

[Mahaaveer 🚁🛸🚀🛩️✈️ @Mahaaveer]

The Empire of Silence #SunEater

[Goodreads @goodreads]

It's Friday! What are you reading this weekend?

[Mahaaveer 🚁🛸🚀🛩️✈️ @Mahaaveer]

@avhr797 I assumed you picked up blurays of the movies you have already seen and liked. That's why the surprise.

[Mahaaveer 🚁🛸🚀🛩️✈️ @Mahaaveer]

@PINTO03091 My goal is to find the fastest model for C++/TensorRT inference with dynamic batching, strictly under an Apache 2.0 license. Which models should i be looking into as a potential solution ?

[Mahaaveer 🚁🛸🚀🛩️✈️ @Mahaaveer]

@PINTO03091 Greetings! I would like your opinion on selecting models that are compatible with Tensorrt dynamic batch size. I want to deploy a nano model in c++ Tensorrt for basic detection tasks such as vehicles (1/3)

[Mahaaveer 🚁🛸🚀🛩️✈️ @Mahaaveer]

@PINTO03091 I've had good success with RF-DETR Nano for vehicle detection, but I'm unable to export it with dynamic batches. My understanding is that many DETR-based architectures have internal complexities that make dynamic batching for TensorRT deployment a challenge. Any Advice?

[Mahaaveer 🚁🛸🚀🛩️✈️ @Mahaaveer]

@PINTO03091 Understood. I will have to retrain and try. Where can i find this deimv2_hgnetv2_n_wholebody34 weights? or can i retrain with official weights as base ?

[Mahaaveer 🚁🛸🚀🛩️✈️ @Mahaaveer]

@PINTO03091 Thanks for your continued relentless work on computer vision.

[Mahaaveer 🚁🛸🚀🛩️✈️ @Mahaaveer]

@PINTO03091 When exporting with its post-processor, we got a single label_xyxy_score output of shape [N, 300, 6], treating this as [class_id, x_min, y_min, x_max, y_max, score] with normalized [0,1] bbox coordinates and handling all post-processing externally.