Pruning AI Models for Peak Performance - NVIDIA DRIVE Labs Ep. 31
9 295
17.3
NVIDIA1.55 млн
Следующее
310 дней – 304 7021:28Популярные
190 дней – 403 7433:43
21.03.23 – 96 4652:48Опубликовано 19 сентября 2023, 15:55
Check out HALP (Hardware-Aware Latency Pruning), a new method designed to adapt convolutional neural networks (CNNs) and #transformer-based architectures for real-time performance. HALP optimizes pre-trained models to maximize compute utilization. In testing with NVIDIA DRIVE Orin™ on the road, it consistently outperformed alternative approaches.
00:00:00 - Introducing Hardware-Aware Latency Pruning (HALP)
00:00:29 - Common Model Optimization
00:00:59 - DNN Pruning
00:01:21 - Hardware Aware Latency Pruning
00:01:31 - Classification Tasks
00:01:37 - 3D Object Detection
00:02:04 - HALP with Transformers
00:03:09 - To learn more, visit our GitHub and project pages
GitHub: nvda.ws/3rlM7mo
Product page: nvda.ws/46961je
Watch the full series here: nvda.ws/3LsSgnH
Learn more about DRIVE Labs: nvda.ws/36r5c6t
Follow us on social:
Twitter: nvda.ws/3LRdkSs
LinkedIn: nvda.ws/3wI4kue
#NVIDIADRIVE
00:00:00 - Introducing Hardware-Aware Latency Pruning (HALP)
00:00:29 - Common Model Optimization
00:00:59 - DNN Pruning
00:01:21 - Hardware Aware Latency Pruning
00:01:31 - Classification Tasks
00:01:37 - 3D Object Detection
00:02:04 - HALP with Transformers
00:03:09 - To learn more, visit our GitHub and project pages
GitHub: nvda.ws/3rlM7mo
Product page: nvda.ws/46961je
Watch the full series here: nvda.ws/3LsSgnH
Learn more about DRIVE Labs: nvda.ws/36r5c6t
Follow us on social:
Twitter: nvda.ws/3LRdkSs
LinkedIn: nvda.ws/3wI4kue
#NVIDIADRIVE
Свежие видео
2 дня – 2037:11
2 дня – 7624:29
3 дня – 1410:58
4 дня – 175 52411:37Случайные видео
104 дня – 64 31710:13
191 день – 480 54942:35
13.10.20 – 43 7342:23
31.05.20 – 1 202 8891:57:48
06.02.09 – 11 2501:36:33
1 день – 10 2560:32
3 дня – 9280:04
5 дней – 47 57517:57
10 дней – 700 8704:50
14 дней – 1 9930:51
16 дней – 15 0640:14
10 часов – 22 40031:21